Tool recommendation method and device, electronic equipment, storage medium and program product

Abstract

The invention provides a tool recommendation method and device, electronic equipment, a storage medium and a program product, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring post data of a target employee, training data related to tool use skills, first behavior data of the target employee in a tool system, and second behavior data of a post type to which the target employee belongs in the tool system; obtaining a first weight applied by the target tool in the corresponding at least one target work business scene, and obtaining a second weight of the employee of the post type participating in the target work business scene; obtaining a tool skill gap index of the target employee; determining a first recommendation score of the target tool according to the first weight, the second weight and the tool skill gap index; determining a recommendation tool of the target employee from the target tools according to the first recommendation score of each target tool; and outputting the recommendation tool. According to the method, the tool recommendation accuracy is improved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a tool recommendation method, apparatus, electronic device, storage medium, and program product. Background Technology

[0002] The bank's internal digital tools system provides employees with a variety of digital tools. In this system, recommenders pre-configure multiple digital tools for each job type, creating a tool recommendation list for employees in that job type. Employees in the same job type have the same tool recommendation list. Therefore, preset digital tools are recommended to employees based on their job type. For example, if employee A and employee B both belong to the customer manager group, their tool recommendation lists will be the same.

[0003] However, employee A and employee B may have different business focus areas; for example, employee A might be more sales-oriented, while employee B might be more operations-oriented. The same tool recommendation list cannot dynamically adapt to each employee. Therefore, the accuracy of tool recommendation methods in related technologies is relatively low. Summary of the Invention

[0004] This application provides a tool recommendation method, apparatus, electronic device, storage medium, and program product to solve the technical problem of low accuracy in tool recommendation methods in related technologies.

[0005] Firstly, this application provides a tool recommendation method, including:

[0006] The system acquires the target employee's job data, training data related to tool usage skills, the target employee's first behavior data in the tool system, and the target employee's job type in the tool system as a second behavior data; wherein, different job types have different ranges of tools that can be used when working.

[0007] For at least one target tool in the tool system, obtain the first weight of the target tool in the corresponding at least one target work business scenario;

[0008] Based on the second behavioral data, obtain the second weight of the employee of the job type participating in the target work business scenario;

[0009] Based on the job data, the training data, and the first behavioral data, the tool skills gap index of the target employee is obtained, which represents the degree of lack of the target employee in terms of the skills required for the job.

[0010] Based on the first weight, the second weight, and the tool skills gap index, a first recommendation score for the target tool is determined;

[0011] Based on the first recommendation score of each of the target tools, determine the recommender tool for the target employee from among the target tools;

[0012] Output the recommended tool.

[0013] Optionally, determining the first recommendation score for the target tool based on the first weight, the second weight, and the tool skills gap index includes:

[0014] Based on the first weight and the second weight, a second recommendation score is determined to recommend the target tool to employees of the job type;

[0015] The weighted sum of the second recommended score and the tool skills gap index is determined as the first recommended score.

[0016] Optionally, obtaining the second weight of employees of the job type participating in the target work business scenario based on the second behavioral data includes:

[0017] From the second behavioral data, obtain the first number of operations performed by employees of the job type in the target work scenario, and the total second number of operations performed by employees of the job type to which the target employee belongs;

[0018] Based on the first number of operations and the second number of operations, obtain the operation weight of the employee of the job type in the target work business scenario;

[0019] The weighted sum of the historical weights of employees of the job type in the target work scenario and the operational weights is determined as the second weight.

[0020] Optionally, obtaining the operation weights of employees of the job type in the target work scenario based on the first number of operations and the second number of operations includes:

[0021] Obtain the ratio of the first number of operations to the second number of operations;

[0022] The operation weight is obtained by multiplying the ratio of the number of operations by the business scenario coefficient. The business scenario coefficient represents the weight of the target work business scenario in the total work business scenarios.

[0023] Optionally, obtaining the tool skills gap index of the target employee based on the job data, the training data, and the first behavioral data includes:

[0024] Based on the first behavioral data and the training data, obtain the target employee's operational mastery score of the skills required for the job;

[0025] Based on the training data, the target employee's knowledge score of the tools and skills required for the job is obtained;

[0026] The actual mastery of the tool skills by the target employee is obtained by weighting the operation mastery score and the knowledge mastery score.

[0027] Based on the job data, determine the target mastery level of the tool skills required for the job, and based on the target mastery level and the actual mastery level, obtain the tool skills gap index of the target employee.

[0028] Optionally, the method further includes:

[0029] Based on the first behavioral data, the operation error rate of the target employee is obtained, and the knowledge mastery score is updated based on the operation error rate.

[0030] Optionally, obtaining the target employee's operational mastery score for the skills required for the job based on the first behavioral data and the training data includes:

[0031] Based on the first behavioral data, obtain the operation score corresponding to the operation depth of the target employee's operation tool; the operation depth includes: browsing, configuration, and invocation.

[0032] Based on the training data, obtain the training certification level score of the target employee;

[0033] The operation mastery score is obtained based on the operation score and the level score.

[0034] Optionally, the method further includes:

[0035] Based on the behavioral data related to the operation depth, obtain the adoption rate for executing the operation depth;

[0036] If the adoption rate is greater than the adoption threshold, update the operation score corresponding to the operation depth.

[0037] Optionally, the method further includes:

[0038] Get the click rate of the target tool for employees of the specified job type in the specified target work business scenario;

[0039] If the click-through rate is less than the click threshold, the second weight is updated based on the click-through rate, and the first recommendation score of the target tool is updated.

[0040] Optionally, the method further includes:

[0041] Obtain the usage rate of the target tool by the target employees;

[0042] If the usage rate is greater than the usage threshold, the weight of the tool skills gap index in the weighted sum of the second recommendation score and the tool skills gap index is updated according to the usage rate, and the first recommendation score of the target tool is updated.

[0043] Secondly, this application provides a tool recommendation device, comprising:

[0044] The first acquisition module is used to acquire the target employee's job data, training data related to tool usage skills, the target employee's first behavior data in the tool system, and the target employee's job type in the tool system as a second behavior data; wherein, different types of jobs have different ranges of tools that can be used when working;

[0045] The second acquisition module is used to acquire, for at least one target tool in the tool system, the first weight of the target tool in the corresponding at least one target work business scenario;

[0046] The third acquisition module is used to acquire, based on the second behavioral data, the second weight of employees of the job type participating in the target work business scenario;

[0047] The fourth acquisition module is used to acquire the tool skills gap index of the target employee based on the job data, the training data and the first behavior data. The tool skills gap index represents the degree of lack of the target employee in terms of the skills required for the job.

[0048] The first determining module is used to determine the first recommendation score of the target tool based on the first weight, the second weight, and the tool skills gap index.

[0049] The second determining module is used to determine the recommending tool for the target employee from the target tools based on the first recommendation score of each target tool;

[0050] The output module is used to output the recommendation tool.

[0051] Thirdly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0052] The memory stores computer-executed instructions;

[0053] The processor executes computer execution instructions stored in the memory to implement the method as described in any of the first aspects.

[0054] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any of the first aspects.

[0055] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the method described in any of the first aspects.

[0056] The tool recommendation method, apparatus, electronic device, storage medium, and program product provided in this application acquire target employee job data, tool usage skills-related training data, target employee first behavior data in the tool system, and target employee job type second behavior data in the tool system; for at least one target tool in the tool system, acquire a first weight for the application of the target tool in at least one corresponding target work business scenario; based on the second behavior data, acquire a second weight for employees of job type participating in the target work business scenario; based on the job data, training data, and first behavior data, acquire the target employee's tool skills gap index; based on the first weight, second weight, and tool skills gap index, determine a first recommendation score for the target tool; based on the first recommendation scores of each target tool, determine the recommended tool for the target employee from the target tools; and output the recommended tool. The method of this application determines the recommendation score of the target tool based on the weight of the target tool's application in the target work business scenario, the weight of the employee's participation in the target work business scenario by job type, and the degree of lack of skills required by the target employee for the job. The recommendation score of the target tool changes according to the relevant data of each target employee. By recommending tools to target employees based on the first recommendation score of each target tool, the method can dynamically adapt to target employees and improve the accuracy of tool recommendations. Attached Figure Description

[0057] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0058] Figure 1 A flowchart illustrating the tool recommendation method provided in the embodiments of this application. Figure 1 ;

[0059] Figure 2 A flowchart illustrating the method for obtaining the second weight provided in an embodiment of this application;

[0060] Figure 3 A flowchart illustrating the method for obtaining the tool skills gap index provided in this application embodiment;

[0061] Figure 4 A flowchart illustrating a tool recommendation method provided in this application embodiment. Figure 2 ;

[0062] Figure 5 This is a schematic diagram of the structure of a tool recommendation device provided in an embodiment of this application;

[0063] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0064] The accompanying drawings have illustrated specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to specific embodiments. Detailed Implementation

[0065] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0066] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with the relevant laws, regulations, and standards of the relevant countries and regions, have taken necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation portals for users to choose to authorize or refuse.

[0067] Furthermore, the technical solution involved in this application, which involves big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.) and the use of artificial intelligence technology for automated decision-making, and makes decisions that have a significant impact on personal rights based on the results of automated decision-making, provides users with corresponding operation entry points for users to choose to agree to or reject the results of automated decision-making; if the user chooses to reject, the process will proceed to the expert decision-making process.

[0068] It should be noted that the tools, methods, apparatus, electronic devices, storage media, and program products provided in this application can be used in the field of artificial intelligence technology, or in any field other than artificial intelligence technology. The application fields of the tools, methods, apparatus, electronic devices, storage media, and program products in this application are not limited.

[0069] In related technologies, the tool recommendation lists in digital intelligence tool systems are pre-configured by recommenders for each job type, and employees in the same job type have the same tool recommendation list. However, employees in the same job type may have different business scenario preferences, and the same tool recommendation list cannot dynamically adapt to each employee. Therefore, the accuracy of tool recommendation methods in related technologies is relatively low.

[0070] In view of this, this application proposes a tool recommendation method. For at least one target tool in a tool system, it obtains a first weight for the application of the target tool in at least one corresponding target work scenario, and a second weight for employees of the target employee's job type participating in the target work scenario. It also obtains a tool skill gap index representing the degree of skill deficiency of the target employee for the job requirements. Based on the first weight, the second weight, and the tool skill gap index, it determines a first recommendation score for the target tool. Based on the first recommendation scores of each target tool, it determines the recommended tool for the target employee from the target tools and outputs the recommended tool. In this method, the recommendation score of the target tool is based on the weight of the target tool's application in the target work scenario, the weight of employees of the target employee's job type participating in the target work scenario, and the degree of skill deficiency of the target employee for the job requirements. The recommendation score of the target tool changes with changes in the relevant data of each target employee. Recommending tools to target employees based on the first recommendation scores of each target tool can dynamically adapt to the target employees and improve the accuracy of tool recommendations.

[0071] This application's embodiments apply to applications, websites, or mini-programs with tool recommendation functionality. The tool recommendation function is implemented within the application, website, or mini-program. For example, a website for recommending tools might have a tool recommendation list for recommending tools to employees, configured through a tool recommendation method. Another example is a third-party application that implements the tool recommendation function by calling the tool recommendation method through an application programming interface (API). The following explanation uses a tool system as the executing entity.

[0072] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0073] Figure 1 A flowchart illustrating the tool recommendation method provided in the embodiments of this application. Figure 1 .like Figure 1 As shown, document translation methods may include:

[0074] S101. Obtain the target employee's job data, training data related to tool usage skills, the target employee's first behavior data in the tool system, and the target employee's job type in the tool system as a second behavior data.

[0075] Job data refers to information related to an employee's job position. For example, job data may include the job type and the skills required for the position. For instance, human resources job data might include information related to risk data interpretation and customer profiling analysis.

[0076] Training data refers to data related to employee participation in training. For example, training data may include employee progress in courses, course exam scores, and course certification data.

[0077] A tool system is a system used to recommend tools to employees, who can then use these tools. For example, a tool system may include drawing tools, attendance tools, and statistical tools.

[0078] Behavioral data refers to the data recorded by employees on tools and systems. For example, behavioral data can include the tools used, the duration of the operation, the content of the operation, and the work scenario. Different types of positions have different ranges of tools available, therefore, the behavioral data for different types of positions will differ.

[0079] For example, the tool system can obtain the job data of target employees in the human resources system by calling the interface provided by the human resources system. The tool system can also obtain the training data of target employees in the training system by calling the interface provided by the training system. This training data may include course completion rates, exam scores, etc. The tool system can also obtain first-behavioral data and second-behavioral data from the data points embedded in the tool system. For instance, from the obtained job data of target employees, the tool system can obtain the job type of the target employee, obtain the first-behavioral data of the target employee in the tool system based on the target employee's identifier, and obtain the second-behavioral data of the job type of the target employee in the tool system based on the target employee's job type.

[0080] For example, the tool system can obtain the target employee's job data from the human resources database, the target employee's training data from the training database, and the first and second behavior data from the tool system's logs.

[0081] S102. For at least one target tool in the tool system, obtain the first weight of the target tool in the corresponding at least one target work business scenario.

[0082] Work scenarios refer to the different environments in which one works. Examples include marketing, operations, and security.

[0083] Each target tool can be applied to at least one work business scenario. For example, some functions of target tool A can be used for marketing, and some functions can be used for operations.

[0084] Each tool has a different weight in different target work scenarios, and the weight of each tool in different work scenarios can be set in advance. The first weight is the weight of the target tool in at least one corresponding target work scenario, which represents the preference of the target tool for the target work scenario.

[0085] For example, the tool system can set the weight of the target tool in at least one corresponding target work business scenario based on the function of the target tool. For instance, if 50% of the functions of the target tool are available in the marketing work business scenario and 50% are available in the operations work business scenario, the first weight of the target tool in the marketing target work business scenario can be set to 0.5, and the first weight of the target tool in the operations target work business scenario can also be set to 0.5.

[0086] For example, the tool system can set the weight of the target tool in at least one corresponding target work scenario based on the application frequency of the target tool. For instance, in the historical data of the target tool's application, the number of times the target tool is used in each work scenario can be obtained, and the first weight of each work scenario can be determined according to the percentage of times it is used.

[0087] S103. Based on the second set of data, obtain the second weight of employees of different job types participating in the target work business scenario.

[0088] The second weight of employee participation in the target work business scenario by job type is the weight of the tool application system of the employee to which the target employee belongs in participating in the target work business scenario, which represents the preference of employees of that job type in participating in the target work business scenario.

[0089] For example, for any target business scenario, the total number of times employees of that job type clicked the tool is obtained from the second behavior data, and the number of operations belonging to the target work business scenario is obtained from the number of operations. The ratio of the number of operations in the target work business scenario to the total number of operations is determined as the second weight.

[0090] For example, for any target business scenario, the total operation time of the employee application tools for that job type is obtained from the second behavior data, and the total operation time belonging to the target work business scenario is obtained from the total operation time. The ratio of the operation time in the target work business scenario to the total operation time is determined as the second weight.

[0091] S104. Based on job data, training data, and first behavior data, obtain the tool skills gap index for target employees.

[0092] The tool skills gap index represents the degree to which target employees lack the skills required for their positions.

[0093] For example, the tool system can obtain the operational mastery score of the target employee for the skills required for the job based on the first behavioral data and training data. Based on the target employee's training data, it can obtain the knowledge mastery score of the target employee for the tool skills required for the job. For instance, the target employee's percentage score for tool skill-related courses can be converted to a ten-point scale to obtain the knowledge mastery score.

[0094] Furthermore, the tool system can obtain the target employee's actual mastery of tool skills by weighting the operation mastery score and knowledge mastery score, and obtain the target employee's tool skills gap index based on the target mastery and the actual mastery.

[0095] For example, the tool system can also obtain the tool skills gap index of the target employee based on a classification model. For instance, a classification model is trained based on training data. The trained model can then determine the level of each tool skill required for the target employee's position based on the training data and the first-behavior data. For any given tool skill, if the level of the tool skill required for the position is greater than the level of the target employee's tool skill, the difference between the required level and the target employee's tool skill level is determined as the target employee's tool skills gap index. If the level of the tool skill required for the position is less than or equal to the level of the target employee's tool skill, then the target employee's tool skills gap index is 0.

[0096] For example, each tool skill can be categorized into levels 1 to 10. Based on training data and first-person behavior data, the classification model assigns a risk data interpretation level of 3 and a customer profile analysis level of 5. Further, the job data yields a risk data interpretation level of 5 and a customer profile analysis level of 5, respectively. The target employee's risk data interpretation gap index is 2, and the customer profile analysis gap index is 0.

[0097] S105. Based on the first weight, the second weight, and the tool skills gap index, determine the first recommended score for the target tool.

[0098] The first recommendation score is the score by which the target tool is recommended to the target employee.

[0099] Since the tool skills gap index represents the degree of lack of skills required for the job by the target employee, the first weight represents the preference of the target tool for the target work business scenario, and the second weight represents the preference of employees of the target employee's job type for participating in the target work business scenario, the score for recommending the target tool to the target employee can be determined based on the first weight, the second weight, and the tool skills gap index.

[0100] For example, the tool system can determine the score for recommending the tool to the job type based on the weighted sum of the first weight and the second weight, and determine the first recommendation score of the target tool by the weighted sum of the score and the tool skills gap index.

[0101] S106. Based on the first recommendation score of each target tool, determine the recommended tool for the target employee from among the target tools.

[0102] For example, for a target employee, the target tools are sorted according to their recommendation scores, and the top-ranked target tools are selected as the recommended tools for the target employee.

[0103] S107, Output recommendation tool.

[0104] For example, in the user interface of the tool system, a list of recommended tools is displayed, and multiple recommended tools are displayed in the list in sequence.

[0105] For example, in response to a user's action, recommended tools are displayed in a floating window of the tool system. For instance, the floating window may hide the list of recommended tools; when the user clicks on the floating window, the tool system captures this action and displays multiple recommended tools in the window.

[0106] The tool recommendation method of this application embodiment obtains the target employee's job data, training data related to tool usage skills, first behavioral data of the target employee in the tool system, and second behavioral data of the job type of the target employee in the tool system; for at least one target tool in the tool system, it obtains a first weight of the target tool's application in at least one corresponding target work business scenario; based on the second behavioral data, it obtains a second weight of the employee's participation in the target work business scenario based on the job data, training data, and first behavioral data; it obtains the target employee's tool skill gap index; based on the first weight, second weight, and tool skill gap index, it determines a first recommendation score for the target tool; based on the first recommendation score of each target tool, it determines the recommended tool for the target employee from the target tools; and it outputs the recommended tool. In this method, the recommendation score of the target tool is based on the weight of the target tool's application in the target work business scenario, the weight of the employee's participation in the target work business scenario based on the job type, and the degree of the target employee's lack of skills required for the job. The recommendation score of the target tool changes with changes in the relevant data of each target employee. Recommending tools to target employees based on the first recommendation score of each target tool can dynamically adapt to target employees and improve the accuracy of tool recommendations.

[0107] The following explains how, in the tool recommendation method of this application, the second weight of the employee's job type participating in the target work business scenario is obtained based on the second-behavior data.

[0108] Figure 2 This is a flowchart illustrating the method for obtaining the second weight provided in an embodiment of this application. Figure 2 As shown, obtaining the second weight of employee participation in the target work business scenario based on the second behavior data can include the following steps:

[0109] S201. From the second action data, obtain the number of first operations performed by employees of the job type in the target work business scenario, and the total number of second operations performed by employees of the same job type as the target employee.

[0110] The first number of operations refers to the number of operations performed by employees of a specific job type within the target work scenario.

[0111] The second number of operations is the total number of operations performed by employees of the same job type.

[0112] For example, the second row of data is obtained through the data points collected by the tool system. This second row of data includes the work and business scenarios of the operations. The tool system can count the total number of operations within a specified time period as the second number of operations, and filter the number of operations for a target work and business scenario based on the work and business scenarios to determine the first number of operations.

[0113] S202. Based on the first number of operations and the second number of operations, obtain the operation weights of employees of different job types in the target work business scenario.

[0114] For example, the tool system can obtain the ratio of the number of first operations to the number of second operations, and calculate the product of the ratio and the business scenario coefficient to obtain the operation weight.

[0115] The business scenario coefficient represents the weight of the target work business scenario within the total work business scenarios. For example, the business scenario coefficient can be set according to business documents. For instance, the number of keywords related to different target tool business scenarios can be counted based on keywords in the business documents, and the business scenario coefficient for different target work business scenarios can be determined proportionally.

[0116] The operation weights of employees of job type c in the target work business scenario s are shown in equation (1):

[0117]

[0118] Wherein, the first number of operations cs represents the number of first operations performed by employees of job type c in the target work business scenario s, the second number of operations c represents the total number of second operations performed by employees of job type c, and the business scenario coefficient s represents the weight of the target work business scenario s in the total work business scenarios.

[0119] In this approach, the second weight obtained subsequently based on the operation weight incorporates the bias of the current work business scenario.

[0120] S203. The weighted sum of the historical weights of employees of different job types in the target work business scenarios and the operational weights is determined as the second weight.

[0121] Optionally, the second weight can be updated periodically. The historical weight of employees of a job type participating in the target work business scenario is the second weight obtained in the previous period, and the second weight in the t-th period is... As shown in equation (2):

[0122]

[0123] in, γ is the second weight of the (t-1)th period, i.e., the historical weight, γ is the weight of the historical weight, and 1-γ is the weight of the operation weight.

[0124] For example, γ can be set to 0.3, with the target work business scenario as the risk control scenario, the job type as corporate account manager, the business scenario coefficient of the risk control scenario as 1.5, the first operation count as 1200, the second operation count as 2500, and the historical weight as 0.4. For example, the second weight can be obtained by calculating 0.3×0.4+0.7×(1200 / 2500×1.5).

[0125] The above is an example of obtaining the second weight of employees of the target job type participating in the target work business scenario. The second weight can be obtained based on the number of operations. The second weight represents the preference of employees of the job type to participate in the target work business scenario. Subsequently, the first recommendation score is obtained based on the second weight to dynamically adapt to the preference of the target employee's job type for the target work business scenario. The following describes how to obtain the tool skills gap index of the target employee.

[0126] Figure 3 This is a flowchart illustrating a method for obtaining a tool skills gap index provided in an embodiment of this application. Figure 3 As shown, based on job data, training data, and first-behavioral data, the tool skills gap index for target employees can be obtained, which may include:

[0127] S301. Based on the first behavioral data and training data, obtain the target employee's operational mastery score of the skills required for the job.

[0128] The operation mastery score represents the target employee's level of proficiency in operating the tools.

[0129] For example, the tool system can obtain the operation score corresponding to the target employee's operation depth based on the first line of data, obtain the target employee's training certification level score based on the training data, and obtain the operation mastery score based on the operation score and the level score.

[0130] Operation depth refers to the actions taken by the target employee to operate the tool. For example, operation depth can include browsing, configuration, and invocation. For instance, browsing is an action of simply opening a page or viewing the documentation, with an operation score of 0.5; configuration is an action of modifying parameters and saving configurations, with an operation score of 1; and invocation is an action of invoking the tool, with an operation score of 1.5.

[0131] For example, with a maximum grade score of 10, the operation mastery score is obtained as shown in equation (3):

[0132]

[0133] Optionally, the tool system can also obtain the adoption rate of the execution operation depth based on behavioral data related to the operation depth; if the adoption rate is greater than the adoption threshold, the operation score corresponding to the operation depth is updated. In this approach, the operation score corresponding to the operation depth is dynamically adjusted based on behavioral data related to the operation depth.

[0134] The adoption rate of the execution operation depth is feedback data on the operation of the target tool. For example, if the target tool is a product promotion tool, and the target employee calls the product promotion tool and uses the product promotion tool to perform the operation of promoting the product, this operation can be regarded as an adoption operation.

[0135] Taking the operation depth as an example, if the acceptance rate is greater than the acceptance threshold after the call, the operation score corresponding to the call is updated, as shown in equation (4):

[0136]

[0137] Wherein, the operation score t is the updated operation score of the call, and the operation score t- 1 The score for the operation called before the update. The weights are preset based on the adoption rate. The baseline adoption rate is a preset baseline value that can be set based on the average adoption rate.

[0138] S302. Based on the training data, obtain the target employees' knowledge scores of the tools and skills required for their positions.

[0139] For example, the tool system can obtain the grades of courses corresponding to the tool skills required for the job from the training data, and convert the grades into knowledge mastery scores. For instance, a grade of 85 for a course corresponding to a tool skill can be converted into 8.5 points to obtain the knowledge mastery score for the tool skill.

[0140] Optionally, the tool system can obtain the target employee's operational error rate based on the first row of data, and update the knowledge mastery score accordingly. This approach enables dynamic updating of the knowledge mastery score.

[0141] The operation error rate is the probability of an error triggered by a target employee while using the tool. For example, during the operation of the tool, incorrect clicks, inputs, or other actions by the employee will trigger errors. The first row of data includes records of these errors. Therefore, based on the target employee's identifier, the operation error rate of the target employee can be obtained from the first row of data.

[0142] For example, the knowledge mastery score is updated based on the operational error rate, as shown in equation (5):

[0143]

[0144] Wherein, the knowledge mastery score t is the updated knowledge mastery score, and the knowledge mastery score t- 1 The baseline error rate is the base value for the knowledge mastery score before the update. For example, the tool system can determine the average error rate of all employees as the baseline error rate.

[0145] S303. The actual mastery of tool skills by the target employee is obtained by weighting the operation mastery score and the knowledge mastery score.

[0146] For example, the actual mastery of tool skills by the target employees is shown in Equation (6):

[0147] Actual mastery level = β × operational mastery score + (1-β) × knowledge mastery score (6)

[0148] Where β is the weight of the operation mastery score, and 1-β is the weight of the knowledge mastery score. For example, β can be set to 0.6.

[0149] S304. Based on job data, determine the target mastery level of the tool skills required for the job, and based on the target mastery level and the actual mastery level, obtain the tool skills gap index for the target employees.

[0150] For example, the target mastery level of the tool skills required for the job requirements is obtained from the job data. For example, the tool skills required for corporate account managers in the job data include risk data interpretation and customer profiling analysis. The target mastery level for risk data interpretation is 8, and the target mastery level for customer profiling analysis is 7.

[0151] For example, the tool skills gap index of the target employees is obtained periodically. Based on the target mastery level and the actual mastery level, the tool skills gap index of the target employees is obtained as shown in Equation (7):

[0152]

[0153] in, This represents the tool skills gap index for the target employee u in the t-th period regarding tool skills k. Let k be the target mastery level of the tool skills k required for the job requirements obtained in the current t-th period. The actual mastery of tool skill k by the target employee u obtained in the current t-th cycle.

[0154] Through the above embodiments, a tool skills gap index for target employees can be obtained based on job data, training data, and first behavior data. Based on this index, the recommendation score for recommended tools can be adjusted according to skill mastery; for example, the tool can be recommended to the target employee to encourage them to use it and improve their lacking skills. Furthermore, the tool system can determine a first recommendation score for the target tool based on a first weight, a second weight, and the skills gap index.

[0155] The following describes, with reference to specific embodiments, how the tool recommendation method of this application determines the first recommendation score of the target tool.

[0156] Optionally, the tool system can determine a second recommendation score based on a first weight and a second weight, and determine the first recommendation score by weighting the second recommendation score and the skills gap index.

[0157] For example, the second recommendation score for the target tool p to employees of this job type is shown in Equation (8), and the first recommendation score for the target tool p to the target employee u is shown in Equation (9):

[0158]

[0159] Recommendation score p = second recommendation score + λ × ∑ k G uk Equation (9)

[0160] Wherein, the target tool p corresponds to n target work business scenarios, the second weight s is the second weight of the employee of the job type to which the target employee u belongs when participating in the target work business scenario s, the first weight ps is the first weight of the application of the target tool p in the corresponding target work business scenario s, λ is the weight of the skill gap index, the target tool p corresponds to k tool skills, and the recommendation score p is the first recommendation score of the target tool p for the target employee u.

[0161] The method for obtaining the first recommendation score is described below with reference to specific embodiments.

[0162] With λ = 0.4, the target work scenarios include marketing and customer acquisition and risk control, the second weight of the employee of the target employee u's job type participating in marketing and customer acquisition is 0.6, the second weight of the employee of the target employee u's job type participating in risk control is 0.4, the target tool p1 is the risk control dashboard, and its first weight in the corresponding risk control is 0.9, the target tool p2 is the marketing toolbox, and its first weight in the corresponding marketing and customer acquisition is 0.8, the skill gap index of the risk control tool skills of the target employee u is 0.34, and the skill gap index of the marketing and customer acquisition tool skills is 0. Taking this example, the first recommendation scores of the target tool p1 and the target tool p2 are as shown in Equations (10) and (11):

[0163] Recommended score p1 =0.4×0.9+0.4×0.34=0.496 Equation (10)

[0164] Recommended score p2 =0.6×0.8+0.4×0=0.48 Equation (11)

[0165] For the target employee u, the first recommendation score of target tool p1 is higher than that of target tool p2.

[0166] Based on the above embodiments, the tool system can determine a second recommendation score for recommending the target tool to employees of any job type based on a first weight and a second weight, and determine the first recommendation score by weighting the second recommendation score and the skills gap index.

[0167] Optionally, the tool system can also obtain the click rate of employees of different job types for the target tool in the target work business scenario. If the click rate is less than the click threshold, the second weight is updated based on the click rate, and the first recommendation score of the target tool is updated.

[0168] For example, if an employee of a certain job type has a click-through rate of less than 10% on the target tool in the target work scenario, the second weight is updated based on the click-through rate, as shown in Equation (12):

[0169]

[0170] in, The second weight for employees of the updated job type participating in the target work business scenario s. The second weight for employees of the previous job type participating in the target work business scenario.

[0171] The baseline click-through rate is the set baseline value. For example, it can be set as the average click-through rate of the target tool under each target business scenario.

[0172] Optionally, the tool system can also obtain the usage rate of the target tool by the target employees. If the usage rate is greater than the usage threshold, the weight of the skill gap index in the weighted sum of the second recommendation score and the skill gap index is updated according to the usage rate, and the first recommendation score of the target tool is updated.

[0173] For example, if the target employee's usage rate of the target tool exceeds the usage threshold, the weight of the skills gap index is updated according to the usage rate, as shown in Equation (13):

[0174]

[0175] Where, λ (t) For the weighting of the updated skills gap index, λ (t-1) The weights for the skills gap index before the update are η1, which is a preset weight adjusted based on usage rate, and the usage threshold is a preset threshold.

[0176] Optionally, if the usage rate increase value is greater than the increase value threshold, the tool system can also update the weight of the skill gap index in the weighted sum of the second recommendation score and the skill gap index based on the usage rate increase value, and update the first recommendation score of the target tool.

[0177] For example, if the increase in the usage rate of the target tool by the target employees is greater than the threshold, the weight of the skills gap index is updated according to the increase in usage rate, as shown in Equation (14):

[0178]

[0179] Where, λ (t) For the weighting of the updated skills gap index, λ (t-1) The weights of the skill gap index before the update are: the threshold for the increase value is a preset threshold, and η2 is a preset weight adjusted based on the increase value of the usage rate.

[0180] According to the above embodiments, a first recommendation score for a target tool can be determined based on a first weight, a second weight, and a tool skills gap index. Further, the tool system can determine the recommended tool for the target employee from among the target tools based on the first recommendation scores of each target tool, and output the recommended tool.

[0181] Optionally, after obtaining the target employee's job data, training data related to tool usage skills, the target employee's first behavior data in the tool system, and the target employee's job type in the tool system's second behavior data, data cleaning and alignment operations can be performed on the data.

[0182] For example, delete data in the first and second rows of data whose operation time is less than 1 second, or delete data whose operation time is outside the working time range.

[0183] For example, when the first-line data, job data, second-line data, and training data are obtained from multiple sources, the data can be aligned based on alignment operations. For instance, when data is obtained from multiple databases, a mapping table can be created to identify the same employee in different databases based on information such as employee email addresses and names in each system. For example, when data is obtained from multiple systems, if the first system includes multiple job types for account managers, while the second system only includes corporate account managers and retail account managers, a mapping table can be created between the multiple account manager job types in the first system and the two account types in the second system.

[0184] This approach improves the quality of acquired data through data cleaning and alignment operations, providing data support for subsequent recommendations and enhancing the accuracy of tool recommendations.

[0185] The following is combined Figure 4 The implementation of the tool recommendation method provided in this embodiment will be explained.

[0186] Figure 4 A flowchart illustrating a tool recommendation method provided in this application embodiment. Figure 2 .like Figure 4 As shown, the following steps may be included:

[0187] S401. Obtain the target employee's job data, training data related to tool usage skills, the target employee's first behavior data in the tool system, and the target employee's second behavior data in the tool system from the data points embedded in the human resources system, training system, and tool system.

[0188] S402. Perform data cleaning and data alignment on the acquired data.

[0189] S403. For at least one target tool in the tool system, obtain the first weight of the target tool in the corresponding at least one target work business scenario.

[0190] S404. Based on the second set of data, obtain the second weight of employees of the job type participating in the target work business scenario.

[0191] S405. Based on job data, training data, and first behavior data, obtain the tool skills gap index for target employees.

[0192] S406. Based on the first weight, the second weight, and the tool skills gap index, determine the first recommended score for the target tool.

[0193] S407. Based on the first recommendation score of each target tool, determine the recommended tool for the target employee from among the target tools.

[0194] S408, Output Recommendation Tool.

[0195] It should be noted that, in Figure 4 The various processing steps (S401-S408) shown in the embodiments do not constitute a specific limitation on the tool recommendation process. In other embodiments of this application, the tool recommendation process may include... Figure 4 The embodiments may have more or fewer steps. For example, the tool recommendation process may include... Figure 4 Some steps in the embodiments, or, Figure 4 Some steps in the embodiments can be replaced by steps with the same function, or Figure 4 Some steps in the embodiments can be broken down into multiple steps, etc.

[0196] The tool recommendation method of this application embodiment obtains the target employee's job data, training data related to tool usage skills, first behavioral data of the target employee in the tool system, and second behavioral data of the job type of the target employee in the tool system; for at least one target tool in the tool system, it obtains a first weight of the target tool's application in at least one corresponding target work business scenario; based on the second behavioral data, it obtains a second weight of the employee's participation in the target work business scenario based on the job data, training data, and first behavioral data; it obtains the target employee's tool skill gap index; based on the first weight, second weight, and tool skill gap index, it determines a first recommendation score for the target tool; based on the first recommendation score of each target tool, it determines the recommended tool for the target employee from the target tools; and it outputs the recommended tool. In this method, the recommendation score of the target tool is based on the weight of the target tool's application in the target work business scenario, the weight of the employee's participation in the target work business scenario based on the job type, and the degree of the target employee's lack of skills required for the job. The recommendation score of the target tool changes with changes in the relevant data of each target employee. Recommending tools to target employees based on the first recommendation score of each target tool can dynamically adapt to target employees and improve the accuracy of tool recommendations.

[0197] Figure 5 This is a schematic diagram of a tool recommendation device provided in an embodiment of this application. Figure 5As shown, the tool recommendation device 500 may include, for example, a first acquisition module 501, a second acquisition module 502, a third acquisition module 503, a fourth acquisition module 504, a first determination module 505, a second determination module 506, and an output module 507. Optionally, it may also include an update module.

[0198] The first acquisition module 501 is used to acquire the target employee's job data, training data related to tool usage skills, the target employee's first behavior data in the tool system, and the target employee's job type in the tool system as a second behavior data; wherein, different types of jobs have different ranges of tools that can be used when working.

[0199] The second acquisition module 502 is used to acquire, for at least one target tool in the tool system, the first weight of the target tool in the corresponding at least one target work business scenario;

[0200] The third acquisition module 503 is used to acquire, based on the second behavior data, the second weight of the employee of the job type participating in the target work business scenario;

[0201] The fourth acquisition module 504 is used to acquire the tool skills gap index of the target employee based on the job data, the training data and the first behavior data. The tool skills gap index represents the degree of lack of the target employee in terms of the skills required for the job.

[0202] The first determining module 505 is used to determine the first recommendation score of the target tool based on the first weight, the second weight, and the tool skills gap index;

[0203] The second determining module 506 is used to determine the recommending tool for the target employee from the target tools based on the first recommendation score of each target tool;

[0204] Output module 507 is used to output the recommendation tool.

[0205] One possible implementation is that the first determining module 505 is specifically used for:

[0206] Based on the first weight and the second weight, a second recommendation score is determined to recommend the target tool to employees of the job type;

[0207] The weighted sum of the second recommended score and the tool skills gap index is determined as the first recommended score.

[0208] One possible implementation is that the third acquisition module 503 is specifically used for:

[0209] From the second behavioral data, obtain the first number of operations performed by employees of the job type in the target work scenario, and the total second number of operations performed by employees of the job type to which the target employee belongs;

[0210] Based on the first number of operations and the second number of operations, obtain the operation weight of the employee of the job type in the target work business scenario;

[0211] The weighted sum of the historical weights of employees of the job type in the target work scenario and the operational weights is determined as the second weight.

[0212] One possible implementation is that the third acquisition module 503 is specifically used for:

[0213] Obtain the ratio of the first number of operations to the second number of operations;

[0214] The operation weight is obtained by multiplying the ratio of the number of operations by the business scenario coefficient. The business scenario coefficient represents the weight of the target work business scenario in the total work business scenarios.

[0215] One possible implementation is that the fourth acquisition module 504 is specifically used for:

[0216] Based on the first behavioral data and the training data, obtain the target employee's operational mastery score of the skills required for the job;

[0217] Based on the training data, the target employee's knowledge score of the tools and skills required for the job is obtained;

[0218] The actual mastery of the tool skills by the target employee is obtained by weighting the operation mastery score and the knowledge mastery score.

[0219] Based on the job data, determine the target mastery level of the tool skills required for the job, and based on the target mastery level and the actual mastery level, obtain the tool skills gap index of the target employee.

[0220] One possible implementation is that the update module is specifically used for:

[0221] Based on the first behavioral data, the operation error rate of the target employee is obtained, and the knowledge mastery score is updated based on the operation error rate.

[0222] One possible implementation is that the update module is specifically used for:

[0223] Based on the first behavioral data, obtain the operation score corresponding to the operation depth of the target employee's operation tool; the operation depth includes: browsing, configuration, and invocation.

[0224] Based on the training data, obtain the training certification level score of the target employee;

[0225] The operation mastery score is obtained based on the operation score and the level score.

[0226] One possible implementation is that the update module is specifically used for:

[0227] Based on the behavioral data related to the operation depth, obtain the adoption rate for executing the operation depth;

[0228] If the adoption rate is greater than the adoption threshold, update the operation score corresponding to the operation depth.

[0229] One possible implementation is that the update module is specifically used for:

[0230] Get the click rate of the target tool for employees of the specified job type in the specified target work business scenario;

[0231] If the click-through rate is less than the click threshold, the second weight is updated based on the click-through rate, and the first recommendation score of the target tool is updated.

[0232] One possible implementation is that the update module is specifically used for:

[0233] Obtain the usage rate of the target tool by the target employees;

[0234] If the usage rate is greater than the usage threshold, the weight of the tool skills gap index in the weighted sum of the second recommendation score and the tool skills gap index is updated according to the usage rate, and the first recommendation score of the target tool is updated.

[0235] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 6 As shown, the electronic device may include at least one processor 601 and a memory 602.

[0236] The memory 602 is used to store programs. Specifically, the program may include program code, which includes computer operation instructions.

[0237] Memory 602 may include high-speed RAM memory, and may also include non-volatile memory.

[0238] The processor 601 is used to execute computer execution instructions stored in the memory 602 to implement the method of the foregoing method embodiments. The processor 601 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0239] Optionally, the electronic device may also include a communication interface 603. In specific implementations, if the communication interface 603, the memory 602, and the processor 601 are implemented independently, the communication interface 603, the memory 602, and the processor 601 can be interconnected via a bus to complete communication between them.

[0240] Optionally, in a specific implementation, if the communication interface 603, memory 602, and processor 601 are integrated on a single chip, then the communication interface 603, memory 602, and processor 601 can communicate through an internal interface.

[0241] This application also provides a computer-readable storage medium, which may include various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), and a random access memory (RAM). Specifically, the computer-readable storage medium stores program instructions, which are used to implement the actions of the above-described method implementation.

[0242] This application also provides a computer program product, which includes a computer program that, when executed by a processor, performs the actions of the above-described method implementation.

[0243] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0244] When an integrated unit / module is implemented in hardware, the hardware can be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors. Unless otherwise specified, the processor can be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the storage unit can be any suitable storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc.

[0245] If the integrated unit / module is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), and portable hard drives.

[0246] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0247] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM and RAM.

Claims

1. A tool recommendation method, characterized in that, include: The system acquires the target employee's job data, training data related to tool usage skills, the target employee's first behavior data in the tool system, and the target employee's job type in the tool system as a second behavior data; wherein, different job types have different ranges of tools that can be used when working. For at least one target tool in the tool system, obtain the first weight of the target tool in the corresponding at least one target work business scenario; Based on the second behavioral data, obtain the second weight of the employee of the job type participating in the target work business scenario; Based on the job data, the training data, and the first behavioral data, the tool skills gap index of the target employee is obtained, which represents the degree of lack of the target employee in terms of the skills required for the job. Based on the first weight, the second weight, and the tool skills gap index, a first recommendation score for the target tool is determined; Based on the first recommendation score of each of the target tools, determine the recommender tool for the target employee from among the target tools; Output the recommended tool.

2. The method according to claim 1, characterized in that, The step of determining the first recommendation score for the target tool based on the first weight, the second weight, and the tool skills gap index includes: Based on the first weight and the second weight, a second recommendation score is determined to recommend the target tool to employees of the job type; The weighted sum of the second recommended score and the tool skills gap index is determined as the first recommended score.

3. The method according to claim 1, characterized in that, The step of obtaining the second weight of employees of the job type participating in the target work business scenario based on the second behavioral data includes: From the second behavioral data, obtain the first number of operations performed by employees of the job type in the target work scenario, and the total second number of operations performed by employees of the job type to which the target employee belongs; Based on the first number of operations and the second number of operations, obtain the operation weight of the employee of the job type in the target work business scenario; The weighted sum of the historical weights of employees of the job type in the target work scenario and the operational weights is determined as the second weight.

4. The method according to claim 3, characterized in that, The step of obtaining the operation weights of employees of the job type in the target work scenario based on the first number of operations and the second number of operations includes: Obtain the ratio of the first number of operations to the second number of operations; The operation weight is obtained by multiplying the ratio of the number of operations by the business scenario coefficient. The business scenario coefficient represents the weight of the target work business scenario in the total work business scenarios.

5. The method according to claim 1, characterized in that, The step of obtaining the tool skills gap index of the target employee based on the job data, the training data, and the first behavioral data includes: Based on the first behavioral data and the training data, obtain the target employee's operational mastery score of the skills required for the job; Based on the training data, the target employee's knowledge score of the tools and skills required for the job is obtained; The actual mastery of the tool skills by the target employee is obtained by weighting the operation mastery score and the knowledge mastery score. Based on the job data, determine the target mastery level of the tool skills required for the job, and based on the target mastery level and the actual mastery level, obtain the tool skills gap index of the target employee.

6. The method according to claim 5, characterized in that, The method further includes: Based on the first behavioral data, the operation error rate of the target employee is obtained, and the knowledge mastery score is updated based on the operation error rate.

7. The method according to claim 5 or 6, characterized in that, The step of obtaining the target employee's operational mastery score for the skills required for the job based on the first behavioral data and the training data includes: Based on the first behavioral data, obtain the operation score corresponding to the operation depth of the target employee's operation tool; the operation depth includes: browsing, configuration, and invocation. Based on the training data, obtain the training certification level score of the target employee; The operation mastery score is obtained based on the operation score and the level score.

8. The method according to claim 7, characterized in that, The method further includes: Based on the behavioral data related to the operation depth, obtain the adoption rate for executing the operation depth; If the adoption rate is greater than the adoption threshold, update the operation score corresponding to the operation depth.

9. The method according to any one of claims 1-6, characterized in that, The method further includes: Get the click rate of the target tool for employees of the specified job type in the specified target work business scenario; If the click-through rate is less than the click threshold, the second weight is updated based on the click-through rate, and the first recommendation score of the target tool is updated.

10. The method according to any one of claims 2-6, characterized in that, The method further includes: Obtain the usage rate of the target tool by the target employees; If the usage rate is greater than the usage threshold, the weight of the tool skills gap index in the weighted sum of the second recommendation score and the tool skills gap index is updated according to the usage rate, and the first recommendation score of the target tool is updated.

11. A tool recommendation device, characterized in that, The device includes: The first acquisition module is used to acquire the target employee's job data, training data related to tool usage skills, the target employee's first behavior data in the tool system, and the target employee's job type in the tool system as a second behavior data; wherein, different types of jobs have different ranges of tools that can be used when working; The second acquisition module is used to acquire, for at least one target tool in the tool system, the first weight of the target tool in the corresponding at least one target work business scenario; The third acquisition module is used to acquire, based on the second behavioral data, the second weight of employees of the job type participating in the target work business scenario; The fourth acquisition module is used to acquire the tool skills gap index of the target employee based on the job data, the training data and the first behavior data. The tool skills gap index represents the degree of lack of the target employee in terms of the skills required for the job. The first determining module is used to determine the first recommendation score of the target tool based on the first weight, the second weight, and the tool skills gap index. The second determining module is used to determine the recommending tool for the target employee from the target tools based on the first recommendation score of each target tool; The output module is used to output the recommendation tool.

12. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as claimed in any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 10.

14. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 10.

Images