CN114677247A - Enterprise learning method and system based on data driving - Google Patents

Abstract

The invention discloses a data-driven enterprise learning method and a data-driven enterprise learning system, wherein the method comprises the following steps: firstly, building a distributed learning decision-making framework of a target enterprise, and traversing mainstream operation information according to a data traversal layer in the framework, so as to obtain a post knowledge structure; the format conversion can generate each position map set; according to the portrait generation layer, performing role positioning on internal workers to generate a set of portrait of each worker; and uploading the post map sets and the employee portrait sets to a decision matching layer for matching training to obtain an individualized learning decision model set for driving learning of the employees.

Description

Enterprise learning method and system based on data driving

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to an enterprise learning method and system based on data driving.

Background

Under the digital wave, society, politics, technology, law, industry, competition, consumption and the like are gradually and rapidly changed, and the business environment is rapidly rushing forward. The enterprise organization can be in the green base only by adapting to the environment, agile evolution and continuous revolution.

However, in the prior art, it is difficult for an enterprise to perform adaptive training and learning on internal employees, so that the development path of the employees is disconnected from the sustainable development of the enterprise, the personal development of the employees is slow, and meanwhile, the enterprise cannot be actively assisted in the good sustainable development.

Disclosure of Invention

The invention aims to provide a data-driven enterprise learning method and a data-driven enterprise learning system, which are used for solving the technical problems that in the prior art, an enterprise is difficult to carry out self-adaptive training and learning on internal staffs, so that the development path of the staffs is disconnected from the sustainable development of the enterprise, the individual development of the staffs is slow, and meanwhile, the enterprise cannot be actively assisted in good sustainable development.

In view of the above problems, the present invention provides a data-driven enterprise learning method and system.

In a first aspect, the present invention provides a data-driven enterprise learning method, where the method is implemented by a data-driven enterprise learning system, where the method includes: setting up a distributed learning decision framework of a target enterprise, wherein the distributed learning decision framework comprises a data traversal layer, an image generation layer and a decision matching layer; traversing the mainstream operation information of the target enterprise based on the data traversal layer to obtain a post knowledge structure of the target enterprise; carrying out format conversion on the post knowledge structure to generate each post map set; based on the image generation layer, carrying out role positioning on internal employees of the target enterprise to generate an employee role positioning set; according to the additional characteristic information of each employee, performing information fusion on the role positioning sets of each employee to generate image sets of each employee; uploading the post map sets and the employee image sets to the decision matching layer for matching training to obtain an individualized learning decision model set of the internal employees; and performing driving learning on each employee of the target enterprise based on the personalized learning decision model set.

In another aspect, the present invention further provides a data-driven enterprise learning system, configured to execute the method for data-driven enterprise learning according to the first aspect, where the system includes: the system comprises a first building unit, a second building unit and a third building unit, wherein the first building unit is used for building a distributed learning decision framework of a target enterprise, and the distributed learning decision framework comprises a data traversal layer, an image generation layer and a decision matching layer; a first obtaining unit, configured to traverse the mainstream operation information of the target enterprise based on the data traversal layer, and obtain a post knowledge structure of the target enterprise; the first conversion unit is used for carrying out format conversion on the post knowledge structure to generate each post map set; the first positioning unit is used for carrying out role positioning on internal staff of the target enterprise based on the image generation layer to generate staff role positioning sets; the first fusion unit is used for carrying out information fusion on the employee role positioning sets according to the additional characteristic information of the employees to generate employee image sets; the first uploading unit is used for uploading the post map sets and the employee image sets to the decision matching layer for matching training to obtain an individualized learning decision model set of the internal employees; a first driving unit, configured to perform driving learning on each employee of the target enterprise based on the personalized learning decision model set.

In a third aspect, the present invention further provides a data-driven enterprise learning system, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to the first aspect when executing the computer program.

In a fourth aspect, an electronic device, comprising a processor and a memory;

the memory is used for storing;

the processor is configured to execute the method according to any one of the first aspect above by calling.

In a fifth aspect, a computer program product comprises a computer program and/or instructions which, when executed by a processor, implement the steps of the method of any one of the first aspect.

One or more technical schemes provided by the invention at least have the following technical effects or advantages:

traversing the mainstream operation information according to a data traversal layer in a distributed learning decision framework of a target enterprise to obtain a post knowledge structure; the format conversion can generate a set of maps of all posts; according to the portrait generation layer, performing role positioning on internal workers to generate a portrait set of each worker; and uploading the post map sets and the employee portrait sets to a decision matching layer for matching training to obtain an individualized learning decision model set for driving learning of the employees. Through the collection of the operation project mainstream of target enterprise traversal accurate post knowledge structure, generate accurate each post map, carry out accurate role location and skill level test to the inside staff of enterprise simultaneously, combine individual habit characteristic, establish every staff's accurate portrait, through carrying out data analysis to the picture, can make individualized study decision model for every staff for the realization carries out the training study of self-adaptation to inside staff, helping hand enterprise development.

The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.

Drawings

In order to more clearly illustrate the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only exemplary, and for those skilled in the art, other drawings can be obtained according to the provided drawings without inventive effort.

FIG. 1 is a schematic flow chart of a data-driven enterprise learning method according to the present invention;

fig. 2 is a schematic flow chart of uploading the post map sets and the employee image sets to the decision matching layer for matching training in the data-driven enterprise learning method of the present invention;

FIG. 3 is a schematic flow chart illustrating the construction of a first matching logic in the data-driven enterprise learning method according to the present invention;

FIG. 4 is a schematic flow chart of a personalized learning decision model for generating a non-standard employee set in the data-driven enterprise learning method according to the present invention;

FIG. 5 is a schematic flow chart illustrating the step-driven learning process performed on the non-qualified employee set according to the data-driven enterprise learning method of the present invention;

FIG. 6 is a schematic structural diagram of a data-driven enterprise learning system according to the present invention;

fig. 7 is a schematic structural diagram of an exemplary electronic device of the present invention.

Description of reference numerals:

the system comprises a first building unit 11, a first obtaining unit 12, a first converting unit 13, a first positioning unit 14, a first fusing unit 15, a first uploading unit 16, a first driving unit 17, a bus 300, a receiver 301, a processor 302, a transmitter 303, a memory 304 and a bus interface 305.

Detailed Description

The invention provides an enterprise learning method and system based on data driving, and solves the technical problems that an enterprise is difficult to carry out self-adaptive training and learning on internal staffs, so that the development path of the staffs is disconnected from the sustainable development of the enterprise, the individual development of the staffs is slow, and the enterprise cannot be actively assisted in good sustainable development. Through the operation project mainstream to the target enterprise ergodic accurate post knowledge structure collection, generate accurate each post map, carry out accurate role location and skill level test to the inside staff of enterprise simultaneously, combine individual habit characteristic, establish every staff's accurate portrait, carry out data analysis through to the picture, can make individualized study decision-making model for every staff, reach the training study that carries out the self-adaptation to inside staff, when improving staff professional skill, the good sustainable development's of helping hand enterprise technical effect.

In the technical scheme of the invention, the data acquisition, storage, use, processing and the like all conform to relevant regulations of national laws and regulations.

In the following, the technical solutions in the present invention will be clearly and completely described with reference to the accompanying drawings, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments of the present invention, and it should be understood that the present invention is not limited by the example embodiments described herein. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention. It should be further noted that, for the convenience of description, only some but not all of the elements associated with the present invention are shown in the drawings.

The invention provides a data-driven enterprise learning method, which is applied to a data-driven enterprise learning system, wherein the method comprises the following steps: setting up a distributed learning decision framework of a target enterprise, wherein the distributed learning decision framework comprises a data traversal layer, an image generation layer and a decision matching layer; traversing the mainstream operation information of the target enterprise based on the data traversal layer to obtain a post knowledge structure of the target enterprise; carrying out format conversion on the post knowledge structure to generate each post map set; based on the image generation layer, carrying out role positioning on internal employees of the target enterprise to generate an employee role positioning set; performing information fusion on the employee role positioning sets according to the additional characteristic information of each employee to generate employee portrait sets; uploading the post map sets and the employee image sets to the decision matching layer for matching training to obtain an individualized learning decision model set of the internal employees; and performing driving learning on each employee of the target enterprise based on the personalized learning decision model set.

Having described the general principles of the invention, reference will now be made in detail to various non-limiting embodiments of the invention, examples of which are illustrated in the accompanying drawings.

Example one

Referring to fig. 1, the present invention provides a data-driven enterprise learning method, wherein the method is applied to a data-driven enterprise learning system, and the method specifically includes the following steps:

step S100: setting up a distributed learning decision framework of a target enterprise, wherein the distributed learning decision framework comprises a data traversal layer, an image generation layer and a decision matching layer;

step S200: traversing the mainstream operation information of the target enterprise based on the data traversal layer to obtain a post knowledge structure of the target enterprise;

particularly, under the digital wave, society, politics, technology, law, industry, competition, consumption, etc. are evolving more and more rapidly, and the business environment is rushing forward at an increasingly rapid rate. The enterprise organization can be in the green base only by adapting to the environment, agile evolution and continuous revolution. However, the existing enterprises are difficult to carry out self-adaptive training and learning on internal employees, so that the development roads of the employees are disconnected from the sustainable development of the enterprises, the personal development of the employees is slow, and the enterprises cannot be helped to develop the good sustainable development actively. In order to solve the problems, the application provides a data-driven enterprise learning method, namely, a post knowledge structure which is used for accurately traversing the main stream of an operation project of a target enterprise is acquired, an accurate post map is generated, meanwhile, accurate role positioning and skill level testing are carried out on employees in the enterprise, an accurate portrait of each employee is constructed by combining personal habit characteristics, and an individualized learning decision model can be made for each employee by carrying out data analysis on the portrait, so that self-adaptive training and learning of the employees in the enterprise are realized, and enterprise development is assisted.

More specifically, a distributed learning decision framework of a target enterprise can be set up, wherein the target enterprise is an enterprise in which internal employees are required to be trained in the application, and a small and medium financial enterprise can be taken as an example to explain the training of the internal employees of the small and medium financial enterprise, and the training can be realized based on the distributed learning decision mechanism, wherein the distributed learning decision mechanism comprises a data traversal layer, an image generation layer and a decision matching layer. Further, the data traversal layer is used for acquiring a post knowledge structure for accurately traversing operation project mainstream (items such as wind control investment) of a target enterprise (financial enterprise); the figure generation layer is used for carrying out accurate role positioning and skill level testing on employees in the enterprise and constructing an accurate figure of each employee by combining personal habit characteristics; the decision matching layer is used for carrying out data analysis on the image and can make an individualized learning decision model for each employee.

Step S300: carrying out format conversion on the post knowledge structure to generate each post map set;

further, step S300 includes:

step S310: traversing and analyzing the post knowledge structure to obtain a set of functional departments;

step S320: acquiring execution main body information of each functional department in the functional department set;

step S330: and carrying out format conversion on the functional department set and the execution main body information to generate the position map sets.

Specifically, after obtaining the post knowledge structure of the target enterprise, format conversion can be performed on the post knowledge structure, specifically, the post knowledge structure can be characterized as an organization architecture of a financial enterprise, and often includes a front part, including an asset management part, an innovation business part, a reorganization and purchase part, an asset management part, and the like; the middle platform part comprises a legal compliance part, a business check part and the like; and the background part comprises a planning finance department, a personnel administration department and the like.

When the format of the post knowledge structure is converted, the post knowledge structure can be subjected to traversal analysis to obtain a set of functional departments, the set of functional departments can be characterized as the above-mentioned asset management department, innovation business department, reorganization and purchase department, asset management department, or the like, further, the information of the execution subject of each functional department is obtained, illustratively, the execution subject of the innovation business department includes the constituent information of the chief and the business officer, further converting the format of the set of functional departments and the execution subject information to generate the set of position maps, that is, the business administration and the business executive body distribution information of the business administration are converted into the format, for example, tree distribution information, the tree distribution information shows the status distribution of each execution main body, namely that the minister is responsible for overall planning, and the salesman is responsible for actual business operation. The position maps are collected and distributed throughout any position of the financial enterprise and the executive body thereof.

Step S400: based on the image generation layer, carrying out role positioning on internal employees of the target enterprise to generate an employee role positioning set;

step S500: according to the additional characteristic information of each employee, performing information fusion on the role positioning sets of each employee to generate image sets of each employee;

further, step S500 includes:

step S510: performing relevance analysis on the additional feature information of each employee to obtain a first relevance additional feature and a second relevance additional feature;

step S520: performing information fusion on the employee role positioning sets and the first correlation additional features to generate primary employee portrait sets;

step S530: and performing secondary information fusion on the second correlation additional characteristics and the primary staff image sets to generate the staff image sets.

Specifically, after generating accurate position maps, accurate role positioning needs to be performed on internal employees of the enterprise, specifically, role positioning can be performed on internal employees of the target enterprise according to the image generation layer, and an employee role positioning set is generated, where the employee role positioning set includes business personnel of the innovation business department, merger and purchase personnel of the reorganization and purchase department, financial personnel of the planning financial department, or administrative personnel of the human administration department, that is, each employee inside the enterprise has its own role positioning.

Meanwhile, information fusion can be carried out on the role positioning sets of the employees according to additional characteristic information of the employees, specifically, the additional characteristic information of the employees comprises knowledge storage, actual combat experience, personal habit characteristics and the like, and the obtained first correlation additional characteristic can be represented as a characteristic which has the greatest influence on the personal abilities of the employees, namely the skill level; the second relevance additional feature can be characterized as a next-to-next feature, namely personal habits and the like.

And further performing information fusion on each employee role positioning set and the first correlation additional characteristic to generate a primary employee image set, wherein the primary employee image set represents an employee image set with skill level characteristics, and further performing secondary information fusion on the second correlation additional characteristic and the primary employee image set to generate each employee image set, and each employee image set can be characterized by adding personal habit characteristics of an employee on the basis of the employee image set with skill level characteristics to obtain a final enterprise internal employee image set through fusion.

Step S600: uploading the post map sets and the employee image sets to the decision matching layer for matching training to obtain an individualized learning decision model set of the internal employees;

step S700: and performing driving learning on each employee of the target enterprise based on the personalized learning decision model set.

Specifically, after accurate post maps are generated and accurate images of employees in an enterprise are generated, the post map sets and the employee image sets can be uploaded to the decision matching layer to be matched and trained, the employee images and the post maps are matched and matched, and a self-adaptive personalized learning decision model can be generated for each post execution main body to improve the professional technical level of the employees.

Illustratively, the personalized learning decision model set comprises a personalized learning decision model of business personnel of an innovation business department, a personalized learning decision model of business personnel of a recombination and purchase department, a personalized learning decision model of financial personnel of a planning financial department, a personalized learning decision model of administrative personnel of a personnel administrative department and the like, and each employee of the target enterprise can be driven to learn based on the personalized learning decision model set, so that the sustainable development requirement of the helping enterprise is better while the personal occupation level of the employee is improved.

Further, as shown in fig. 2, the step S600 of uploading the post map sets and the employee image sets to the decision matching layer for matching training includes:

step S610: performing hierarchical division on the decision matching layer to generate a first matching sequence and a second matching sequence, wherein the second matching sequence is in one-to-one correspondence with the first matching sequence;

step S620: performing demand feature extraction on each post in each post map set to generate a demand feature set, and inputting the demand feature set into the first matching sequence;

step S630: performing skill feature extraction on each employee in each employee image set to generate a skill feature set, and inputting the skill feature set into the second matching sequence;

step S640: constructing a first matching logic;

step S650: and performing matching training on the first matching sequence and the second matching sequence according to the first matching logic.

Specifically, when the post map sets and the employee image sets are uploaded to the decision matching layer for matching training, specifically, the decision matching layer may be hierarchically divided, the first matching sequence corresponds to each post requirement feature of a financial enterprise, and the second matching sequence corresponds to a personal skill feature of an employee in the enterprise.

Extracting the requirement characteristics of the stations in the station map sets to generate a requirement characteristic set, wherein the extracted result comprises personal professional knowledge storage of the employees, a co-purchasing case result, a detailed gallbladder and other personal behavior characteristic sets, and the requirement characteristic set is input into the first matching sequence; meanwhile, the skill feature extraction can be performed on each employee in each employee image set, and the first correlation additional features can be referred to for extraction, wherein the extraction includes feature sets such as personal professional skills and professional literacy, and the skill feature sets are input into the second matching sequence.

And further, according to a first constructed matching logic, matching training can be carried out on the first matching sequence and the second matching sequence, wherein the first matching logic is logic for matching the requirement characteristics of each post with the personal skill characteristics of the staff in the enterprise, so that the first matching logic and the second matching logic are optimally and accurately matched.

Further, as shown in fig. 3, the step S640 of constructing the first matching logic includes:

step S641: embedding an access type signal instruction into the first matching sequence;

step S642: embedding a response type signal instruction into the second matching sequence;

step S643: acquiring a first requirement characteristic in the requirement characteristic set, loading the first requirement characteristic to the access type signal instruction, and sending the first requirement characteristic to the second matching sequence for cycle traversal to acquire a first skill characteristic set in the second matching sequence;

step S644: and loading the first skill characteristic set to the answer signal instruction, and feeding back the first skill characteristic set and the answer signal instruction to the first requirement characteristic together to obtain a first skill employee set corresponding to the first skill characteristic set.

Specifically, the first matching logic is constructed, specifically, an access type signal instruction can be embedded into the first matching sequence, and the access type signal instruction can be similar to a signal accessor, can load information to be accessed, and transmits the information to an access destination for signal access; meanwhile, a response type signal instruction is embedded into the second matching sequence, and the response type signal instruction can be similar to a signal responder to realize response to the accessed signal.

Furthermore, a first requirement feature in the requirement feature set is obtained, where the first requirement feature is any post requirement feature in the requirement feature set, and may be, for example, a post requirement feature of a recombined merger-and-purchase department, and the first requirement feature is loaded into the access type signal instruction and is sent to the second matching sequence together for cycle traversal, so that a first skill feature set in the second matching sequence is obtained, where the first skill feature set is a personal behavior feature set, such as a personal professional knowledge reserve, a merger-and-purchase case result, and a detailed courage and great mood, that is suitable for the post requirement feature of the recombined merger-and-purchase department.

And finally, loading the first skill characteristic set to the answer signal instruction, and feeding back the first skill characteristic set and the first requirement characteristic together to obtain a first skill staff set corresponding to the first skill characteristic set, wherein the first skill staff set has the personal behavior characteristic sets such as the personal professional knowledge storage, the co-purchase case result, the detailed gallbladder and the like, so that the first skill staff set can be conveniently subjected to personalized learning decision model generation.

Further, as shown in fig. 4, step S600 further includes step S660:

step S661: inputting the first requirement characteristic and the first skill characteristic set into a skill association matching model for training, and obtaining a first association value of a first employee skill and the first requirement characteristic, a second association value of a second employee skill and the first requirement characteristic in the first skill employee set until an Nth association value of an Nth employee skill and the first requirement characteristic;

step S662: classifying the first relevance value, the second relevance value and the Nth relevance value on the basis of a preset relevance value to obtain a first standard relevance value set and a second non-standard relevance value set;

step S663: obtaining a set of post necessary knowledge structures of the first set of qualifying relevance values;

step S664: and generating an individualized learning decision model of the non-standard employee set based on the post necessary knowledge structure set and the second non-standard association value set.

Specifically, after a first skill employee set corresponding to the first skill feature set is obtained, a personalized learning decision model may be generated based thereon. Specifically, the first skill characteristic and the first skill characteristic set are input into a skill association matching model for training, wherein the skill association matching model can accurately train the association degree between the personal skill of the employee and the post requirement characteristic, and as the first skill employee set has the post requirement of the reorganization and purchase department, the actual skill of each employee is greatly different, and thus accurate matching can be performed according to the association degree between the personal skill of the employee and the post requirement characteristic.

Specifically, based on the skill association matching model, a first association value between a first employee skill and the first requirement characteristic, a second association value between a second employee skill and the first requirement characteristic, and an nth association value between an nth employee skill and the first requirement characteristic in the first skill employee set, that is, a distribution of association degrees between an actual skill of each employee and the first requirement characteristic, may be obtained through training, and further, based on a preset association value, the first association value, the second association value, and the nth association value are classified, where the preset association value may be set such that the personal skills of the employees meet the standard requirements of a reorganization and purchase department, that is, personal habits of abundant personal expertise, many cases of purchasing experience, most cases of success, great hearts of gallbladder, and the like, and the first standard reaching association value set obtained through classification may be characterized as meeting the personal expertise, abundant reserve, abundant personal expertise, abundant energy, and the like, The experience of the co-purchasing cases is more, and most cases are association degree sets of successful cases and personal habits such as gallbladder, heart and thin, and on the contrary, the second non-standard association degree set is an unsatisfied association degree set.

Based on the above, the post necessary knowledge structure set of the first standard-reaching relevance value set can be obtained, the post necessary knowledge structure set can summarize the post necessary knowledge related to the enrichment of personal professional knowledge reserves, and the personalized learning decision model of the non-standard employee set can be generated through the post necessary knowledge structure set and the second non-standard relevance value set, so that the self-adaptive driving learning of the non-standard employee set is realized.

Further, as shown in fig. 5, step S664 includes:

step S6641: obtaining a first learning achievement of the non-standard employee set after a preset time based on the personalized learning decision model;

step S6642: dividing the post necessary knowledge structure set in order to generate a first-order knowledge framework, a second-order knowledge framework and a third-order knowledge framework;

step S6643: judging whether the first learning achievement reaches the third-order knowledge architecture;

step S6644: and if the first learning result reaches the third-order knowledge framework, performing advanced driving learning on the non-standard employee set.

Specifically, after an individualized learning decision model of a non-standard employee set is generated and adaptive drive learning of the non-standard employee set is achieved, in order to evaluate the learning effect of the individualized learning decision model, a first learning achievement of the non-standard employee set after a preset time is obtained based on the individualized learning decision model, wherein the preset time is a period of employee learning based on the individualized learning decision model, and may be a week, a month, or a quarter, and the first learning achievement is an actual personal professional knowledge reserve of an employee after learning for a period of time.

Meanwhile, the post necessary knowledge structure set is divided in order to generate a first-order knowledge framework, a second-order knowledge framework and a third-order knowledge framework, wherein the first-order knowledge framework can be understood as more than 90% reserve of professional knowledge, the second-order knowledge framework can be understood as more than 80% reserve of professional knowledge, the third-order knowledge framework can be understood as more than 60% reserve of professional knowledge, the individual learning decision model is adapted to the non-standard employees by judging whether the first learning result reaches the third-order knowledge framework, namely whether the actual personal professional knowledge reserve of the employees reaches more than 60% reserve of the professional knowledge, if so, the individual learning decision model can be adapted to the non-standard employees, and the non-standard employee set can be subjected to advanced driving learning to be advanced to the second-order knowledge framework and even the first-order knowledge framework, so that the adaptive driving learning to the employees is realized, thereby improving the knowledge storage of the staff and helping the development of the company.

In summary, the enterprise learning method based on data driving provided by the invention has the following technical effects:

1. traversing the mainstream operation information according to a data traversal layer in a distributed learning decision framework of a target enterprise to obtain a post knowledge structure; the format conversion can generate a set of maps of all posts; according to the portrait generation layer, performing role positioning on internal workers to generate a portrait set of each worker; and uploading the post map sets and the employee portrait sets to a decision matching layer for matching training to obtain an individualized learning decision model set for driving learning of the employees. Through the collection of the operation project mainstream of target enterprise traversal accurate post knowledge structure, generate accurate each post map, carry out accurate role location and skill level test to the inside staff of enterprise simultaneously, combine individual habit characteristic, establish every staff's accurate portrait, through carrying out data analysis to the picture, can make individualized study decision model for every staff for the realization carries out the training study of self-adaptation to inside staff, helping hand enterprise development.

2. By judging whether the learning achievement reaches the third-order knowledge framework or not, if so, the employee can be subjected to advanced driving learning to be advanced to the second-order knowledge framework and even the first-order knowledge framework, so that the adaptive driving learning of the employee is realized, and the knowledge reserve of the employee is improved.

Example two

Based on the same inventive concept as the data-driven enterprise learning method in the foregoing embodiment, the present invention further provides a data-driven enterprise learning system, please refer to fig. 6, where the system includes:

the system comprises a first building unit 11, a second building unit 11 and a third building unit, wherein the first building unit 11 is used for building a distributed learning decision-making framework of a target enterprise, and the distributed learning decision-making framework comprises a data traversing layer, an image generating layer and a decision matching layer;

a first obtaining unit 12, where the first obtaining unit 12 is configured to traverse the mainstream operation information of the target enterprise based on the data traversal layer, and obtain a post knowledge structure of the target enterprise;

a first conversion unit 13, where the first conversion unit 13 is configured to perform format conversion on the post knowledge structure to generate each post map set;

a first positioning unit 14, configured to perform role positioning on internal employees of the target enterprise based on the image generation layer, and generate an employee role positioning set;

the first fusion unit 15 is configured to perform information fusion on the employee role positioning sets according to the additional feature information of each employee, and generate employee portrait sets;

the first uploading unit 16 is configured to upload the post map sets and the employee image sets to the decision matching layer for matching training, so as to obtain an individualized learning decision model set of the internal employees;

a first driving unit 17, where the first driving unit 17 is configured to perform driving learning on each employee of the target enterprise based on the personalized learning decision model set.

Further, the system further comprises:

the decision matching layer is hierarchically divided by the first dividing unit to generate a first matching sequence and a second matching sequence, wherein the second matching sequence is in one-to-one correspondence with the first matching sequence;

a first extraction unit, configured to perform demand feature extraction on each position in each position map set, generate a demand feature set, and input the demand feature set to the first matching sequence;

the second extraction unit is used for performing skill feature extraction on each employee in each employee image set to generate a skill feature set, and inputting the skill feature set into the second matching sequence;

a first construction unit for constructing a first matching logic;

a first matching unit, configured to perform matching training on the first matching sequence and the second matching sequence according to the first matching logic.

Further, the system further comprises:

a first embedding unit for embedding an access-type signal instruction for the first matching sequence;

a second embedding unit for embedding an answerback signal instruction for the second matching sequence;

a second obtaining unit, configured to obtain a first requirement feature in the requirement feature set, load the first requirement feature into the access signal instruction, and send the first requirement feature and the access signal instruction to the second matching sequence for cyclic traversal, so as to obtain a first skill feature set in the second matching sequence;

and the first loading unit is used for loading the first skill characteristic set to the answer type signal instruction and feeding back the first skill characteristic set to the first requirement characteristic together to obtain a first skill employee set corresponding to the first skill characteristic set.

Further, the system further comprises:

a first input unit, configured to input the first requirement characteristic and the first skill characteristic set into a skill association matching model for training, and obtain a first association value between a first employee skill and the first requirement characteristic, a second association value between a second employee skill and the first requirement characteristic, and an nth association value between an nth employee skill and the first requirement characteristic in the first skill employee set;

a first classification unit, configured to classify the first relevance value, the second relevance value, and up to the nth relevance value based on a preset relevance value, to obtain a first standard relevance value set and a second non-standard relevance value set;

a third obtaining unit, configured to obtain a set of post essential knowledge structures of the first set of qualifying relevance values;

a first generating unit, configured to generate a personalized learning decision model for the set of non-standard employees based on the set of post essential knowledge structures and the second set of non-standard relevance values.

Further, the system further comprises:

a fourth obtaining unit, configured to obtain, based on the personalized learning decision model, a first learning achievement of the non-standard employee set after a preset time;

the second division unit is used for carrying out order division on the post necessary knowledge structure set to generate a first-order knowledge architecture, a second-order knowledge architecture and a third-order knowledge architecture;

a first judging unit, configured to judge whether the first learning achievement reaches the third-order knowledge framework;

and the second driving unit is used for carrying out advanced driving learning on the non-standard employee set if the first learning result reaches the third-order knowledge framework.

Further, the system further comprises:

the first analysis unit is used for carrying out correlation analysis on the additional feature information of each employee to obtain a first correlation additional feature and a second correlation additional feature;

the second fusion unit is used for performing information fusion on the employee role positioning sets and the first correlation additional features to generate primary employee portrait sets;

and the third fusion unit is used for carrying out secondary information fusion on the second relevant additional features and the primary staff image sets to generate the staff image sets.

Further, the system further comprises:

the second analysis unit is used for performing traversal analysis on the post knowledge structure to obtain a set of functional departments;

a fifth obtaining unit, configured to obtain execution subject information of each functional department in the set of functional departments;

and the second conversion unit is used for carrying out format conversion on the function department set and the execution main body information to generate the position map sets.

In the present specification, the embodiments are described in a progressive manner, and each embodiment focuses on differences from other embodiments, and the data-driven-based enterprise learning method and the specific example in the first embodiment of fig. 1 are also applicable to the data-driven-based enterprise learning system of the present embodiment, and through the foregoing detailed description of the data-driven-based enterprise learning method, a skilled person in the art can clearly know a data-driven-based enterprise learning system in the present embodiment, so for the brevity of the description, detailed description is not repeated here. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Exemplary electronic device

The electronic device of the present invention is described below with reference to fig. 7.

Fig. 7 illustrates a schematic structural diagram of an electronic device according to the present invention.

Based on the inventive concept of a data-driven enterprise learning method as described in the previous embodiments, the present invention further provides a data-driven enterprise learning system, on which a computer program is stored, which when executed by a processor implements the steps of any one of the above-described data-driven enterprise learning methods.

Where in fig. 7 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 305 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium.

The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.

The invention provides a data-driven enterprise learning method, which is applied to a data-driven enterprise learning system, wherein the method comprises the following steps: setting up a distributed learning decision framework of a target enterprise, wherein the distributed learning decision framework comprises a data traversal layer, an image generation layer and a decision matching layer; traversing the mainstream operation information of the target enterprise based on the data traversal layer to obtain a post knowledge structure of the target enterprise; carrying out format conversion on the post knowledge structure to generate each post map set; based on the image generation layer, carrying out role positioning on internal employees of the target enterprise to generate an employee role positioning set; according to the additional characteristic information of each employee, performing information fusion on the role positioning sets of each employee to generate image sets of each employee; uploading the post map sets and the employee image sets to the decision matching layer for matching training to obtain an individualized learning decision model set of the internal employees; and performing driving learning on each employee of the target enterprise based on the personalized learning decision model set. The technical problems that self-adaptive training and learning of internal staffs are difficult to carry out by enterprises, so that development roads of the staffs are disconnected from sustainable development of the enterprises, the individual development of the staffs is slow, and meanwhile good sustainable development of the enterprises cannot be actively assisted are solved. Through the operation project mainstream to the target enterprise ergodic accurate post knowledge structure collection, generate accurate each post map, carry out accurate role location and skill level test to the inside staff of enterprise simultaneously, combine individual habit characteristic, establish every staff's accurate portrait, carry out data analysis through to the picture, can make individualized study decision-making model for every staff, reach the training study that carries out the self-adaptation to inside staff, when improving staff professional skill, the good sustainable development's of helping hand enterprise technical effect.

The invention also provides an electronic device, which comprises a processor and a memory;

the memory is used for storing;

the processor is configured to execute the method according to any one of the first embodiment through calling.

The invention also provides a computer program product comprising a computer program and/or instructions which, when executed by a processor, performs the steps of the method of any of the above embodiments.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely software embodiment, an entirely hardware embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention is in the form of a computer program product that may be embodied on one or more computer-usable storage media having computer-usable program code embodied therewith. And such computer-usable storage media include, but are not limited to: various media capable of storing program codes, such as a usb disk, a portable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk Memory, a Compact Disc Read-Only Memory (CD-ROM), and an optical Memory.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a system for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the present invention and its equivalent technology, it is intended that the present invention also include such modifications and variations.

Claims (10)

1. A data-driven enterprise learning method, the method comprising:

setting up a distributed learning decision framework of a target enterprise, wherein the distributed learning decision framework comprises a data traversal layer, an image generation layer and a decision matching layer;

traversing the mainstream operation information of the target enterprise based on the data traversal layer to obtain a post knowledge structure of the target enterprise;

carrying out format conversion on the post knowledge structure to generate a set of each post map;

based on the image generation layer, carrying out role positioning on internal employees of the target enterprise to generate an employee role positioning set;

according to the additional characteristic information of each employee, performing information fusion on the role positioning sets of each employee to generate image sets of each employee;

uploading the post map sets and the employee image sets to the decision matching layer for matching training to obtain an individualized learning decision model set of the internal employees;

and performing driving learning on each employee of the target enterprise based on the personalized learning decision model set.

2. The method of claim 1, wherein uploading the respective position map sets and the respective employee image sets to the decision matching layer for matching training comprises:

performing hierarchical division on the decision matching layer to generate a first matching sequence and a second matching sequence, wherein the second matching sequence is in one-to-one correspondence with the first matching sequence;

performing demand feature extraction on each post in each post map set to generate a demand feature set, and inputting the demand feature set into the first matching sequence;

performing skill feature extraction on each employee in each employee image set to generate a skill feature set, and inputting the skill feature set into the second matching sequence;

constructing a first matching logic;

and performing matching training on the first matching sequence and the second matching sequence according to the first matching logic.

3. The method of claim 2, wherein said constructing a first match logic comprises:

embedding an access type signal instruction into the first matching sequence;

embedding a response type signal instruction into the second matching sequence;

acquiring a first requirement characteristic in the requirement characteristic set, loading the first requirement characteristic to the access type signal instruction, and sending the first requirement characteristic to the second matching sequence for cycle traversal to acquire a first skill characteristic set in the second matching sequence;

and loading the first skill characteristic set to the answer signal instruction, and feeding back the first skill characteristic set and the answer signal instruction to the first requirement characteristic together to obtain a first skill employee set corresponding to the first skill characteristic set.

4. The method of claim 3, wherein the method comprises:

inputting the first requirement characteristic and the first skill characteristic set into a skill association matching model for training, and obtaining a first association value of a first employee skill and the first requirement characteristic, a second association value of a second employee skill and the first requirement characteristic in the first skill employee set until an Nth association value of an Nth employee skill and the first requirement characteristic;

classifying the first relevance value, the second relevance value and the Nth relevance value on the basis of a preset relevance value to obtain a first standard relevance value set and a second non-standard relevance value set;

obtaining a set of post necessary knowledge structures of the first set of qualifying relevance values;

and generating an individualized learning decision model of the non-standard employee set based on the post necessary knowledge structure set and the second non-standard association value set.

5. The method of claim 4, wherein the method comprises:

obtaining a first learning achievement of the non-standard employee set after a preset time based on the personalized learning decision model;

dividing the post necessary knowledge structure set in order to generate a first-order knowledge framework, a second-order knowledge framework and a third-order knowledge framework;

judging whether the first learning achievement reaches the third-order knowledge architecture;

and if the first learning result reaches the third-order knowledge framework, performing advanced driving learning on the non-standard employee set.

6. The method of claim 1, wherein the fusing the information of the role positioning sets of the employees according to the additional feature information of the employees comprises:

performing relevance analysis on the additional feature information of each employee to obtain a first relevance additional feature and a second relevance additional feature;

performing information fusion on the employee role positioning sets and the first correlation additional features to generate primary employee portrait sets;

and performing secondary information fusion on the second correlation additional characteristics and the primary staff image sets to generate the staff image sets.

7. The method of claim 1, wherein said converting the post knowledge structure into a format comprises:

traversing and analyzing the post knowledge structure to obtain a set of functional departments;

acquiring execution main body information of each functional department in the functional department set;

and carrying out format conversion on the functional department set and the execution main body information to generate the position map sets.

8. A data-driven enterprise learning system, the system comprising:

the system comprises a first building unit, a second building unit and a third building unit, wherein the first building unit is used for building a distributed learning decision framework of a target enterprise, and the distributed learning decision framework comprises a data traversal layer, an image generation layer and a decision matching layer;

a first obtaining unit, configured to traverse the mainstream operation information of the target enterprise based on the data traversal layer, and obtain a post knowledge structure of the target enterprise;

the first conversion unit is used for carrying out format conversion on the post knowledge structure to generate each post map set;

the first positioning unit is used for carrying out role positioning on internal staff of the target enterprise based on the image generation layer to generate staff role positioning sets;

the first fusion unit is used for carrying out information fusion on the employee role positioning sets according to the additional characteristic information of the employees to generate employee image sets;

the first uploading unit is used for uploading the post map sets and the employee image sets to the decision matching layer for matching training to obtain an individualized learning decision model set of the internal employees;

a first driving unit, configured to perform driving learning on each employee of the target enterprise based on the personalized learning decision model set.

9. An electronic device comprising a processor and a memory;

the memory is used for storing;

the processor is used for executing the method of any one of claims 1-7 through calling.

10. A computer program product comprising a computer program and/or instructions, characterized in that the computer program and/or instructions, when executed by a processor, implement the steps of the method according to any one of claims 1 to 7.

Images