CN116595156B

CN116595156B - Knowledge management system and knowledge management method

Info

Publication number: CN116595156B
Application number: CN202310870610.6A
Authority: CN
Inventors: 张伟; 杜毅
Original assignee: Beijing Puhua Hengxin Technology Service Co ltd
Current assignee: Beijing Puhua Hengxin Technology Service Co ltd
Priority date: 2023-07-17
Filing date: 2023-07-17
Publication date: 2023-12-19
Anticipated expiration: 2043-07-17
Also published as: CN116595156A

Abstract

The application discloses a knowledge management system and a knowledge management method. The system includes a question and answer subsystem; the question-answering subsystem comprises at least one data cluster, wherein the data cluster comprises indication data and content data; if the content data of one data cluster contains the indication data of the other data cluster, the data structure relationship of the father node and the child node is formed; the question-answering subsystem responds to a first request of the first interface and outputs a first data set to the first interface; the first data set comprises a plurality of first data clusters; the question-answering subsystem receives a second data cluster through a second interface; the indication data of the second data cluster is included in the content data of the target data cluster. By adopting the technical scheme, the ductility of the data of the question-answering subsystem can be ensured. The IT service subsystem and the question-answering subsystem are also increased and matched accurately due to the synchronous increment of data, and the accuracy of the data is ensured.

Description

Knowledge management system and knowledge management method

Technical Field

The application relates to the technical field of internet, in particular to a knowledge management system and a knowledge management method.

Background

With the continuous development of internet technology, information retrieval and feedback become the most commonly used tool models in many fields.

The question and answer subsystem is used as an information storage system, and the data structure of knowledge points used in the question and answer subsystem is in the form of a tree structure, and nodes of the tree structure become classification nodes. Common question and answer subsystems include FAQ (Frequently Asked Questions) systems. The question answering system has the characteristics of clear structure framework, simple realization, easy understanding and the like. The question and answer subsystem is often used in conjunction with an IT service (IT Service Management) subsystem.

In the combination application of the existing IT service subsystem and the question-answering subsystem, the IT service subsystem initiates a data acquisition request according to a certain problem description, and the question-answering subsystem performs data classification positioning and data query in the existing database according to the problem description. However, the classification of data in the existing question-answering subsystem needs to be defined in advance and the update of the data needs to be performed manually, which causes a problem that the classification is not comprehensive enough, namely, the breadth is not enough. In addition, classification nodes that manually continue deep from one knowledge base classification node are not deep enough, i.e., there is a problem of insufficient depth. Therefore, the question and answer subsystem is often difficult to match to more accurate content, and reasonable data cannot be returned to the IT service subsystem, so that the use experience of a user is affected. In addition, the expansion of the question-answer knowledge base needs to be updated by special manual work, the instantaneity is difficult to ensure, and the labor cost is increased.

Disclosure of Invention

The embodiment of the application provides a knowledge management system and a knowledge management method. Aiming at the problems of insufficient classification breadth and classification depth of a question-answering subsystem and the need of manual classification in the prior art, a management subsystem is adopted to perform data analysis and data arrangement operation according to a new data request of an IT service subsystem, and under the condition that the question-answering subsystem does not have precisely matched knowledge point data, new knowledge points are generated and synchronized to the question-answering subsystem, so that the ductility of the data of the question-answering subsystem is ensured. The IT service subsystem and the question-answering subsystem are also increased and matched accurately due to the synchronous increment of data, and the accuracy of the data is ensured.

In a first aspect, embodiments of the present application provide a knowledge management system, the system comprising a question-answering subsystem;

the question-answering subsystem includes at least one data cluster including indicating data and content data; if the content data of one data cluster contains the indication data of the other data cluster, the data structure relationship of the father node and the child node is formed;

the question-answering subsystem responds to a first request of a first interface and outputs a first data set to the first interface; the first data set comprises a plurality of first data clusters;

The question-answering subsystem receives a second data cluster through a second interface;

the indication data of the second data cluster is contained in the content data of the target data cluster.

Further, the method comprises the steps of,

and the question-answering subsystem determines a plurality of first data clusters with semantic similarity larger than a set threshold value according to the keywords in the first request to form the first data set.

Further, the method comprises the steps of,

the question-answering subsystem receives a third data cluster from the second interface, wherein the third data cluster has no father-son node relation with the data cluster in the question-answering subsystem.

In a second aspect, an embodiment of the present application provides a knowledge management system, further including, on the basis of the system embodiment set forth in the first aspect, a management subsystem:

the management subsystem receives a second data set through a third interface, wherein the second data set comprises at least one first data cluster and/or a second request, the second request comprises supplementary data, and the second data cluster is generated based on the at least one first data cluster and/or the supplementary data.

Further:

the management subsystem is further configured to, when the target data cluster meeting the association degree cannot be determined based on the at least one first data cluster and/or the second request, generate a third data cluster based on the second request, and output the third data cluster to the second interface; and the third data cluster has no parent-child node relation with the data cluster in the question-answering subsystem.

Further:

the management subsystem is stored with a data structure of the question-answer subsystem, and the data structure comprises an indication of the relationship between the father node and the child node and a keyword for representing a data cluster.

In an embodiment of the system set forth in the first aspect or the second aspect of the present application, further:

a target data cluster satisfying a degree of association is determined in the first data set or the data structure based on the at least one first data cluster and/or the second request.

In a third aspect, an embodiment of the present application further provides a knowledge management system, further including an IT service subsystem, on the basis of the system embodiment set forth in the first aspect or the second aspect of the present application, to accomplish at least one of the following:

the IT service subsystem generates a first request based on user indication and/or service indication and sends the first request through the first interface;

the IT service subsystem obtains supplementary data based on user instructions and/or service instructions, generates a second request, and sends the second request through a third interface;

the IT service subsystem determines at least one first data cluster response to a user in the first data set;

and the IT service subsystem determines a target data cluster meeting the association degree in the first data set.

In a fourth aspect, embodiments of the present application further provide a knowledge management method, which is performed by the knowledge management system as described above; the method comprises the following steps:

generating a first data set in response to the first request; the first data set comprises a plurality of first data clusters;

determining a second data cluster; wherein the indication data of the second data cluster is contained in the content data of the target data cluster.

Further, the method further comprises the following steps: and determining a target data cluster meeting the association degree in the first data set or the data structure based on the at least one first data cluster and/or a second request, wherein the second request contains supplementary data. A second data set is obtained, the second data set comprising at least one first data cluster and/or a second request, the second request comprising supplementary data, the second data cluster being generated based on the at least one first data cluster and/or the supplementary data.

In a fifth aspect, embodiments of the present application also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a knowledge management method as described in any of the embodiments of the present application.

In a sixth aspect, embodiments of the present application further provide an electronic device, including a memory, a processor, and a computer program stored on the memory and executable by the processor, where the processor implements the knowledge management method according to any embodiment of the present application when executing the computer program.

According to the technical scheme, the question-answering subsystem accurately matches the request data with the existing data, and if the accurate matching fails, the data cluster for replying to the user interface is determined after the first data set related to the request data is fed back; sending the request data to the management subsystem; determining a target data cluster for the parent node; the management subsystem receives the request data and at least one part of the first data set, and performs data splicing on the request data and at least one part of the first data set according to a special data format of the question-answering subsystem to obtain a second data cluster; and the management subsystem sends the second data cluster to the question-answer subsystem, instructs the question-answer subsystem to create a sub-node under the node of the target data cluster, and stores the second data cluster.

The above-mentioned at least one technical scheme that this application embodiment adopted can reach following beneficial effect:

according to the scheme, the system can perform data analysis and data arrangement operation according to a new data request of the IT service subsystem, generate new knowledge points under the condition that the question-answering subsystem does not have precisely matched knowledge point data, and synchronize to the question-answering subsystem so as to provide guarantee for the ductility of the data of the question-answering subsystem. Meanwhile, the IT service subsystem and the question-answer subsystem ensure the accuracy of the data because the data are synchronously increased and matched accurately.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:

FIG. 1 is a schematic diagram of a knowledge management system according to an embodiment of the present application;

FIG. 2 is a flow chart of a knowledge management method according to a second embodiment of the present disclosure;

FIG. 3 is a flow chart of a knowledge management method according to a third embodiment of the present application;

fig. 4 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present application.

Detailed Description

For the purposes, technical solutions and advantages of the present application, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.

The following describes in detail the technical solutions provided by the embodiments of the present application with reference to the accompanying drawings.

Example 1

Fig. 1 is a schematic structural diagram of a knowledge management system according to an embodiment of the present application, where the embodiment is applicable to a case of automatically updating data in a question-answering subsystem, and the system may execute the knowledge management method according to the embodiment of the present application, and the system may be implemented by software and/or hardware, and may be integrated into an electronic device for knowledge management.

As shown in fig. 1, the system includes a question and answer subsystem 102;

the question-answering subsystem 102 includes at least one data cluster including indicating data and content data; if the content data of one data cluster contains the indication data of the other data cluster, the data structure relationship of the father node and the child node is formed; the indicating data may be, for example, an address pointer or a name. The question-answering subsystem 102 outputs a first data set to a first interface in response to a first request of the first interface; the first data set comprises a plurality of first data clusters;

the question-answering subsystem 102 receives a second data cluster through a second interface;

Preferably, a target data cluster satisfying the association degree is determined among the data clusters based on at least a part of the first data set and/or the second request. In one embodiment of the present application, preferably, the target data cluster is updated such that the indication data of the second data cluster is included in the content data of the target data cluster.

In one embodiment of the application, the management subsystem receives a second data set through a third interface, wherein the second data set comprises at least one first data cluster and/or a second request, the second request comprises supplementary data, and the second data cluster is generated based on the at least one first data cluster and/or the supplementary data. The second request is used for indicating the generation of new data clusters (second data cluster and/or third data cluster)

IT should be noted that, the management subsystem 103 may be a separate system, or may be a module with a management function, where the module may be set independently, or may be set by attaching to the IT service subsystem 101 and the question and answer subsystem 102. For example, in a system embodiment of the first aspect of the present application, the functionality of the management subsystem may be used to define the question-answering subsystem, that is, the management subsystem may be part of the question-answering subsystem.

Based on the above technical solutions, optionally, the system further includes an IT service subsystem, to accomplish at least one of the following:

the IT service subsystem determines at least one first data cluster directly serving as an answer in the first data set and responds the answer to a user;

Wherein the user indication and the service indication may be two interfaces as IT service subsystem. For example, the user indication interface is configured to receive question data from a user and to obtain a first request based on the question data. The service indication interface is used for receiving a solution provided by the user and used for generating a second request by taking the solution as supplementary data. Preferably, all or at least a portion of the data of the first request may also be included in the second request.

In an aspect of the system embodiment of the second aspect or the third aspect of the present application, as an added subsystem, the management subsystem 103 may also be connected to the IT service subsystem 101 and the question-answering subsystem 102, respectively.

On the basis of the technical schemes, optionally, the management subsystem stores a data structure of the question-answering subsystem, wherein the data structure comprises keywords representing data clusters and indications of the parent-child node relationship.

As a more specific implementation manner, namely, a system embodiment of the third aspect of the present application, the system includes: an IT service subsystem 101, a question and answer subsystem 102, and a management subsystem 103; the question-answering subsystem is connected with the IT service subsystem through a first interface; the question-answering subsystem is connected with the management subsystem through a second interface; the IT service subsystem is connected with the management subsystem through a third interface. Wherein the functions operated include:

the management subsystem generates a first data set in response to the first request. For example, the IT service subsystem generates a first request based on a user indication and issues the first request through the first interface. The IT service subsystem 101 issues a first request to the question and answer subsystem 102, containing request data; the question and answer subsystem 102 performs accurate matching on the request data and the existing data, and if the accurate matching fails, feeds back a first data cluster related to the request data; the associated first data cluster may be plural and feedback may be provided in the form of a first data set. On the basis of the above technical solutions, optionally, the question-answering subsystem determines, according to the keywords in the first request, a plurality of first data clusters with semantic similarity greater than a set threshold value, and forms the first data set.

The IT service subsystem responds to the user indication. The IT service subsystem 101 for determining whether the first data set has at least one first data cluster available for answer; the IT service subsystem determines at least one first data cluster response to a user in the first data set.

And generating a new data cluster by the response of the management subsystem to the IT service subsystem. If the first data set has at least one first data cluster for answer, generating a second data set, wherein the second data set comprises the at least one first data cluster and is sent to the management subsystem 103; preferably, the second data set further comprises a second request, and the second request comprises supplementary data. The management subsystem 103 receives the at least one first data cluster, and performs data splicing on the at least one data according to a data format adapted to the question-answering subsystem 102, or performs data splicing on the second requested data and the at least one data to obtain a second data cluster.

And determining a target data cluster. The IT service subsystem determines a target data cluster meeting the association degree in the first data set; or the IT service subsystem determines a target data cluster meeting the association degree in the at least one first data cluster. Further, it is determined that the content data of the target data cluster contains the indication data of the second data cluster. For example, the content data of the target data cluster already contains the name data of the second data cluster. For another example, when the content data of the target data cluster does not include the indication data of the second data cluster, the content data of the target data cluster is updated, and the indication data of the second data cluster is added. The management subsystem 103 sends the second data cluster to the question-answer subsystem 102, instructs the question-answer subsystem 102 to create a sub-node under the node of the target data cluster, and stores the second data cluster. For example, the storage address of the child node is identified by the indicating data.

The subsystem functions in the above-described embodiments are further illustrated below.

For example, a first request issued by the IT service subsystem 101 to the question and answer subsystem 102 contains request data; wherein, the request data can be a repair worksheet. For example, a person or engineer may be used to record the problem descriptions and screenshots, etc. in the repair worksheets. Accordingly, question and answer subsystem 102 may store a description of the question and a solution to the question, which may also include images, text, and even audio-visual, etc., without limitation. In the form, the ITSM subsystem (IT service subsystem) receives a description of the problem requirement and then collates the description into a graphic data set containing information such as title, keywords, text, pictures and remarks.

For another example, question and answer subsystem 102, which is collectively referred to as Faq Retrieval And Clustering Technique (FRACT), comprises at least two subsystems: a query log clustering system and a cluster-based retrieval system. The clustering system periodically collects and refines the user's query logs, then takes each FAQ as an independent category, and classifies the query logs into the respective FAQ categories by vector similarity measurement in semantic space. Based on the classification, the query log clustering system clusters the query logs and calculates a centroid of each query log cluster. When a user inputs a query, a cluster-based retrieval system calculates the similarity between the query and the FAQ through the query log clusters, and based on the calculated similarity, the retrieval system ranks the relevant FAQ and returns a list. When indexing, the system effectively clusters user query logs by utilizing a classification technology through potential semantic analysis; during retrieval, the system utilizes the query log cluster to enable FAQ query to be smoother. The system is applied to practice to test, and through different experiments, the system can reduce the problem of vocabulary disputes in short text retrieval, and the system performance is superior to that of other traditional information retrieval systems in the aspect of FAQ retrieval, and in addition, the system is more practical and reliable than the prior FAQ retrieval system because only a data-driven method is adopted without a high-level knowledge source. For example, libraries sort and store questions and answers to questions that are frequently asked or common to readers based on long-term service practices and reader surveys. And establishing a question and answer system so as to facilitate the inquiry of the user.

It should be noted that, the question and answer subsystem 102 performs accurate matching on the request data and the existing data, and if the accurate matching fails, feeds back a first data cluster related to the request data; for example, after the request data is received by the question and answer subsystem 102, knowledge acquisition may be performed in the existing data based on information such as keywords, titles, etc., in an attempt to match knowledge points exactly. If the question and answer subsystem cannot be matched accurately, similar matching inquiry is carried out according to the similarity, a first data set formed by a plurality of first data clusters is generated, and the first data set is fed back to the ITSM subsystem.

The first data cluster related to the request data may be arranged according to the similarity, and data with the similarity higher than a set threshold is taken as the first data cluster. For example, the first data cluster with the similarity higher than 40% related to the request data is returned to the ITSM subsystem in the form of a data set.

Here, the IT service subsystem 101 may be provided with a predetermined verification rule identifying a first data cluster in the first data set, determining whether there is at least one first data that may be fed back to the user as a solution. The validation rule here may be based on a comparison and analysis of the degree of association of each first data cluster with the requested data and the level of the resulting effect, or at least one first data cluster for feeding back the user may be determined in the first data set according to the service indication.

It will be appreciated that the data format of the question and answer subsystem 102 may be provided to the management subsystem 103 in advance. For example, the management algorithm of the data format of the question-answering subsystem 102 is synchronized into the management subsystem 103. In this embodiment, the management subsystem 103 performs data sorting and adding to form a new data stream, where the formed new data stream includes information such as a title, a keyword, a text, a picture, and a remark.

As another possible solution, the IT service subsystem 101 may perform data sorting and adding, and for this purpose, IT is also possible that the related functions of the solution are set to be executed by the IT service subsystem 101 or by the management subsystem 103.

In this scenario, the management subsystem 103 may send the second data cluster to the question-answering subsystem 102 if the second data cluster is obtained. It may be appreciated that, during the sending process, the question-answering subsystem 102 may be informed of the new location of the second data cluster, for example, the second data cluster is used as a new child node of the target data, and the question-answering subsystem 102 is instructed to create a child node under the node of the target data, and store the second data cluster.

In this scenario, the question-answering subsystem 102 may store the database of the tree structure formed by the data in the external storage, and then, for the second data cluster, may be added as a new knowledge point to the database.

On the basis of the above embodiment, optionally, the management subsystem 103 is further configured to:

acquiring node position information of the target data cluster in the question-answering subsystem 102;

after obtaining a second data cluster, determining node position information of the second data cluster according to the node position information of the target data cluster;

transmitting node location information of the second data cluster to the question-answering subsystem 102;

the question and answer subsystem 102 is configured to create a child node under a node of the target data based on node location information of the second data cluster, and store the second data cluster.

Wherein, after the management subsystem 103 obtains the node position information of the target data in the question-answer subsystem 102, the second data cluster may be used as a child node of the target data. The node information of the target data is, for example: 10-45, i.e., the 45 th child node of the 10 th node, the node location information of the second data cluster may be: 10-45-08, i.e. the original target data has 7 child nodes, a new child node is created for the second data cluster, i.e. the 8 th child node of the second data cluster bit target data.

The question-answering subsystem 102, after receiving the second data cluster, may create a child node under the node of the target data based on the child node location information of the second data cluster, and store the second data cluster.

According to the scheme, the relation between the second data cluster and the target data can be constructed through the management subsystem, and the relation is fed back to the question-answering subsystem, so that the position information for storing the second data cluster can be provided for the question-answering subsystem, and the effect of automatically providing the nodes for the question-answering subsystem with data is achieved. Because need not the manual entry, so can reduce the human cost of manual entry, can also improve the node efficiency of data simultaneously, there is not the problem of hysteresis.

On the basis of the above technical solution, optionally, the management subsystem 103 is specifically configured to:

after obtaining a second data cluster, adding a marking field to the second data cluster, wherein the marking field is used for marking the target data as basic data (father node) of the second data cluster;

the question and answer subsystem 102 is configured to determine node location information of the second data cluster based on the tag field, create a child node under a node of the target data, and store the second data cluster.

Wherein a marking field may be added to the second data cluster, which marking field may be used to mark the location information of the second data cluster. For example, the second data cluster is marked as being attached to the target data cluster.

The question-answering subsystem 102 can create a child node of the target data cluster based on the child node location information indicated by the tag field after reading the information of the tag field.

According to the method and the device, through the setting of the mark field, after the mark field is read by the question-answering subsystem, the node creation position of the second data cluster is determined based on the content of the mark field, so that the hysteresis problem caused by manually inputting the nodes is avoided.

In this embodiment, optionally, the management subsystem 103 is further configured to:

reading node position information of the target data cluster in the question-answering subsystem 102 by receiving the target data cluster sent by the IT service subsystem 101;

or,

and sending a node position information acquisition instruction of the target data cluster to the question-answering subsystem 102 so as to receive the node position information of the target data cluster fed back by the question-answering subsystem 102.

In the solution of the foregoing embodiment of the present application, the management subsystem 103 may acquire the location information of the target data cluster, which is attached with the location information of the target data cluster when the target data cluster is received from the IT service subsystem 101, or may determine the location information of the target data cluster based on feedback from the question-answering subsystem by sending an acquisition request to the question-answering subsystem.

As another possibility, the management subsystem 103 may have access to externally stored data of the questioning and answering subsystem 103 to determine the location information of the target data cluster.

The embodiment is arranged in such a way, so that the management subsystem can conveniently create the position information of the second data cluster, the interaction efficiency between the subsystems is improved, and the purpose of automatic input is realized.

In a possible embodiment, optionally, the management subsystem 103 is specifically configured to: receiving the second request and the at least one first data cluster, and performing data splicing, cutting and/or adding on the at least one first data cluster based on the request data to obtain a second data cluster; wherein the second data cluster comprises: at least one of a title, a keyword, a text, a picture, and a remark; and at least one of the title, the keyword, the text, the picture and the remarks accords with a set data format. Here, according to the received New data stream, the management subsystem 103 may perform operations such as keyword splitting, automatic semantic analysis, data sorting, and the like, to generate a data stream suitable for the question-answering subsystem to store, F-New (assuming that the basic data thereof, i.e., the target data cluster, is F). The F-New data is then passed to the question and answer subsystem, which stores it in an external store and adds it as a New knowledge point to the database.

The scheme is set in such a way that after the data are collated, a data stream suitable for the question-answering subsystem is generated, so that the question-answering subsystem can conveniently receive and input.

According to the scheme, an additionally-added management subsystem is adopted to conduct data analysis and data arrangement operation according to new data requests of the IT service subsystem, new knowledge points are generated under the condition that the question-answering subsystem does not have precisely matched data, and the knowledge points are synchronized to the question-answering subsystem, so that the ductility of the data of the question-answering subsystem is guaranteed. Meanwhile, the IT service subsystem and the question-answer subsystem are synchronously increased and accurately matched with each other, so that the accuracy of the data is ensured.

In another possible embodiment, in particular, the IT service subsystem 101 determines, based on the first data set, whether there is a first data cluster available for answer; if no data is available, sending the request data and/or a solution made by the staff based on the request data as supplementary data to the management subsystem 103;

the management subsystem 103 receives a second request, where the second request includes the supplementary data, and performs data splicing on the request data and/or the solution according to a data format adapted to the question-answering subsystem 102, so as to obtain a second data cluster; in this embodiment, for example, the management subsystem is further configured to: receiving the data of the second request, and performing data splicing, cutting and/or adding on the data of the second request to obtain a newly expanded second data cluster or third data cluster; wherein the second data cluster or the third data cluster comprises: at least one of a title, a keyword, a text, a picture, and a remark; and at least one of the title, the keyword, the text, the picture and the remark accords with a data format.

IT can be understood that, in the case that the IT service subsystem cannot find the appropriate first data cluster for replying to the user indication, the IT service subsystem or the management subsystem performs data creation aiming at the problem requirement, and forms a new data stream, which includes information such as a title, a keyword, a text, a picture, a remark, and the like.

When the IT service subsystem performs data creation, a new data stream is transmitted to the management subsystem through a second request, a field is added in the second request, and the new data stream is marked as independent data without dependence. The method has the advantages that the data volume suitable for the question-answering subsystem can be generated, the question-answering subsystem can be used for storing the data in a classified mode, and the matching degree of the data and the question-answering subsystem is improved.

The management subsystem 103 sends the second data cluster or the third data cluster to the question-answering subsystem 102, instructs the question-answering subsystem 102 to create an extension node, and stores the second data cluster or the third data cluster.

The method has the advantages that after the IT service subsystem cannot obtain the available data cluster serving as the answer from the first data set, the question-answering subsystem is updated based on the second request data, and the transverse expansion of knowledge points is realized for the question-answering subsystem.

IT should be noted that, in the IT service subsystem, available data as an answer cannot be obtained from the question-answer subsystem, IT is still possible to determine a target data cluster satisfying the matching degree in the first data set. For example, applying semantic analysis techniques and adjusting a similarity threshold, the first requested data and the first data set can be compared, from which a target data cluster satisfying the degree of matching is determined.

IT should be further noted that the IT service subsystem may further compare the second requested data with the first data set, and determine a target data cluster that satisfies the matching degree. For example, when the first requested data and the first data set are compared according to a set threshold value, and a target data cluster satisfying the matching degree cannot be determined, the IT service subsystem compares the second requested data and the first data set, and determines a target data cluster satisfying the matching degree therefrom.

Optionally, the management subsystem or the question-answering subsystem may further determine, based on the at least one first data cluster and/or the second request, a target data cluster satisfying the association degree in the first data set, the second data set or the data structure, and generate a second data cluster based on the at least one first data cluster and/or the second request; the content data of the target data cluster comprises indication data of the second data cluster. In an alternative embodiment, the target data cluster is not provided to the management subsystem by the ITSM subsystem, and may be obtained by searching the management subsystem in the first data set or the second data set, or may be obtained by searching the management subsystem from the data structure, or may be obtained by searching the question-answering subsystem in the first data set, the second data set or the data structure.

In another embodiment of the present application, the management subsystem is further configured to, in a case that, based on the at least one first data cluster and/or the second request, the target data cluster that satisfies the association cannot be determined, generate, based on the second request, a third data cluster, and output the third data cluster to the second interface; and the third data cluster has no parent-child node relation with the data cluster in the question-answering subsystem.

after a third data cluster is obtained, adding a mark field to the third data cluster, wherein the mark field is used for marking the third data cluster as non-basic data;

the question and answer subsystem 102 is configured to determine node location information of the third data cluster based on the tag field, create a node, and store the third data cluster.

The management subsystem 103 performs operations such as keyword splitting, automatic semantic analysis, data sorting and the like according to the received New data stream, and generates a data stream suitable for the question-answering subsystem 102 to store, wherein X-New (X represents that no target data cluster can be used as a parent node). The management subsystem 103 passes the X-New data to the question and answer subsystem 102, which the question and answer subsystem 102 stores in external storage as a New addition to the database.

The management subsystem 103 creates a New classification node suitable for the question-answering system according to the keyword information of the X-New, and the New classification node is used as a New branch classification node because the X-New is independent and unattached. The management subsystem 103 transmits the classification node of the X-New and the location data to the question-answer subsystem 102, and the question-answer subsystem 102 stores the data into an external storage and the classification structure data of the question-answer subsystem 102.

The scheme is that the question-answering subsystem automatically adds a new classification node and a corresponding classification node through the management subsystem along with the new addition of the request data of the IT service subsystem. With the repeated operation of the process, the question-answering subsystem achieves the effect of automatic expansion.

In this scenario, the second request data may be sent to the knowledge management subsystem 103 without the target data cluster. The knowledge management subsystem 103 performs data stitching on the request data, and the sorting manner may refer to the manner in the foregoing embodiments, that is, the third data cluster may be obtained. And sends the third cluster of data to the question-answering subsystem 102. The question and answer subsystem 102 may store it as extended knowledge. For example, there are 104 classifications of the original question-answering subsystem 102, and the third data cluster can be stored as an entirely new classification, i.e., the number of stored third data cluster is 105.

The foregoing solutions are summaries and summaries of the technical solutions provided by the embodiments of the present application, and are associated with the foregoing technical details, so the functional effects are the same, and are not repeated herein.

Example two

Fig. 2 is a flow chart of a knowledge management method according to a second embodiment of the present application. As shown in fig. 2, the method includes:

s201, responding to a first request, and outputting a first data set; the first data set comprises a plurality of first data clusters;

s202, determining a second data cluster in response to a second request;

in particular, for example, a second data set is obtained, the second data set comprising at least one first data cluster and/or a second request, the second request comprising supplementary data, the second data cluster being generated based on the at least one first data cluster and/or the supplementary data.

In some embodiments of the present application, the at least one first data cluster is selected in the first data set by a service indication when the at least one first data cluster is included in the second data set.

When the second request is contained in the second data set, the second request contains supplementary data. In some embodiments of the present application, the supplemental data is obtained through an external interface, e.g., a manual response to a user indication is obtained through a service indication.

Further, in response to the user indication, the method further comprises the steps of:

s203, at least one first data cluster is determined in the first data set, and a response is output to a user interface.

Further, to obtain the location of the second data cluster in the data cluster, the method further comprises the following steps:

s204, determining a target data cluster in the first data set, or determining the target data cluster by searching the data structure;

the target data cluster is a data cluster satisfying a degree of association with the second data cluster, specifically, at least a portion of the second data cluster, for example, the first request, the supplemental data, or a combination of at least one of the first data cluster and the supplemental data.

The association degree may be a similarity threshold of natural semantic analysis set in advance, for example, by comparing at least a part of the second data cluster with the first data cluster, to obtain a target data cluster; for another example, to increase processing efficiency, a target data cluster is obtained by comparing at least a portion of the second data cluster with the data structure.

Wherein the indication data of the second data cluster is contained in the content data of the target data cluster. It can be understood that the target data cluster meeting the association degree is obtained by searching in the first data cluster or all data structures. The second data cluster is used as a child node of the target data cluster in a data structure, the content data of the target data cluster can contain the indication data of the second data cluster, and if the content data of the target data cluster does not contain the indication data of the second data cluster, the target data cluster is updated so that the content data of the target data cluster contains the indication data of the second data cluster.

S205, determining the position of a second data cluster in the data cluster according to the target data cluster, and taking the second data cluster as a child node of the target data cluster. Further, in the content data of the target data cluster, the indication data of the second data cluster is added.

Further, when the target data cluster cannot be obtained in S203 to S205, step S206 is provided:

s206, generating a third data cluster based on the second request, wherein the third data cluster has no parent-child relationship with the data clusters in the question-answering subsystem.

S207, determining a marking field of the second data cluster or the third data cluster, wherein the marking field is used for marking the node position information of the second data cluster or the third data cluster, and creating new added data based on the node position information represented by the marking field.

The knowledge management system provided by the embodiments has the corresponding functional units and beneficial effects. And will not be described in detail herein.

Example III

Fig. 3 is a flow chart of a knowledge management method according to a third embodiment of the present application. The embodiment of the application also provides a knowledge management method, and the embodiment is a preferred scheme provided on the basis of the embodiment.

A management subsystem for automatically analyzing and processing data is established between the ITSM subsystem and the question-answer subsystem. The management subsystem has the functions that when the ITSM subsystem generates image-text data information capable of solving the problem according to the problem requirement, the management subsystem can perform data analysis and data processing according to the image-text data information to form a standard data set and push the standard data set to the question-answer subsystem to enter the external memory. Meanwhile, data structure classification node information is created according to the keywords in the canonical data set, and a new data structure is generated by combining the existing data structure path analysis of the question-answering subsystem and pushing the new data structure to the question-answering subsystem to enter an external memory. The data acquisition and data structure modification of the question-answering subsystem realize the automatic completion function, and the expanded data model of the question-answering subsystem has more pertinence and ductility, can cope with the demand scenes with deeper and wider range in actual use, enhances the machine processing efficiency, and reduces the manual participation.

Specifically, the method comprises the following steps:

s310, sending a first request to a question-answer subsystem through an IT service subsystem, wherein the first request comprises request data;

for example, the ITSM subsystem receives a description of the need for a problem, collates it into a set of teletext data containing information such as title, key word, text, picture, remarks, etc. The ITSM subsystem sends the data set (via the first request) to the question-answering subsystem.

S320, the question and answer subsystem acquires knowledge according to the keywords and the title information to try to match accurately. The question and answer subsystem cannot match the exact knowledge points. For example, the question and answer subsystem performs keyword matching with existing data based on the keywords of the request data, and the keyword matching fails.

S330, if the keyword matching fails, feeding back a plurality of first data clusters related to the request data; the question and answer subsystem performs similar matching query according to the similarity, generates a data set (first data set) composed of a plurality of knowledge points, and returns the data set to the ITSM subsystem.

S340, the ITSM subsystem attempts to find available data in the returned data set. Assuming that a knowledge point F (i.e. at least one first data cluster) with higher similarity with the description of the problem is found as a basis for solving the problem, jumping to step S361; assuming that no information is found to be available, step S371 is skipped.

Determining, by the IT service subsystem, whether there is at least one first data available as an answer based on the first data cluster; if available data exists, the request data and the at least one first data are sent to the management subsystem; and if no data is available, acquiring the supplementary data and sending the supplementary data to the management subsystem.

S361, the ITSM subsystem performs data arrangement and addition based on the knowledge point F to form a new data stream (a second data set comprises at least one first data cluster and a second request, and the second request comprises supplementary data) comprising information such as a title, a keyword, a text, a picture, a remark and the like.

The ITSM subsystem transfers the newly formed data stream to the management subsystem, and adds a field to the newly formed data stream along with the data representing the knowledge point F, where the flag F is the basic data of the new data stream, i.e., the target data cluster having the knowledge point F as the parent node of the new knowledge point.

S363, receiving the second request data and the at least one first data cluster through the management subsystem, and performing data splicing on the second request data and the at least one first data cluster according to a special data format of the question-answering subsystem to obtain a second data cluster;

And the management subsystem performs operations such as keyword splitting, automatic semantic analysis, data arrangement and the like according to the received New data stream, and generates a data stream suitable for being stored by the question-answer subsystem, and F-New (namely a second data cluster). The management subsystem transmits the F-New data to the question-answer subsystem, and the question-answer subsystem stores the F-New data into an external storage and adds the F-New data into a database as a New knowledge point.

S364, the second data cluster is sent to the question-answer subsystem through the management subsystem, the question-answer subsystem is instructed to create a sub-node under the node of the target data cluster, and the second data cluster is stored.

The management subsystem creates a New classification node suitable for the question-answering system according to the F-New keyword information, and the New classification node is placed behind or below the classification node corresponding to F because the F knowledge point is the basis (namely the target data cluster determined in the first data set). I.e. the F-New knowledge point is a child knowledge point of the F knowledge point. The management subsystem transmits the F-New classification nodes and the position data to the question-answering system, and the question-answering system stores the data into an external storage to update the classification structure data.

S371, determining whether available knowledge point data capable of being used as an answer exists or not based on the first data cluster through the IT service subsystem; if the data cluster does not have the available knowledge point data cluster, the data of the second request is sent to the management subsystem;

The ITSM subsystem cannot find proper knowledge points as a basis, performs data creation aiming at the problem demands, and forms a temporary data stream (the second request contains supplementary data) containing information such as titles, keywords, texts, pictures, remarks and the like.

S372, determining whether a target data cluster which can be used as a father node exists or not based on the first data cluster by the IT service subsystem; if the ITSM subsystem does not have the target data cluster, a field is added when the ITSM subsystem transmits the newly formed data stream to the management subsystem, and the new data stream is marked as independent data without dependence.

S373, receiving the request data through the management subsystem, and performing data splicing on the supplementary data in the second request according to the special data format of the question-answer subsystem to obtain a third data cluster; for example, the management subsystem performs operations such as keyword splitting, automatic semantic analysis, data sorting, etc. according to the received New data stream, and generates a data stream suitable for being stored by the question-and-answer subsystem, and X-New (i.e., a third data cluster). The management subsystem transmits the X-New data to the question and answer subsystem, and the question and answer subsystem stores the data into an external storage and adds the data into a database as a New knowledge point.

And S374, sending the third data cluster to the question-answering subsystem through the management subsystem, indicating the question-answering subsystem to create an expansion node, and storing the third data cluster.

The management subsystem creates a New classification node suitable for the question-answer subsystem according to the keyword information of the X-New, and the New classification node is used as a brand New branch classification node because the X-New is independent and unattached. The management subsystem transmits the classification nodes and the position data of the X-New to the question-answer subsystem, and the question-answer subsystem stores the data into an external storage and the classification structure data of the question-answer subsystem.

Through the steps, the question-answering subsystem is added with the data of the ITSM subsystem, and a new knowledge point and a corresponding classification node are automatically added through the management subsystem. With the repeated operation of the process, the question-answering subsystem achieves the effect of automatic expansion.

According to the invention, new data of the ITSM subsystem can be added, data analysis and data arrangement operations are carried out through the management subsystem, new and corresponding classification nodes are generated in the question-answering subsystem, and the ductility of the data is ensured. The ITSM subsystem and the question-answer subsystem are also increased and matched accurately due to the synchronous increment of data, and the accuracy of the data is ensured.

Example IV

The present embodiments also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are for performing a knowledge management method comprising: steps S201 to S207 and steps S310 to S374.

The method can be realized by the knowledge management system provided by the embodiments, and has the corresponding functions and beneficial effects. And will not be described in detail herein. The storage medium is any of various types of memory electronics or storage electronics. The term "storage medium" is intended to include: mounting media such as CD-ROM, floppy disk or tape devices; computer system memory or random access memory such as DRAM, DDR RAM, SRAM, EDORAM, lanbas (Rambus) RAM, etc.; nonvolatile memory such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in a computer system in which the program is executed, or may be located in a different second computer system connected to the computer system through a network (such as the internet). The second computer system may provide program instructions to the computer for execution. The term "storage medium" may include two or more storage media that may reside in different locations (e.g., in different computer systems connected by a network). The storage medium may store program instructions (e.g., embodied as a computer program) executable by one or more processors.

Of course, the storage medium containing the computer executable instructions provided in the embodiments of the present application is not limited to the knowledge management operations described above, and may also perform the related operations in the knowledge management method provided in any embodiment of the present application.

Example five

The embodiment of the application provides electronic equipment. Fig. 4 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present application. The electronic device 400 shown in fig. 4 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present application.

As shown in fig. 4, the electronic device 400 includes a processor 420, a storage device 410, an input device 430, and an output device 440; the number of processors 420 in the electronic device may be one or more, one processor 420 being taken as an example in fig. 4; the processor 420, the storage device 410, the input device 430, and the output device 440 in the electronic device may be connected by a bus or other means, as exemplified by connection via a bus 450 in fig. 4.

The storage device 410 is a computer readable storage medium, and is aimed at storing a software program, a computer executable program, and a module unit, such as program instructions corresponding to the knowledge management method in the embodiment of the present application.

The storage device 410 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for functions; the storage data area may store data created according to the use of the terminal, etc. In addition, the storage 410 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some examples, storage device 410 may further include memory located remotely from processor 420, which may be connected via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The input device 430 may be used to receive input numeric, character information, or voice information, and to generate key signal inputs related to user settings and function control of the electronic device. The output device 440 may include an electronic device such as a display screen, a speaker, etc.

The knowledge management system, medium and equipment provided in the above embodiment can operate the knowledge management method provided in any embodiment of the application, and have the corresponding functional modules and beneficial effects of operating the method. Technical details not described in detail in the above embodiments may be found in the knowledge management method provided in any embodiment of the present application.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations 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 means 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 instruction means 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.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element. In the present application, at least one means 1 or more.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims

1. A knowledge management system, wherein the system comprises a question and answer subsystem;

the question-answering subsystem receives a second data cluster through a second interface; the second data cluster is generated based on at least one first data cluster and/or supplemental data;

the indication data of the second data cluster is contained in the content data of the target data cluster; the target data cluster is the data cluster which meets the association degree with the second data cluster; the association degree is a similarity threshold of natural semantic analysis, which is preset.

2. The knowledge management system of claim 1, further comprising a management subsystem:

the question-answering subsystem is connected with the management subsystem through the second interface;

the management subsystem receives a second data set through a third interface, wherein the second data set comprises the at least one first data cluster and/or a second request, and the second request comprises the supplementary data.

3. The knowledge management system of claim 1 or 2, wherein:

and determining a target data cluster meeting the association degree in the first data set or the data structure based on the at least one first data cluster and/or a second request, wherein the second request contains the supplementary data.

4. The knowledge management system of claim 1, further comprising an IT service subsystem to perform at least one of:

5. The knowledge management system of claim 2, wherein:

6. The knowledge management system of claim 2, wherein:

7. The knowledge management system of any one of claims 1-2, 4-6, wherein,

8. The knowledge management system of any one of claims 1-2, 4-6, wherein,

9. A knowledge management method, characterized by being executed by the system of any one of claims 1-8; the method comprises the following steps:

10. Method according to claim 9, characterized in that a target data cluster satisfying the association is determined in the first data set or the data structure based on the at least one first data cluster and/or a second request, which contains supplementary data.