CN111931068B - Intelligent recommendation method based on enterprise online education - Google Patents

Intelligent recommendation method based on enterprise online education Download PDF

Info

Publication number
CN111931068B
CN111931068B CN202010982926.0A CN202010982926A CN111931068B CN 111931068 B CN111931068 B CN 111931068B CN 202010982926 A CN202010982926 A CN 202010982926A CN 111931068 B CN111931068 B CN 111931068B
Authority
CN
China
Prior art keywords
data
knowledge
user
information
knowledge data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010982926.0A
Other languages
Chinese (zh)
Other versions
CN111931068A (en
Inventor
赵隽隽
赵剑飞
欧阳禄萍
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhixueyun (Beijing) Technology Co.,Ltd.
Original Assignee
Zhixueyun Beijing Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhixueyun Beijing Technology Co ltd filed Critical Zhixueyun Beijing Technology Co ltd
Priority to CN202010982926.0A priority Critical patent/CN111931068B/en
Publication of CN111931068A publication Critical patent/CN111931068A/en
Application granted granted Critical
Publication of CN111931068B publication Critical patent/CN111931068B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3344—Query execution using natural language analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/335—Filtering based on additional data, e.g. user or group profiles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/258—Heading extraction; Automatic titling; Numbering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention provides an intelligent recommendation method based on enterprise online education, which comprises the following steps: acquiring knowledge data and storing the knowledge data in a knowledge database; acquiring user data and behavior data of a user; acquiring necessary recommended resources pushed by an enterprise; the knowledge recommendation model is used for acquiring corresponding knowledge data in the knowledge database according to the user data and the behavior data; the knowledge recommendation model is also used for acquiring corresponding necessary recommended resources according to the user data; combining the acquired knowledge data with the necessary recommended resources to generate resource recommended data, and transmitting the resource recommended data to the user side; the method combines the necessary recommended resources needed to be learned by the user and the knowledge data interested by the user, generates the resource recommended data and pushes the resource recommended data to the user, so that the necessary recommended resources and the knowledge data are transmitted to the user side at the same time, and the function of enterprise online education is further realized.

Description

Intelligent recommendation method based on enterprise online education
Technical Field
The invention relates to the technical field of information push, in particular to an intelligent recommendation method based on enterprise online education.
Background
With the continuous development of big data technology and artificial intelligence technology, the information can be pushed more conveniently and quickly; meanwhile, the information is pushed to the user according to the information browsing record of the user and the preference of the user to the information, so that the user experience is greatly improved;
however, currently, for information pushing, only the knowledge data in which the user is interested is recommended to the user based on the interests and hobbies of the user, and when an enterprise needs to push necessary resources to be learned to the user, the necessary resources to be learned by the user can only be transmitted to the user by means of a traditional mail mode.
Therefore, an intelligent recommendation method based on enterprise online education is urgently needed.
Disclosure of Invention
In order to solve the technical problems, the invention provides an intelligent recommendation method based on enterprise online education, which is used for transmitting knowledge data interesting to a user and necessary recommendation resources pushed by enterprises to the user.
The embodiment of the invention provides an intelligent recommendation method based on enterprise online education, which is characterized by comprising the following steps:
acquiring knowledge data of an enterprise, and storing the knowledge data in a knowledge database;
acquiring user data and behavior data of a user;
acquiring necessary recommended resources pushed by an enterprise;
the knowledge recommendation model is used for acquiring corresponding knowledge data in the knowledge database according to the user data and the behavior data; the knowledge recommendation model is further used for acquiring the corresponding necessary recommended resources according to the user data; and combining the acquired knowledge data and the necessary recommended resources to generate resource recommended data, and transmitting the resource recommended data to a user side.
In one embodiment, obtaining knowledge data and saving the knowledge data to a knowledge database comprises:
acquiring the knowledge data based on big data technology, and detecting the knowledge data, which comprises:
acquiring knowledge data containing sensitive information, and marking the sensitive information in the knowledge data; analyzing the knowledge data marked with the sensitive information through a sensitive analysis model to obtain the sensitive information in the knowledge data and a relevant plot of the sensitive information;
detecting the acquired knowledge data, judging whether the knowledge data contains the sensitive information or the relevant plot of the sensitive information, and suspending the transmission of the knowledge data to the knowledge database when the knowledge data contains the sensitive information or the relevant plot of the sensitive information; when the knowledge data does not contain the sensitive information and the relevant situation of the sensitive information, transmitting the knowledge data to the knowledge database;
the knowledge database is used for identifying the knowledge data and acquiring the title information, the category information and the authority information of the knowledge data according to the content of the knowledge data; associating the knowledge data with the title information, the category information, the permission information of the knowledge data;
the knowledge recommendation model is configured to, according to the user data and the behavior data, acquire the corresponding knowledge data in the knowledge database, and includes:
acquiring corresponding knowledge data in the knowledge database according to the behavior data of the user;
acquiring the authority information of the knowledge data;
comparing the job information in the user data of the user with the authority information, and transmitting the title information and the category information of the knowledge data to the user side when the job information in the user data conforms to the authority information;
the user side is used for receiving a knowledge data acquisition instruction input by a user according to the title information and the category information displayed by the user side and transmitting the knowledge data acquisition instruction to the knowledge recommendation model;
and the knowledge recommendation model is used for acquiring corresponding knowledge data from the knowledge database according to the title information and the category information in the knowledge acquisition instruction and transmitting the corresponding knowledge data to the user side.
In one embodiment, when the knowledge data contains the sensitive information or a related episode of the sensitive information, suspending transmission of the knowledge data to the knowledge database comprises:
when the knowledge data only contains the sensitive information, deleting the sensitive information in the knowledge data, and detecting the semantic integrity of the knowledge data with the sensitive information deleted; when the semantics of the knowledge data for deleting the sensitive information are judged to be complete, transmitting the knowledge data for deleting the sensitive information to the knowledge database; when the semantics of the knowledge data for deleting the sensitive information are judged to be incomplete, detecting whether the key content of the knowledge data is missing, and when the key content of the knowledge data is missing, filtering the knowledge data for deleting the sensitive information; when the fact that key contents of the knowledge data are not lost is detected, restoring the part with incomplete semantics in the knowledge data to enable the semantics of the knowledge data after restoration processing to be complete, and transmitting the knowledge data after restoration processing to the knowledge database;
when the knowledge data only contains the relevant plot of the sensitive information, analyzing the relevant plot of the sensitive information through a sensitive analysis model, and judging whether the relevant plot of the sensitive information contains the induction of the sensitive information or the deformation of the sensitive information; when judging that the relevant plot of the sensitive information contains the induction of the sensitive information or the deformation of the sensitive information, filtering the knowledge data; when judging that the relevant plot of the sensitive information does not contain the induction of the sensitive information and the deformation of the sensitive information, transmitting the knowledge data to the knowledge database;
and when the knowledge data contains the sensitive information and the relevant situation of the sensitive information, filtering the knowledge data.
In one embodiment, obtaining user data and behavior data of the user comprises:
transmitting a user data acquisition instruction to the user side;
the user side is used for transmitting the user data corresponding to the user side to the knowledge recommendation model when receiving the user data acquisition instruction;
the knowledge database is also used for recording the acquisition record of the knowledge data by the user terminal when the user terminal acquires the knowledge data; acquiring an operation record of the user on the knowledge data based on the user end according to the acquisition record; the knowledge database is further used for acquiring interest information of the user on the knowledge data according to the acquisition record of the user on the knowledge data and the operation content of the operation record; and combining the acquisition record of the knowledge data, the operation record and the interest information of the user to generate behavior data of the user.
In one embodiment, the operation records comprise collecting operation, sharing operation and commenting operation of the knowledge data;
and the user data comprises name information, age information, job information and affiliated department information of the user.
In one embodiment, after acquiring the user data and the behavior data of the user, the method further includes:
obtaining comment operation in the operation record in the behavior data of the user;
whether the content of the comment operation of the user contains sensitive information or not is analyzed, when the content of the comment operation contains the sensitive information, the comment operation is deleted, and warning information is sent to the user side performing the comment operation; the user side is also used for displaying the warning information to a user;
recording the times of sending the warning information to the user side, and limiting the user to perform comment operation based on the user side within a preset time period when the times of sending the warning information to the user side reaches a first threshold value; and when the number of times of sending the warning information to the user side reaches a second threshold number of times, limiting any operation of the user based on the user side, and transmitting the user data of the user to enterprise background staff.
In one embodiment, obtaining the necessary recommended resources pushed by the enterprise includes:
acquiring the necessary recommended resources and acquiring recommendation authority information corresponding to the necessary recommended resources;
according to the content of the necessary recommended resource, acquiring the shortest time information of the necessary recommended resource read by a user, and transmitting the shortest time information corresponding to the necessary recommended resource to the user side;
the knowledge recommendation model is further used for acquiring the corresponding necessary recommended resources according to the user data; the method specifically comprises the following steps:
acquiring the information of the positions and the information of the departments in the user data;
comparing the recommendation permission information corresponding to the necessary recommended resources with the position information and the affiliated department information in the user data, and merging the acquired knowledge data and the necessary recommended resources to generate resource recommendation data when the position information and the affiliated department information both meet the recommendation permission information corresponding to the necessary recommended resources; after the necessary recommended resources in the resource recommendation data are subjected to top setting processing, the resource recommendation data are transmitted to the user side; when the job information and the department information do not meet the recommendation authority information corresponding to the necessary recommended resources, the necessary recommended resources are prohibited from being transmitted to the user side;
the user side is used for displaying the resource recommendation data transmitted by the knowledge recommendation model to a user; and the user side is further used for timing according to the shortest time information when the user reads the necessary resource data in the resource recommendation data based on the user side, and the user side can only display the necessary recommended resources in the timing process.
In one embodiment, the user side is further configured to record a reading condition and reading time information of the necessary recommended resource by the user, and transmit the reading condition and the reading time information to the knowledge recommendation model;
the knowledge recommendation model is further used for recording the learning conditions of all users on the necessary recommended resources according to the reading conditions and the reading time information transmitted by the user side and displaying the learning conditions to enterprise background staff;
the user side is further used for recording the necessary recommended resources and the knowledge data read by the user, establishing a read database of the user, and transmitting and storing the necessary recommended resources and the knowledge data read by the user to the read database; transmitting the read database to the knowledge recommendation model;
the knowledge recommendation model is further configured to compare the resource recommendation data with the necessary recommended resources and the knowledge data in the read database when the generated resource recommendation data is transmitted to the user side, filter the necessary recommended resources and the knowledge data that are in accordance with each other in the resource recommendation data when the resource recommendation data is in accordance with the necessary recommended resources and the knowledge data in the read database, and transmit the filtered resource recommendation data to the user side.
In one embodiment, obtaining the corresponding knowledge data in the knowledge database according to the user data and the behavior data includes:
the knowledge recommendation model is further used for classifying the user sides corresponding to the users according to the interest information; acquiring the knowledge data read by the users with the same interest information from the knowledge database according to a collaborative filtering algorithm, and transmitting the knowledge data to the user side corresponding to the user;
the knowledge recommendation model is further used for acquiring the knowledge data read by the user, performing deep understanding learning on the knowledge data by adopting a natural language processing technology, and acquiring the essential content and the related topological content of the knowledge data; inquiring knowledge data similar to the essential content and the related topological content in the knowledge database according to the essential content and the related topological content of the knowledge data, and transmitting the knowledge data acquired by inquiry to the user side;
acquiring current hot information through a network, and transmitting the current hot information to the knowledge database; and the knowledge database is used for storing the current hot information as knowledge data and transmitting the knowledge data to the user side.
In one embodiment, the process of combining the acquired knowledge data and the necessary recommended resources to generate resource recommendation data further includes:
acquiring a first data list of the knowledge data, and acquiring a second data list of the necessary recommended resources, wherein the first data list and the second data list comprise: the list name and the area name, the area position, the area attribute and the data index of each sub-area in the list;
according to the first data list and the second data list, temporary storage data of each sub-area are determined, data analysis is carried out on the temporary storage data, whether data to be eliminated exist in the temporary storage data is judged, and the data to be eliminated include: blank characters, overlapping fields;
if the data to be eliminated exists, eliminating the data to be eliminated, simultaneously acquiring residual data of a corresponding sub-area, determining a morphological index of the residual data, and simultaneously importing the morphological index into a knowledge morphological model to obtain a knowledge form of the residual data;
if the temporary storage data does not exist, acquiring the knowledge form of the temporary storage data of the corresponding sub-area;
constructing a first modality set of the knowledge data based on the knowledge modality, and simultaneously constructing a second modality set of the necessary recommended resources;
calculating a first degree of match between a first knowledge form in the first set of forms and a second knowledge form in the second set of forms S1 and a second degree of match between each first knowledge form in the first set of forms and each remaining knowledge form S2, according to the following formulas;
Figure 393357DEST_PATH_IMAGE001
；
Figure 728524DEST_PATH_IMAGE002
；
wherein p1 represents the number of the first knowledge forms in the first form set, and the value range is [1, N1 ]]P2 represents the number of second knowledge forms in the second form set, and the value range is [1, N2 ]]And i represents the form index number of the first knowledge form and has a value range of [1, n1 ]]；
Figure 519762DEST_PATH_IMAGE003
A morphological parameter representing the ith morphological index in the p1 th first knowledge morphological index; j represents the form index number of the second knowledge form and has a value range of [1, n2 ]]；
Figure 598577DEST_PATH_IMAGE004
A morphological parameter representing a jth morphological index in the p2 th second knowledge morphology;
Figure 96554DEST_PATH_IMAGE005
an average morphology parameter representing a first knowledge morphology;
Figure 868201DEST_PATH_IMAGE006
representing the p2 th second knowledge morphological mean morphological parameter;
Figure 881157DEST_PATH_IMAGE007
the morphological parameters of the kth morphological index in the p3 th first knowledge form are represented, and the value range of k is [1, n2 ]]，
Figure 763662DEST_PATH_IMAGE008
An average morphology parameter representing the remaining knowledge morphology; wherein the value range of p3 is [1, N1-1 ]]；
If the first matching degree is greater than or equal to a first preset degree, judging whether the current capacity of the first form set is greater than the current capacity of the second form set;
if yes, deleting data related to the first knowledge form in the knowledge data;
otherwise, deleting the data related to the second knowledge form in the necessary recommended resources;
meanwhile, if the second matching degree is greater than or equal to a second preset degree, deleting data related to the knowledge form matched with the first knowledge form in the knowledge data;
if the first matching degree is smaller than a first preset degree and the second matching degree is smaller than a second preset degree, retaining the data corresponding to the first knowledge form;
and generating resource recommendation data according to the reserved data.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
Fig. 1 is a schematic structural diagram of an intelligent recommendation method based on enterprise online education provided by the invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
The embodiment of the invention provides an intelligent recommendation method based on enterprise online education, which comprises the following steps of:
acquiring knowledge data of an enterprise, and storing the knowledge data in a knowledge database;
acquiring user data and behavior data of a user;
acquiring necessary recommended resources pushed by an enterprise;
the knowledge recommendation model is used for acquiring corresponding knowledge data in the knowledge database according to the user data and the behavior data; the knowledge recommendation model is also used for acquiring corresponding necessary recommended resources according to the user data; and combining the acquired knowledge data and the necessary recommended resources to generate resource recommended data, and transmitting the resource recommended data to the user side.
The working principle of the method is as follows: acquiring knowledge data and storing the knowledge data in a knowledge database; acquiring user data and behavior data of a user; acquiring necessary recommended resources pushed by an enterprise; the knowledge recommendation model acquires corresponding knowledge data in a knowledge database according to the user data and the behavior data; the knowledge recommendation model acquires corresponding necessary recommended resources according to the user data; and combining the acquired knowledge data and the necessary recommended resources to generate resource recommended data, and transmitting the resource recommended data to the user side.
In the embodiment, the acquisition of corresponding knowledge data in a knowledge database is realized according to the acquired user data and behavior data through a knowledge recommendation model; the necessary recommended resources are acquired according to the user data of the user; the acquired knowledge data and the necessary recommended resources are combined, so that the acquisition of the resource recommended data is realized, and the resource recommended data is transmitted to the user side; compared with the prior art, the method not only realizes the acquisition of the knowledge data which is interested by the user from the knowledge database according to the user data and the behavior data of the user; according to the user data of the user, the intelligent acquisition of necessary recommended resources required to be learned by the user is realized; and the acquired knowledge data and the necessary recommended resources are combined to generate resource recommended data to be transmitted to the user side, so that the knowledge data interested by the user and the necessary recommended resources required to be learned by the user are transmitted to the user side, and the user can acquire the knowledge data and the necessary recommended resources recommended by the learning enterprises through the user side.
The beneficial effects of the above technical scheme are: the method combines the necessary recommended resources needed to be learned by the user and the knowledge data interested by the user to generate resource recommended data to be pushed to the user, realizes the transmission of the necessary recommended resources and the knowledge data to the user side at the same time, and simultaneously realizes the transmission of the necessary recommended resources pushed by the enterprise to the user side by adopting a mode of recommending the knowledge data to the user, thereby further realizing the function of online education of the enterprise.
The embodiment of the invention provides an intelligent recommendation method based on enterprise online education, which comprises the following steps of obtaining knowledge data, storing the knowledge data into a knowledge database, and:
knowledge data are acquired based on big data technology and detected, and the method comprises the following steps:
acquiring knowledge data containing sensitive information, and marking the sensitive information in the knowledge data; analyzing the knowledge data marked with the sensitive information through a sensitive analysis model to obtain the sensitive information in the knowledge data and relevant plots of the sensitive information;
detecting the acquired knowledge data, judging whether the knowledge data contains sensitive information or a relevant plot of the sensitive information, and suspending transmission of the knowledge data to the knowledge database when the knowledge data contains the sensitive information or the relevant plot of the sensitive information; when the knowledge data does not contain the sensitive information and the relevant situation of the sensitive information, the knowledge data is transmitted to a knowledge database;
the knowledge database is used for identifying the knowledge data and acquiring the title information, the category information and the authority information of the knowledge data according to the content of the knowledge data; associating the knowledge data with title information, category information and authority information of the knowledge data;
the knowledge recommendation model is used for acquiring corresponding knowledge data in the knowledge database according to the user data and the behavior data, and comprises the following steps:
acquiring corresponding knowledge data in a knowledge database according to the behavior data of the user;
acquiring authority information of knowledge data;
comparing the job information in the user data of the user with the authority information, and transmitting the title information and the category information of the knowledge data to the user side when the job information in the user data conforms to the authority information;
the user side is used for receiving a knowledge data acquisition instruction input by a user according to the title information and the category information displayed by the user side and transmitting the knowledge data acquisition instruction to the knowledge recommendation model;
and the knowledge recommendation model is used for acquiring corresponding knowledge data from the knowledge database according to the title information and the category information in the knowledge acquisition instruction and transmitting the corresponding knowledge data to the user side.
In the embodiment, the sensitive information in the knowledge data and the relevant plot of the sensitive information are obtained by analyzing the knowledge data containing the sensitive information; detecting the acquired knowledge data, detecting whether the knowledge data contains sensitive information or a relevant plot of the sensitive information, and suspending transmission of the knowledge data to the knowledge database when the knowledge data contains the sensitive information or the relevant plot of the sensitive information; when the knowledge data does not contain the sensitive information and the relevant situation of the sensitive information, the knowledge data is transmitted to a knowledge database; therefore, the acquisition of knowledge data which does not contain sensitive information is realized, and the knowledge data is transmitted to a knowledge database; the knowledge recommendation model acquires corresponding knowledge data in a knowledge database according to the behavior data of the user; acquiring authority information of the knowledge data, comparing the job information in the user data of the user with the authority information, judging that the authority of the user accords with the acquired knowledge data when the job information in the user data accords with the authority information, and transmitting the title information and the category information of the knowledge data to a user side; the method comprises the steps that a user side receives a knowledge data acquisition instruction input by a user according to title information and category information displayed by the user side, and the knowledge data acquisition instruction is transmitted to a knowledge recommendation model; and the knowledge recommendation model acquires corresponding knowledge data from the knowledge database according to the title information and the category information in the knowledge acquisition instruction and transmits the corresponding knowledge data to the user side.
The beneficial effects of the above technical scheme are: by the technical scheme, the knowledge data can be acquired according to the user data and the behavior data of the user.
The embodiment of the invention provides an intelligent recommendation method based on enterprise online education, wherein when knowledge data contains sensitive information or relevant conditions of the sensitive information, the step of suspending transmission of the knowledge data to a knowledge database comprises the following steps:
when the knowledge data only contains sensitive information, deleting the sensitive information in the knowledge data, and detecting the semantic integrity of the knowledge data with the sensitive information deleted; when the semantics of the knowledge data for deleting the sensitive information are judged to be complete, transmitting the knowledge data for deleting the sensitive information to a knowledge database; when the semantics of the knowledge data for deleting the sensitive information are judged to be incomplete, detecting whether the key content of the knowledge data is missing, and when the key content of the knowledge data is missing, filtering the knowledge data for deleting the sensitive information; when detecting that the key content of the knowledge data is not missing, recovering the part with incomplete semantics in the knowledge data to ensure that the semantics of the recovered knowledge data are complete, and transmitting the recovered knowledge data to a knowledge database;
when the knowledge data only contain the relevant plots of the sensitive information, analyzing the relevant plots of the sensitive information through a sensitive analysis model, and judging whether the relevant plots of the sensitive information contain the induction of the sensitive information or the deformation of the sensitive information; when the relevant plot of the sensitive information contains the induction of the sensitive information or the deformation of the sensitive information, filtering the knowledge data; when judging that the relevant plot of the sensitive information does not contain the induction of the sensitive information and the deformation of the sensitive information, transmitting the knowledge data to a knowledge database;
and when the knowledge data contains the sensitive information and the relevant conditions of the sensitive information, filtering the knowledge data.
In the embodiment, when the knowledge data only contains sensitive information, the sensitive information in the knowledge data is deleted, and the semantic integrity of the knowledge data with the sensitive information deleted is detected; when the semantics of the knowledge data for deleting the sensitive information are judged to be complete, the knowledge data for deleting the sensitive information is transmitted to a knowledge database, so that the sensitive information in the knowledge data is filtered, and when the semantics of the knowledge data for deleting the sensitive information are complete, the knowledge data is transmitted to the knowledge database; when the semantics of the knowledge data for deleting the sensitive information are judged to be incomplete, detecting whether the key content of the knowledge data is missing, and when the key content of the knowledge data is missing, filtering the knowledge data for deleting the sensitive information; when detecting that the key content of the knowledge data is not missing, restoring the part with incomplete semantics in the knowledge data to complete the semantics of the restored knowledge data, and transmitting the restored knowledge data to a knowledge database, so that when the semantics of the knowledge data for deleting sensitive information is incomplete and the key content of the knowledge data is not missing, restoring the part with incomplete semantics in the knowledge data is realized, the semantics of the restored knowledge data is complete, and the restored knowledge data is transmitted to the knowledge database; when the knowledge data only contain the relevant plots of the sensitive information, analyzing the relevant plots of the sensitive information through a sensitive analysis model, and judging whether the relevant plots of the sensitive information contain the induction of the sensitive information or the deformation of the sensitive information; when the relevant plot of the sensitive information contains the induction of the sensitive information or the deformation of the sensitive information, filtering the knowledge data; when judging that the relevant plot of the sensitive information does not contain the induction of the sensitive information and the deformation of the sensitive information, transmitting the knowledge data to a knowledge database; and when the knowledge data contains the sensitive information and the relevant conditions of the sensitive information, filtering the knowledge data.
The beneficial effects of the above technical scheme are: the method and the system realize the processing of the knowledge data of the sensitive information or the relevant plots of the sensitive information, transmit the processed knowledge data to the knowledge database, and further effectively avoid the transmission of the knowledge data of the sensitive information or the relevant plots of the sensitive information to the user side.
The embodiment of the invention provides an intelligent recommendation method based on enterprise online education, which comprises the following steps of:
transmitting a user data acquisition instruction to a user side;
the user side is used for transmitting the user data corresponding to the user side to the knowledge recommendation model when receiving the user data acquisition instruction;
the knowledge database is also used for recording the acquisition record of the knowledge data by the user end when the user end acquires the knowledge data; acquiring an operation record of the user on the knowledge data based on the user end according to the acquisition record; the knowledge database is also used for acquiring the interest information of the user on the knowledge data according to the acquisition record of the user on the knowledge data and the operation content of the operation record; and combining the acquisition records and the operation records of the knowledge data and the interest information of the user to generate the behavior data of the user.
The beneficial effects of the above technical scheme are: when the user side receives the transmitted data acquisition instruction, the user data corresponding to the user side is transmitted to the knowledge recommendation model, so that the user data is acquired; the knowledge database is used for recording the acquisition record of the user end on the knowledge data; acquiring an operation record of the user on the knowledge data based on the user end according to the acquisition record; the knowledge database acquires interest information of the user on the knowledge data according to the acquisition record of the user on the knowledge data and the operation content of the operation record; and the acquisition records and the operation records of the knowledge data and the interest information of the user are combined, so that the acquisition of the behavior data of the user is realized.
The embodiment of the invention provides an intelligent recommendation method based on enterprise online education, which comprises the steps of operation recording, wherein the operation recording comprises collection operation, sharing operation and comment operation on knowledge data;
and the user data comprises name information, age information, job information and affiliated department information of the user. Therefore, the acquisition of the user data and the operation record of the user on the knowledge data is realized through the technical scheme.
The embodiment of the invention provides an intelligent recommendation method based on enterprise online education, which comprises the following steps of after acquiring user data and behavior data of a user:
obtaining comment operation in operation records in behavior data of a user;
whether the content of the comment operation of the user contains sensitive information or not is analyzed, when the content of the comment operation contains sensitive information, the comment operation is deleted, and warning information is sent to a user side performing the comment operation; the user side is also used for displaying the warning information to the user;
recording the times of sending warning information to a user side, and limiting a user to perform comment operation based on the user side within a preset time period when the times of sending warning information to the user side reaches a first threshold value; and when the number of times of sending the warning information to the user side reaches a second threshold number of times, limiting any operation of the user based on the user side, and transmitting the user data of the user to enterprise background staff.
In the embodiment, whether the content of the comment operation in the operation record in the behavior data of the user contains sensitive information is detected, when the content of the comment operation contains the sensitive information, the comment operation is deleted, and warning information is sent to a user side performing the comment operation; the user side displays the warning information to a user to remind the user who sends comment operation containing sensitive information through the user side; recording the number of times of sending warning information to the user side, and limiting the user to perform comment operation based on the user side within a preset time period (for example, the preset time period is 24 hours) when the number of times of sending warning information to the user side reaches a first threshold number of times (for example, the first threshold number of times is 1 time); when the number of times of sending the warning information to the user side reaches a second threshold number of times (for example, the first threshold number of times is 3), limiting any operation of the user based on the user side, and transmitting the user data of the user to the enterprise background staff.
The beneficial effects of the above technical scheme are: the comment operation can be deleted in time when the comment operation carried out by the user violates rules, and a warning is sent to the user to remind the user to standardize the comment operation.
The embodiment of the invention provides an intelligent recommendation method based on enterprise online education, which comprises the following steps of:
acquiring necessary recommended resources and acquiring recommendation authority information corresponding to the necessary recommended resources;
acquiring the shortest time information of reading the necessary recommended resources by the user according to the content of the necessary recommended resources, and transmitting the shortest time information corresponding to the necessary recommended resources to the user side;
the knowledge recommendation model is also used for acquiring corresponding necessary recommended resources according to the user data; the method specifically comprises the following steps:
acquiring the information of the positions and the information of the departments in the user data;
comparing the recommendation authority information corresponding to the necessary recommended resources with the position information and the affiliated department information in the user data, and merging the acquired knowledge data and the necessary recommended resources to generate resource recommendation data when the position information and the affiliated department information both meet the recommendation authority information corresponding to the necessary recommended resources; after the necessary recommended resources in the resource recommendation data are subjected to top setting processing, the resource recommendation data are transmitted to the user side; when the job information and the department information do not meet the recommendation authority information corresponding to the necessary recommended resources, the necessary recommended resources are prohibited from being transmitted to the user side;
the user side is used for displaying the resource recommendation data transmitted by the knowledge recommendation model to the user; and the user side is also used for timing according to the shortest time information when the user reads necessary resource data in the resource recommendation data based on the user side, and only the necessary recommended resources can be displayed by the user side in the timing process.
In the embodiment, by acquiring necessary recommended resources and recommended permission information corresponding to the necessary recommended resources, and comparing the recommended permission information corresponding to the necessary recommended resources with the position information and the affiliated department information in the user data, when both the position information and the affiliated department information meet the recommended permission information corresponding to the necessary recommended resources, the acquired knowledge data and the necessary recommended resources are combined to generate resource recommended data; after the necessary recommended resources in the resource recommended data are subjected to top setting processing, the resource recommended data are transmitted to the user side, so that the resource recommended data are transmitted to the user side, the necessary recommended resources in the resource recommended data are set on the top, and the user can read the necessary recommended resources conveniently; and when the user reads the necessary recommended resources based on the user side, timing is carried out according to the shortest time information of the necessary recommended resources read by the user, and in the timing process, the user side can only display the necessary recommended resources, so that the user can read the necessary recommended resources.
The embodiment of the invention provides an intelligent recommendation method based on enterprise online education, wherein a user side is also used for recording the reading condition and the reading time information of a user on necessary recommended resources and transmitting the reading condition and the reading time information to a knowledge recommendation model;
the knowledge recommendation model is also used for recording the learning conditions of all users on the necessary recommended resources according to the reading conditions and the reading time information transmitted by the user side and displaying the learning conditions to enterprise background staff;
the user side is also used for recording the necessary recommended resources and knowledge data read by the user, establishing a read database of the user, and transmitting and storing the necessary recommended resources and knowledge data read by the user to the read database; transmitting the read database to a knowledge recommendation model;
the knowledge recommendation model is further used for comparing the resource recommendation data with the necessary recommendation resources and the knowledge data in the read database when the generated resource recommendation data are transmitted to the user side, filtering the necessary recommendation resources and the knowledge data which are compared and consistent in the resource recommendation data when the resource recommendation data are compared and consistent with the necessary recommendation resources and the knowledge data in the read database, and transmitting the filtered resource recommendation data to the user side.
In the embodiment, the reading condition and the reading time information of the necessary recommended resources by the user are recorded through the user side, and the reading condition and the reading time information are transmitted to the knowledge recommendation model; the knowledge recommendation model records the learning conditions of all users on the necessary recommended resources according to the reading conditions and the reading time information transmitted by the user side, and displays the learning conditions to enterprise background workers, so that the enterprise background workers can acquire the learning conditions of all users on the necessary recommended resources; the user side stores the necessary recommended resources and knowledge data which are read by the user based on the user side into a read database of the user, and transmits the read database to the knowledge recommendation model; when the knowledge recommendation model transmits the generated resource recommendation data to the user side, the resource recommendation data is compared with the necessary recommendation resources and the knowledge data in the read database, when the resource recommendation data is compared with the necessary recommendation resources and the knowledge data in the read database to be consistent, the necessary recommendation resources and the knowledge data which are compared to be consistent in the resource recommendation data are filtered, and the filtered resource recommendation data is transmitted to the user side, so that the repeated knowledge data and the necessary recommendation resources are effectively prevented from being transmitted to the user side, and the user experience is effectively improved.
The embodiment of the invention provides an intelligent recommendation method based on enterprise online education, and the knowledge recommendation model is used for acquiring corresponding knowledge data in a knowledge database according to user data and behavior data and comprises the following steps:
the knowledge recommendation model is also used for classifying the user sides corresponding to the users according to the interest information; acquiring knowledge data read by users with the same interest information from a knowledge database according to a collaborative filtering algorithm, and transmitting the knowledge data to a user side corresponding to the user;
the knowledge recommendation model is further used for acquiring the knowledge data read by the user, performing deep understanding learning on the knowledge data by adopting a natural language processing technology, and acquiring the essential content and the related topological content of the knowledge data; inquiring knowledge data similar to the essential content and the related topological content in a knowledge database according to the essential content and the related topological content of the knowledge data, and transmitting the knowledge data acquired by inquiry to a user side;
acquiring current hot information through a network, and transmitting the current hot information to a knowledge database; and the knowledge database is used for storing the current hot information as knowledge data and transmitting the knowledge data to the user side.
In the embodiment, the knowledge recommendation model classifies user sides corresponding to users according to interest information, acquires knowledge data read by users with the same interest information from a knowledge database by adopting a collaborative filtering algorithm, and transmits the knowledge data to the user sides; the knowledge recommendation model also adopts a natural language processing technology to carry out deep understanding learning on the knowledge data read by the user, and the essential content and the related topological content of the knowledge data are obtained; inquiring knowledge data similar to the essential content and the related topological content in a knowledge database according to the essential content and the related topological content of the knowledge data, and transmitting the knowledge data acquired by inquiry to a user side; acquiring current hot information through a network, and transmitting the current hot information to a knowledge database; the knowledge database saves the current hot information as knowledge data and transmits the knowledge data to the user side; therefore, the technical scheme realizes that the knowledge recommendation model transmits the acquired knowledge data to the user side in various modes.
The embodiment of the invention provides an intelligent recommendation method based on enterprise online education, which is used for merging the acquired knowledge data and the necessary recommended resources to generate resource recommendation data, and further comprises the following steps:
acquiring a first data list of the knowledge data, and acquiring a second data list of the necessary recommended resources, wherein the first data list and the second data list comprise: the list name and the area name, the area position, the area attribute and the data index of each sub-area in the list;
according to the first data list and the second data list, temporary storage data of each sub-area are determined, data analysis is carried out on the temporary storage data, whether data to be eliminated exist in the temporary storage data is judged, and the data to be eliminated include: blank characters, overlapping fields;
if the data to be eliminated exists, eliminating the data to be eliminated, simultaneously acquiring residual data of a corresponding sub-area, determining a morphological index of the residual data, and simultaneously importing the morphological index into a knowledge morphological model to obtain a knowledge form of the residual data;
if the temporary storage data does not exist, acquiring the knowledge form of the temporary storage data of the corresponding sub-area;
constructing a first modality set of the knowledge data based on the knowledge modality, and simultaneously constructing a second modality set of the necessary recommended resources;
calculating a first degree of match between a first knowledge form in the first set of forms and a second knowledge form in the second set of forms S1 and a second degree of match between each first knowledge form in the first set of forms and each remaining knowledge form S2, according to the following formulas;
Figure 116146DEST_PATH_IMAGE001
；
Figure 121011DEST_PATH_IMAGE002
；
wherein p1 represents the number of the first knowledge forms in the first form set, and the value range is [1, N1 ]]P2 represents the number of second knowledge forms in the second form set, and the value range is [1, N2 ]]And i represents the form index number of the first knowledge form and has a value range of [1, n1 ]]；
Figure 558945DEST_PATH_IMAGE003
A morphological parameter representing the ith morphological index in the p1 th first knowledge morphological index; j represents the form index number of the second knowledge form and has a value range of [1, n2 ]]；
Figure 979563DEST_PATH_IMAGE004
A morphological parameter representing a jth morphological index in the p2 th second knowledge morphology;
Figure 514449DEST_PATH_IMAGE005
an average morphology parameter representing a first knowledge morphology;
Figure 627899DEST_PATH_IMAGE006
representing the p2 th second knowledge morphological mean morphological parameter;
Figure 553129DEST_PATH_IMAGE007
the morphological parameters of the kth morphological index in the p3 th first knowledge form are represented, and the value range of k is [1, n2 ]]，
Figure 777437DEST_PATH_IMAGE008
An average morphology parameter representing the remaining knowledge morphology; wherein the value range of p3 is [1, N1-1 ]]；
If the first matching degree is greater than or equal to a first preset degree, judging whether the current capacity of the first form set is greater than the current capacity of the second form set;
if yes, deleting data related to the first knowledge form in the knowledge data;
otherwise, deleting the data related to the second knowledge form in the necessary recommended resources;
meanwhile, if the second matching degree is greater than or equal to a second preset degree, deleting data related to the knowledge form matched with the first knowledge form in the knowledge data;
if the first matching degree is smaller than a first preset degree and the second matching degree is smaller than a second preset degree, retaining the data corresponding to the first knowledge form;
and generating resource recommendation data according to the reserved data.
In the above-described technical solution, the form of the data is, for example, any one of a push form including the data, a type to which the data belongs, the corresponding push content, and the like, and is mainly related to the push content.
The beneficial effects of the above technical scheme are: through obtaining relevant list, and then confirm the data of keeping in the subregion, judge through the knowledge form to the data of keeping in, obtain relevant set, simultaneously, through calculating first matching degree and second matching degree, can improve the effective screening to the data, guarantee at the propelling movement data in-process, reduce the overlap nature of data, improve the validity of propelling movement, and judge through the current capacity to the set, be convenient for delete the irrelevant data in the corresponding data, improve the propelling movement precision of data, and indirectly reduce the occupation to service resource, improve propelling movement efficiency.
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 claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (8)

1. An intelligent recommendation method based on enterprise online education is characterized by comprising the following steps:
acquiring knowledge data of an enterprise, and storing the knowledge data in a knowledge database;
acquiring user data and behavior data of a user;
acquiring necessary recommended resources pushed by an enterprise;
the knowledge recommendation model is used for acquiring corresponding knowledge data in the knowledge database according to the user data and the behavior data; the knowledge recommendation model is further used for acquiring the corresponding necessary recommended resources according to the user data; merging the acquired knowledge data and the necessary recommended resources to generate resource recommended data, and transmitting the resource recommended data to a user side;
acquiring knowledge data, and storing the knowledge data in a knowledge database comprises the following steps:
acquiring the knowledge data based on big data technology, and detecting the knowledge data, which comprises:
acquiring knowledge data containing sensitive information, and marking the sensitive information in the knowledge data; analyzing the knowledge data marked with the sensitive information through a sensitive analysis model to obtain the sensitive information in the knowledge data and a relevant plot of the sensitive information;
detecting the acquired knowledge data, judging whether the knowledge data contains the sensitive information or the relevant plot of the sensitive information, and suspending the transmission of the knowledge data to the knowledge database when the knowledge data contains the sensitive information or the relevant plot of the sensitive information; when the knowledge data does not contain the sensitive information and the relevant situation of the sensitive information, transmitting the knowledge data to the knowledge database;
the knowledge database is used for identifying the knowledge data and acquiring the title information, the category information and the authority information of the knowledge data according to the content of the knowledge data; associating the knowledge data with the title information, the category information, the permission information of the knowledge data;
a knowledge recommendation model, configured to obtain the corresponding knowledge data in the knowledge database according to the user data and the behavior data, where the knowledge recommendation model includes:
acquiring corresponding knowledge data in the knowledge database according to the behavior data of the user;
acquiring the authority information of the knowledge data;
comparing the job information in the user data of the user with the authority information, and transmitting the title information and the category information of the knowledge data to the user side when the job information in the user data conforms to the authority information;
the user side is used for receiving a knowledge data acquisition instruction input by a user according to the title information and the category information displayed by the user side and transmitting the knowledge data acquisition instruction to the knowledge recommendation model;
the knowledge recommendation model is used for acquiring corresponding knowledge data from the knowledge database according to the title information and the category information in the knowledge data acquisition instruction and transmitting the corresponding knowledge data to the user side;
in the process of combining the acquired knowledge data and the necessary recommended resources to generate resource recommendation data, the method further includes:
acquiring a first data list of the knowledge data, and acquiring a second data list of the necessary recommended resources, wherein the first data list and the second data list comprise: the list name and the area name, the area position, the area attribute and the data index of each sub-area in the list;
according to the first data list and the second data list, temporary storage data of each sub-area are determined, data analysis is carried out on the temporary storage data, whether data to be eliminated exist in the temporary storage data is judged, and the data to be eliminated include: blank characters, overlapping fields;
if the data to be eliminated exists, eliminating the data to be eliminated, simultaneously acquiring residual data of a corresponding sub-area, determining a morphological index of the residual data, and simultaneously importing the morphological index into a knowledge morphological model to obtain a knowledge form of the residual data;
if the temporary storage data does not exist, acquiring the knowledge form of the temporary storage data of the corresponding sub-area;
constructing a first modality set of the knowledge data based on the knowledge modality, and simultaneously constructing a second modality set of the necessary recommended resources;
calculating a first degree of match between a first knowledge form in the first set of forms and a second knowledge form in the second set of forms S1 and a second degree of match between each first knowledge form in the first set of forms and each remaining knowledge form S2, according to the following formulas;
Figure 705542DEST_PATH_IMAGE001
；
Figure 698906DEST_PATH_IMAGE002
；
wherein p1 represents the number of the first knowledge forms in the first form set, and the value range is [1, N1 ]]P2 represents the number of second knowledge forms in the second form set, and the value range is [1, N2 ]]And i represents the form index number of the first knowledge form and has a value range of [1, n1 ]]；
Figure 984394DEST_PATH_IMAGE003
A morphological parameter representing the ith morphological index in the p1 th first knowledge morphological index; j represents the form index number of the second knowledge form and has a value range of [1, n2 ]]；
Figure 721406DEST_PATH_IMAGE004
A morphological parameter representing a jth morphological index in the p2 th second knowledge morphology;
Figure 775949DEST_PATH_IMAGE005
an average morphology parameter representing a first knowledge morphology;
Figure 205794DEST_PATH_IMAGE006
representing the p2 th second knowledge morphological mean morphological parameter;
Figure 447419DEST_PATH_IMAGE007
the morphological parameters of the kth morphological index in the p3 th first knowledge form are represented, and the value range of k is [1, n2 ]]，
Figure 4434DEST_PATH_IMAGE008
An average morphology parameter representing the remaining knowledge morphology; wherein the value range of p3 is [1, N1-1 ]]；
If the first matching degree is greater than or equal to a first preset degree, judging whether the current capacity of the first form set is greater than the current capacity of the second form set;
if yes, deleting data related to the first knowledge form in the knowledge data;
otherwise, deleting the data related to the second knowledge form in the necessary recommended resources;
meanwhile, if the second matching degree is greater than or equal to a second preset degree, deleting data related to the knowledge form matched with the first knowledge form in the knowledge data;
if the first matching degree is smaller than a first preset degree and the second matching degree is smaller than a second preset degree, retaining the data corresponding to the first knowledge form;
and generating resource recommendation data according to the reserved data.
2. The method of claim 1, wherein when the knowledge data contains the sensitive information or a related episode of the sensitive information, suspending transmission of the knowledge data to the knowledge database comprises:
when the knowledge data only contains the sensitive information, deleting the sensitive information in the knowledge data, and detecting the semantic integrity of the knowledge data with the sensitive information deleted; when the semantics of the knowledge data for deleting the sensitive information are judged to be complete, transmitting the knowledge data for deleting the sensitive information to the knowledge database; when the semantics of the knowledge data for deleting the sensitive information are judged to be incomplete, detecting whether the key content of the knowledge data is missing, and when the key content of the knowledge data is missing, filtering the knowledge data for deleting the sensitive information; when the fact that key contents of the knowledge data are not lost is detected, restoring the part with incomplete semantics in the knowledge data to enable the semantics of the knowledge data after restoration processing to be complete, and transmitting the knowledge data after restoration processing to the knowledge database;
when the knowledge data only contains the relevant plot of the sensitive information, analyzing the relevant plot of the sensitive information through a sensitive analysis model, and judging whether the relevant plot of the sensitive information contains the induction of the sensitive information or the deformation of the sensitive information; when judging that the relevant plot of the sensitive information contains the induction of the sensitive information or the deformation of the sensitive information, filtering the knowledge data; when judging that the relevant plot of the sensitive information does not contain the induction of the sensitive information and the deformation of the sensitive information, transmitting the knowledge data to the knowledge database;
and when the knowledge data contains the sensitive information and the relevant situation of the sensitive information, filtering the knowledge data.
3. The method of claim 1, wherein obtaining user data and behavior data of a user comprises:
transmitting a user data acquisition instruction to the user side;
the user side is used for transmitting the user data corresponding to the user side to the knowledge recommendation model when receiving the user data acquisition instruction;
the knowledge database is also used for recording the acquisition record of the knowledge data by the user terminal when the user terminal acquires the knowledge data; acquiring an operation record of the user on the knowledge data based on the user end according to the acquisition record; the knowledge database is further used for acquiring interest information of the user on the knowledge data according to the acquisition record of the user on the knowledge data and the operation content of the operation record; and combining the acquisition record of the knowledge data, the operation record and the interest information of the user to generate behavior data of the user.
4. The method of claim 3,
the operation records comprise collection operation, sharing operation and comment operation of the knowledge data;
and the user data comprises name information, age information, job information and affiliated department information of the user.
5. The method of claim 4, after obtaining the user data and the behavior data of the user, further comprising:
obtaining comment operation in the operation record in the behavior data of the user;
whether the content of the comment operation of the user contains sensitive information or not is analyzed, when the content of the comment operation contains the sensitive information, the comment operation is deleted, and warning information is sent to the user side performing the comment operation; the user side is also used for displaying the warning information to a user;
recording the times of sending the warning information to the user side, and limiting the user to perform comment operation based on the user side within a preset time period when the times of sending the warning information to the user side reaches a first threshold value; and when the number of times of sending the warning information to the user side reaches a second threshold number of times, limiting any operation of the user based on the user side, and transmitting the user data of the user to enterprise background staff.
6. The method of claim 1, wherein obtaining necessary recommended resources pushed by the enterprise comprises:
acquiring the necessary recommended resources and acquiring recommendation authority information corresponding to the necessary recommended resources;
according to the content of the necessary recommended resource, acquiring the shortest time information of the necessary recommended resource read by a user, and transmitting the shortest time information corresponding to the necessary recommended resource to the user side;
the knowledge recommendation model is further configured to obtain, according to the user data, the corresponding necessary recommendation resource, where the necessary recommendation resource includes:
acquiring the information of the positions and the information of the departments in the user data;
comparing the recommendation permission information corresponding to the necessary recommended resources with the position information and the affiliated department information in the user data, and merging the acquired knowledge data and the necessary recommended resources to generate resource recommendation data when the position information and the affiliated department information both meet the recommendation permission information corresponding to the necessary recommended resources; after the necessary recommended resources in the resource recommendation data are subjected to top setting processing, the resource recommendation data are transmitted to the user side; when the job information and the department information do not meet the recommendation authority information corresponding to the necessary recommended resources, the necessary recommended resources are prohibited from being transmitted to the user side;
the user side is used for displaying the resource recommendation data transmitted by the knowledge recommendation model to a user; and the user side is further used for timing according to the shortest time information when the user reads the necessary resource data in the resource recommendation data based on the user side, and the user side can only display the necessary recommended resources in the timing process.
7. The method of claim 6,
the user side is further used for recording the reading condition and the reading time information of the necessary recommended resources by the user and transmitting the reading condition and the reading time information to the knowledge recommendation model;
the knowledge recommendation model is further used for recording the learning conditions of all users on the necessary recommended resources according to the reading conditions and the reading time information transmitted by the user side and displaying the learning conditions to enterprise background staff;
the user side is further used for recording the necessary recommended resources and the knowledge data read by the user, establishing a read database of the user, and transmitting and storing the necessary recommended resources and the knowledge data read by the user to the read database; transmitting the read database to the knowledge recommendation model;
the knowledge recommendation model is further configured to compare the resource recommendation data with the necessary recommended resources and the knowledge data in the read database when the generated resource recommendation data is transmitted to the user side, filter the necessary recommended resources and the knowledge data that are in accordance with each other in the resource recommendation data when the resource recommendation data is in accordance with the necessary recommended resources and the knowledge data in the read database, and transmit the filtered resource recommendation data to the user side.
8. The method of claim 3, wherein obtaining the corresponding knowledge data in the knowledge database based on the user data and the behavior data comprises:
the knowledge recommendation model is further used for classifying the user sides corresponding to the users according to the interest information; acquiring the knowledge data read by the users with the same interest information from the knowledge database according to a collaborative filtering algorithm, and transmitting the knowledge data to the user side corresponding to the user;
the knowledge recommendation model is further used for acquiring the knowledge data read by the user, performing deep understanding learning on the knowledge data by adopting a natural language processing technology, and acquiring the essential content and the related topological content of the knowledge data; inquiring knowledge data similar to the essential content and the related topological content in the knowledge database according to the essential content and the related topological content of the knowledge data, and transmitting the knowledge data acquired by inquiry to the user side;
acquiring current hot information through a network, and transmitting the current hot information to the knowledge database; and the knowledge database is used for storing the current hot information as knowledge data and transmitting the knowledge data to the user side.
CN202010982926.0A 2020-09-18 2020-09-18 Intelligent recommendation method based on enterprise online education Active CN111931068B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010982926.0A CN111931068B (en) 2020-09-18 2020-09-18 Intelligent recommendation method based on enterprise online education

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010982926.0A CN111931068B (en) 2020-09-18 2020-09-18 Intelligent recommendation method based on enterprise online education

Publications (2)

Publication Number Publication Date
CN111931068A CN111931068A (en) 2020-11-13
CN111931068B true CN111931068B (en) 2021-01-26

Family

ID=73335250

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010982926.0A Active CN111931068B (en) 2020-09-18 2020-09-18 Intelligent recommendation method based on enterprise online education

Country Status (1)

Country Link
CN (1) CN111931068B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1804179A1 (en) * 2005-12-27 2007-07-04 NTT DoCoMo INC. Service recommendation system and service recommendation method
CN110413877A (en) * 2019-07-02 2019-11-05 阿里巴巴集团控股有限公司 A kind of resource recommendation method, device and electronic equipment
CN110458641A (en) * 2019-06-28 2019-11-15 苏宁云计算有限公司 A kind of electric business recommended method and system
CN111444419A (en) * 2020-03-02 2020-07-24 平安国际智慧城市科技股份有限公司 Resource recommendation method and device, computer equipment and storage medium

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1804179A1 (en) * 2005-12-27 2007-07-04 NTT DoCoMo INC. Service recommendation system and service recommendation method
CN110458641A (en) * 2019-06-28 2019-11-15 苏宁云计算有限公司 A kind of electric business recommended method and system
CN110413877A (en) * 2019-07-02 2019-11-05 阿里巴巴集团控股有限公司 A kind of resource recommendation method, device and electronic equipment
CN111444419A (en) * 2020-03-02 2020-07-24 平安国际智慧城市科技股份有限公司 Resource recommendation method and device, computer equipment and storage medium

Also Published As

Publication number Publication date
CN111931068A (en) 2020-11-13

Similar Documents

Publication Publication Date Title
CN110765337B (en) Service providing method based on internet big data
CN109697214A (en) A kind of tourism data analysis system and method
CN110705288A (en) Big data-based public opinion analysis system
CN104160395A (en) Document classification system, document classification method, and document classification program
CN112632405A (en) Recommendation method, device, equipment and storage medium
CN112418695A (en) Multi-dimensional portrait construction method and recommendation method for scientific researchers in tobacco field
Shalev et al. Investigating missing person cases: how can we learn where they go or how far they travel?
CN111931068B (en) Intelligent recommendation method based on enterprise online education
US20140032675A1 (en) Method and system for pushing associated users in social networking service network
RU2660599C1 (en) Method of video data indexing for facet classification
CN112925899A (en) Ranking model establishing method, case clue recommending device and medium
CN109166012A (en) The method and apparatus of classification and information push for stroke predetermined class user
CN110928922B (en) Public policy analysis model deployment method and system based on big data mining
CN116595262A (en) Travel scheme recommendation method and device, electronic equipment and computer storage medium
CN107329956B (en) Project information standardization method and device
CN107491530B (en) Social relationship mining analysis method based on file automatic marking information
CN113779110B (en) Family relation network extraction method, device, computer equipment and storage medium
CN115080636A (en) Big data analysis system based on network service
CN113420711A (en) Service industry worker service behavior recognition algorithm and system
Auld et al. Demographic characterization of anonymous trace travel data
CN111368550A (en) Public opinion information management system
CN110796526A (en) Intellectual property transaction data system and processing method
Khalifa et al. Fake reviews detection based on both the review and the reviewer features under belief function theory
CN117272198B (en) Abnormal user generated content identification method based on business travel business data
CN113592432B (en) Work order weight judging method and device, electronic equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CP01 Change in the name or title of a patent holder

Address after: No.637, 6 / F, 101 West Fourth Ring Road South, Fengtai District, Beijing

Patentee after: Zhixueyun (Beijing) Technology Co.,Ltd.

Address before: No.637, 6 / F, 101 West Fourth Ring Road South, Fengtai District, Beijing

Patentee before: Zhixueyun (Beijing) Technology Co.,Ltd.

CP01 Change in the name or title of a patent holder