CN112015899A

CN112015899A - Method and device for supplementing knowledge base, server and computer storage medium

Info

Publication number: CN112015899A
Application number: CN202010898738.XA
Authority: CN
Inventors: 申亚坤
Original assignee: Bank of China Ltd
Current assignee: Bank of China Ltd
Priority date: 2020-08-31
Filing date: 2020-08-31
Publication date: 2020-12-01
Anticipated expiration: 2040-08-31
Also published as: CN112015899B

Abstract

The application provides a method, a device, a server and a computer storage medium for supplementing a knowledge base, wherein the method comprises the steps of acquiring all unanswered questions received within a preset time period; unanswered questions including questions which are provided by the user and have no corresponding answers in the knowledge base and questions which are fed back by the knowledge base and have incorrect answers; performing clustering analysis on the unanswered questions to obtain the type of knowledge to be supplemented in the knowledge base; sending knowledge supplementing tasks corresponding to the types of the knowledge to be supplemented to a plurality of editing terminals, and receiving the supplementary knowledge fed back by each editing terminal in response to the knowledge supplementing tasks; writing the supplemental knowledge into the knowledge base. The scheme automatically determines the type of the knowledge needing to be supplemented by analyzing unanswered questions in a preset time period, and then obtains the supplementary knowledge through the editing terminal and writes the supplementary knowledge into the knowledge base. Therefore, the scheme can automatically adapt to the occurrence frequency of new knowledge, and timely supplements the new business knowledge to the knowledge base when the new business knowledge appears.

Description

Method and device for supplementing knowledge base, server and computer storage medium

Technical Field

The invention relates to the technical field of knowledge bases, in particular to a method and a device for supplementing a knowledge base, a server and a computer storage medium.

Background

The knowledge base system is a common system of a bank, business knowledge corresponding to various businesses of the bank is stored in the knowledge base, and a business worker can timely find the corresponding business knowledge from the knowledge base, so that the business is handled for a client according to the business knowledge.

Currently, the method of supplementing new service knowledge into the knowledge base is generally to supplement the new service knowledge periodically (for example, supplement every month). The appearance time of the new knowledge needing to be supplemented to the knowledge base is random, a large amount of new knowledge needing to be supplemented can appear in a short time, and the new knowledge can not appear in a long time.

Therefore, the scheme of periodically supplementing new knowledge according to a certain period cannot adapt to the characteristics of the new knowledge, and the phenomenon that a large amount of new knowledge appears in a short period and cannot be timely supplemented to the knowledge base often occurs, so that the use of the knowledge base by a user is influenced.

Disclosure of Invention

Based on the problems in the prior art, the present application provides a method, an apparatus, a server and a computer storage medium for supplementing a knowledge base, so as to provide a knowledge base supplementing scheme capable of timely supplementing new service knowledge.

The first aspect of the present application provides a method for supplementing a knowledge base, including:

acquiring all unanswered questions received within a preset time period; wherein the unanswered questions comprise questions which are provided by the user and have no corresponding answers in the knowledge base and questions which are fed back by the knowledge base and have incorrect answers;

performing cluster analysis on the unanswered questions to obtain the knowledge types to be supplemented of the knowledge base;

sending knowledge supplement tasks corresponding to the knowledge types to be supplemented to a plurality of editing terminals, and receiving supplementary knowledge fed back by each editing terminal in response to the knowledge supplement tasks;

writing the supplemental knowledge to the knowledge base.

Optionally, before writing the supplementary knowledge into the knowledge base, the method further includes:

and identifying repeated supplementary knowledge from the received multiple supplementary knowledge according to the similarity between every two supplementary knowledge, and deleting the repeated supplementary knowledge.

Optionally, the identifying repeated supplementary knowledge from the received multiple supplementary knowledge includes:

for every two supplementary knowledge items, calculating the similarity of the knowledge texts of the two supplementary knowledge items, the similarity of the knowledge labels and the weighted average value of the similarity of the attachments according to preset weights to obtain the total similarity of the two supplementary knowledge items;

and if the total similarity of the two supplementary knowledge items is greater than a preset similarity threshold, determining that one supplementary knowledge item in the two supplementary knowledge items is the repeated supplementary knowledge item corresponding to the other supplementary knowledge item.

Optionally, before sending the knowledge supplementing task corresponding to the type of knowledge to be supplemented to the plurality of editing terminals, the method further includes:

and screening a plurality of users with the working contents associated with the to-be-supplemented knowledge types as candidate users, and determining the working terminal of each candidate user as an editing terminal.

A second aspect of the present application provides a device for supplementing a knowledge base, comprising:

the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring all unanswered questions received within a preset time period; wherein the unanswered questions comprise questions which are provided by the user and have no corresponding answers in the knowledge base and questions which are fed back by the knowledge base and have incorrect answers;

the analysis unit is used for carrying out clustering analysis on the unanswered questions to obtain the knowledge type to be supplemented of the knowledge base;

the communication unit is used for sending the knowledge supplementing tasks corresponding to the knowledge types to be supplemented to a plurality of editing terminals and receiving the supplementary knowledge fed back by each editing terminal in response to the knowledge supplementing tasks;

and the writing unit is used for writing the supplementary knowledge into the knowledge base.

Optionally, the supplementary device further comprises:

and the deleting unit is used for identifying repeated supplementary knowledge from the received multiple supplementary knowledge according to the similarity between every two supplementary knowledge items and deleting the repeated supplementary knowledge.

Optionally, when the deleting unit identifies repeated supplementary knowledge from the received multiple supplementary knowledge, the deleting unit is specifically configured to:

Optionally, the supplementary device further comprises:

and the screening unit is used for screening a plurality of users with the working contents related to the knowledge types to be supplemented as candidate users and determining the working terminal of each candidate user as an editing terminal.

A third aspect of the present application provides a server comprising a memory and a processor;

wherein the memory is for storing a computer program;

the processor is adapted to execute the computer program, in particular to implement a method of supplementing a knowledge base as provided in any of the first aspects of the present application.

A fourth aspect of the present application provides a computer storage medium for storing a computer program which, when executed, is particularly adapted to carry out a method of supplementing a knowledge base as provided in any of the first aspects of the present application.

Drawings

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

Fig. 1 is a schematic diagram of an architecture of a knowledge base according to an embodiment of the present application;

FIG. 2 is a flow chart of a method for supplementing a knowledge base according to an embodiment of the present application;

fig. 3 is a flowchart of a method for determining an editing terminal according to an embodiment of the present application;

FIG. 4 is a schematic structural diagram of a device for supplementing a knowledge base according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of a server according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

To facilitate understanding of the method for supplementing the knowledge base provided in the embodiments of the present application, the framework of the knowledge base is briefly described first. As shown in fig. 1, the knowledge base system is mainly operated on a server or a server cluster composed of a plurality of servers, and any one of the work terminals in the bank can send a question to the knowledge base through the network, and then obtain the corresponding business knowledge fed back by the knowledge base as an answer to the question.

An embodiment of the present application provides a method for supplementing a knowledge base, please refer to fig. 2, where the method may include the following steps:

the implementation subject of the method for supplementing the knowledge base provided by any embodiment of the application can be regarded as a server for running the knowledge base.

S201, all unanswered questions received in a preset time period are acquired.

Wherein the unanswered questions comprise questions which are provided by the user and have no corresponding answers in the knowledge base, and questions which are fed back by the knowledge base and have incorrect answers.

As described in the background, the knowledge base is a common system in banks today. One use mode of the knowledge base is that when a bank clerk transacts business, any question needing to be answered can be input at a business terminal, the business terminal sends the question to a server for operating the knowledge base, the server matches the question with a large amount of business knowledge stored in the knowledge base, one or more business knowledge successfully matched with the question provided by a user is finally found from the knowledge base, and the business knowledge is fed back to the business terminal as the answer of the question and then displayed by the business terminal.

That is, the knowledge base may feed back the knowledge stored in itself to the corresponding terminal as an answer to a question posed by the user.

Specifically, the knowledge base may establish and store a corresponding question record for each question received by itself, where the question record may include a timestamp indicating the time when the user raised the question, and a question text entered by the user, such as "what materials need to be provided for handling XX? For example, for the text of the question, the business knowledge "XX business-business handling material" may be extracted from the knowledge base, and the business knowledge is fed back to the terminal device as an answer to the question, where if a matched business knowledge is not stored in a certain question knowledge base, and the knowledge base fails to feed back the corresponding answer, the record of the answer fed back in the corresponding question record is "answer missing". Finally, the question record may further include user evaluation of the answers fed back by the user to the knowledge base, and the user evaluation may specifically include a good evaluation, a bad evaluation, and an incorrect answer.

Based on the question records stored in the knowledge base, the specific implementation procedure of step S201 may be to access a database for storing the question records, then retrieve the question records with each corresponding timestamp within the preset time period from the database, for example, if the preset time period may be the last 24 hours, then retrieve the question records with each corresponding timestamp within the last 24 hours from the database, then select all the question records with "answer missing" as the answer part from all the retrieved question records within the last 24 hours, and select all the question records with incorrect answers as the evaluation part of the user, where the question texts recorded by the selected question records are all the unanswered questions received within the preset time period in step S201.

S202, carrying out clustering analysis on the unanswered questions to obtain the type of the knowledge to be supplemented in the knowledge base.

As previously mentioned, the unanswered question may be represented as a user-entered text of a question, such as "what materials need to be provided for working with XX services? ". Therefore, in step S202, clustering analysis is performed on the unanswered question, which is substantially performed on the plurality of question texts acquired in step S201.

An alternative cluster analysis method is to first convert each question text into a corresponding question text vector. This step may be implemented using a pre-constructed word vector model.

The word vector model (word2vec) is an existing mathematical model, and after being trained by using a large amount of linguistic data, each vocabulary can be converted into a corresponding word vector by the word vector model. Specifically, in this embodiment, a word vector model may be used to convert all words and phrases contained in a question text into corresponding word vectors, then the word vectors of all words and phrases contained in the question text are accumulated, and the accumulated vectors are determined as the question text vectors of the question text.

After the question texts of the unanswered questions are converted into corresponding question text vectors, clustering the question texts according to the cosine similarity between every two question text vectors, and for every two question texts, if the cosine similarity of the question text vectors of the two question texts is smaller than or equal to a preset threshold, determining that the unanswered questions corresponding to the two question texts belong to the same knowledge type to be supplemented, and otherwise, if the cosine similarity of the question text vectors of the two question texts is larger than the preset threshold, determining that the unanswered questions corresponding to the two question texts do not belong to the same knowledge type to be supplemented.

After clustering is completed, counting the occurrence frequency of each vocabulary in the question texts of all unanswered questions of the same knowledge type to be supplemented, and then sequentially selecting the first N (generally, N can be set to be 3 or 4) vocabularies as the keywords of the knowledge type to be supplemented according to the occurrence frequency from high to low, thereby determining the knowledge type to be supplemented.

For example, in the question texts of a plurality of unanswered questions clustered into the same to-be-supplemented knowledge type, the first three words with the highest occurrence frequency are respectively 'XX business', 'material', 'payment', and then the determined to-be-supplemented knowledge type is the material handling of the XX business and the payment rule of the XX business.

S203, sending knowledge supplementing tasks corresponding to the types of the knowledge to be supplemented to the plurality of editing terminals, and receiving the supplemented knowledge fed back by each editing terminal in response to the knowledge supplementing tasks.

Optionally, the editing terminal may include a work terminal of each employee of the bank, and may also include a work terminal of a plurality of candidate employees selected according to a certain screening manner.

For a type of knowledge to be supplemented, the corresponding knowledge supplementation task may include the following information:

firstly, the knowledge supplementing task can comprise a corresponding keyword of a knowledge type to be supplemented; secondly, the knowledge supplementing task can comprise question texts of a plurality of unanswered questions belonging to the corresponding knowledge type to be supplemented; thirdly, when the unanswered question is a question that the knowledge base feeds back the corresponding answer but the fed-back answer is incorrect, the knowledge supplementing task can also comprise an incorrect answer fed back by the knowledge base; and fourthly, the knowledge supplementing task can also comprise the direction which needs to be supplemented by each editing terminal, for example, the knowledge supplementing task sent to the editing terminal of the service staff can specify that detailed description and description as much as possible need to be provided for the type of the knowledge to be supplemented, and the knowledge supplementing task sent to the editing terminal of the administrator can require to provide frame information of the corresponding type of the knowledge to be supplemented, for example, a corresponding directory.

And S204, carrying out data cleaning on the received multiple items of supplementary knowledge, and writing the cleaned supplementary knowledge into a knowledge base.

It should be noted that the operation of performing data cleansing on the received multiple items of supplemental knowledge in step S204 is an optional operation in the embodiment of the present application, that is, in step S204, the received multiple items of supplemental knowledge may not be subjected to data cleansing, but the received supplemental knowledge may be directly written into the knowledge base.

For each item of received supplementary knowledge, if the item of supplementary knowledge corresponds to a question that is proposed by the user and has no corresponding answer stored in the knowledge base in the unanswered questions, then the item of supplementary knowledge may be directly written into the knowledge base when step S204 is executed.

If the question corresponding to the supplementary knowledge is a question that is proposed by the user but the answer fed back by the knowledge base is incorrect in the unanswered questions, the previous answer is deleted from the knowledge base and then the supplementary knowledge is written into the knowledge base in step S204.

The data cleaning is performed on a plurality of items of supplementary knowledge, and the data cleaning specifically comprises the following steps:

in the first aspect, duplicate supplementary knowledge may be identified from the received plurality of supplementary knowledge and deleted according to a similarity between every two supplementary knowledge.

In a second aspect, for each item of supplemental knowledge, it may be detected whether the item of supplemental knowledge is associated with a corresponding type of knowledge to be supplemented, and if the item of supplemental knowledge is not associated with the corresponding type of knowledge to be supplemented, the item of supplemental knowledge may be deleted.

The method for deleting repeated supplementary knowledge from the multiple supplementary knowledge comprises the following steps:

and aiming at every two supplementary knowledge items, calculating the similarity of the knowledge texts of the two supplementary knowledge items according to a preset weight, and obtaining the total similarity of the two supplementary knowledge items by the weighted average of the similarity of the knowledge labels and the similarity of the attachments.

And if the total similarity of the two supplementary knowledge items is greater than a preset similarity threshold, determining that one supplementary knowledge item in the two supplementary knowledge items is the repeated supplementary knowledge corresponding to the other supplementary knowledge item.

For each item of supplementary knowledge, the staff providing the item of supplementary knowledge can upload the related documents together in the form of attachments of the item of supplementary knowledge when uploading the item of supplementary knowledge.

The similarity of the knowledge text may be:

and for the two supplementary knowledge, counting all the characters contained in the knowledge texts of the two supplementary knowledge, counting the number of the same characters in the two supplementary knowledge, dividing the number by the number of the same characters in the two supplementary knowledge, and taking the obtained ratio as the similarity of the knowledge texts of the two supplementary knowledge.

In addition, each word of the knowledge text of each item of the supplementary knowledge can be converted into a corresponding word vector by using the word vector model, then all word vectors of the knowledge text of one item of the supplementary knowledge are accumulated to obtain a text vector of the knowledge text of the item of the supplementary knowledge, finally, the similarity of the text vectors of the knowledge texts of the two items of the supplementary knowledge is calculated aiming at every two items of the supplementary knowledge, and the calculation result is used as the similarity of the knowledge texts of the two items of the supplementary knowledge.

The calculation method of the similarity of the knowledge tags and the similarity of the attachments is basically consistent with the calculation method of the knowledge text, and the detailed description is omitted here.

For the second aspect of the foregoing data cleansing, the specific implementation procedure may be:

for each item of supplementary knowledge, searching corresponding keywords of the type of the supplementary knowledge to be supplemented in the title, the knowledge text and the attachment of the item of supplementary knowledge, and searching synonyms having the same semantics with the keywords of the type of the supplementary knowledge to be supplemented, if any keyword in a plurality of keywords corresponding to the type of the supplementary knowledge to be supplemented does not appear in the item of supplementary knowledge, and the synonyms of the keywords which do not appear in the item of supplementary knowledge do not exist, then judging that the item of supplementary knowledge is not business knowledge corresponding to the type of the supplementary knowledge, and at the moment, directly deleting the item of supplementary knowledge.

Optionally, if one supplementary knowledge is not the service knowledge corresponding to the type of the knowledge to be supplemented, after the supplementary knowledge is deleted, a prompt message may be sent to the editing terminal that uploads the supplementary knowledge, so as to prompt the relevant person to re-edit and upload the supplementary knowledge.

By deleting repeated supplementary knowledge in multiple supplementary knowledge, the scheme can avoid storing redundant business knowledge in the knowledge base and make full use of the storage space of the knowledge base. By deleting the received supplementary knowledge which does not belong to the corresponding type of the knowledge to be supplemented, the wrong business knowledge can be prevented from being stored in the knowledge base, so that wrong answers can be prevented from occurring when the knowledge base is subsequently used for answering questions.

Optionally, when data cleaning is performed on multiple items of complementary knowledge, in addition to the above two steps, operations such as translating each item of complementary knowledge, deleting wrongly written or mispronounced characters, and the like may be performed.

Optionally, after the data cleaning is completed and before the supplementary knowledge is written into the knowledge base, the supplementary knowledge after the data cleaning may be sent to a corresponding auditing terminal, and the staff of the auditing terminal manually audits the supplementary knowledge after the data cleaning. And for any supplementary knowledge, if the supplementary knowledge does not pass the manual review, deleting the supplementary knowledge and not writing the supplementary knowledge into the knowledge base, and if the supplementary knowledge passes the manual review, writing the supplementary knowledge into the database.

The application provides a method for supplementing a knowledge base, which comprises the steps of acquiring all unanswered questions received in a preset time period; unanswered questions including questions which are provided by the user and have no corresponding answers in the knowledge base and questions which are fed back by the knowledge base and have incorrect answers; performing clustering analysis on the unanswered questions to obtain the type of knowledge to be supplemented in the knowledge base; sending knowledge supplementing tasks corresponding to the types of the knowledge to be supplemented to a plurality of editing terminals, and receiving the supplementary knowledge fed back by each editing terminal in response to the knowledge supplementing tasks; writing the supplemental knowledge into the knowledge base. The scheme automatically determines the type of the knowledge needing to be supplemented by analyzing unanswered questions in a preset time period, and then obtains the supplementary knowledge through the editing terminal and writes the supplementary knowledge into the knowledge base. Therefore, the scheme can automatically adapt to the occurrence frequency of new knowledge, and timely supplements the new business knowledge to the knowledge base when the new business knowledge appears.

The editing terminal may be a terminal device used by each employee of a bank for office work, or a terminal device of a user selected according to a to-be-supplemented knowledge type and associated with work content and the to-be-supplemented knowledge type, and specifically, an embodiment of the present application provides a method for determining an editing terminal, please refer to fig. 3, where the method includes:

s301, obtaining the work content of all users in a preset time period to obtain a work content set.

In this embodiment, the user is an employee who is used to refer to a bank, and may specifically include an operator who handles business for a client, and other technical support personnel, management personnel, and the like.

The work content of the user may include the work content of the user within a preset time period, and may include information such as documents edited by the user within the preset time period, business transaction records, and written mails.

S302, keywords of the knowledge type to be supplemented are searched in the working content set.

When there are multiple knowledge types to be supplemented, and each knowledge type to be supplemented corresponds to multiple keywords, step S302 refers to retrieving the keyword from the work content set for each keyword of each knowledge type to be supplemented.

S303, determining the user with the corresponding work content including the key words of the knowledge type to be supplemented as a candidate user, and determining the work terminal of the candidate user as an editing terminal.

Specifically, for each user, if one or more keywords of a certain to-be-supplemented knowledge type appear in the work content of the user within a preset time period, the user is determined as a candidate user corresponding to the to-be-supplemented knowledge type, and correspondingly, a work terminal of the candidate user is an editing terminal corresponding to the to-be-supplemented knowledge type.

If a user has a plurality of keywords of the knowledge types to be supplemented in the working content in the preset time period, the user is determined as a candidate user of the corresponding knowledge types to be supplemented.

After receiving the knowledge supplement task, any editing terminal can pop up an editing window of the knowledge supplement task in a message pop-up mode so as to prompt related personnel to supplement business knowledge. After the editing terminal pops up the editing window for a period of time, if the editing terminal does not receive a response, the editing terminal can send no-operation feedback information to the server to indicate that the corresponding candidate user does not use the editing terminal, and after the no-operation feedback information is received, the server can send a prompt short message to the mobile phone of the corresponding candidate user to prompt the candidate user to supplement related business knowledge as soon as possible.

Optionally, when the candidate user of any editing terminal edits the related service knowledge for the knowledge supplementing task, the server may send the service knowledge already edited by other editing terminals to the editing terminal, so that the corresponding candidate user supplements other service knowledge different from the already edited service knowledge.

Further optionally, if the unanswered questions corresponding to a certain type of knowledge to be supplemented include questions with incorrect answers fed back by multiple knowledge bases, the server may send the service knowledge to the terminal of each user who provides the question with the incorrect answer to the previous feedback after receiving the supplementary knowledge fed back for the certain type of knowledge to be supplemented, so as to check whether the supplementary knowledge received this time is correct.

In combination with the method for supplementing a knowledge base provided in any embodiment of the present application, an embodiment of the present application further provides an apparatus for supplementing a knowledge base, please refer to fig. 4, where the apparatus may include the following units:

an obtaining unit 401 is configured to obtain all unanswered questions received within a preset time period.

The analysis unit 402 is configured to perform cluster analysis on the unanswered questions to obtain the to-be-supplemented knowledge type of the knowledge base.

A communication unit 403, configured to send a knowledge supplementation task corresponding to a type of knowledge to be supplemented to a plurality of editing terminals, and receive supplementation knowledge fed back by each editing terminal in response to the knowledge supplementation task.

A writing unit 404, configured to write the supplementary knowledge into the knowledge base.

Optionally, the supplementary device further comprises:

and a deleting unit 405, configured to identify repeated supplementary knowledge from the received multiple supplementary knowledge according to a similarity between every two supplementary knowledge items, and delete the repeated supplementary knowledge.

When the deleting unit 405 identifies the repeated supplementary knowledge from the received multiple supplementary knowledge, the deleting unit is specifically configured to:

Optionally, the supplementary device further comprises:

the screening unit 406 is configured to screen out users with work contents associated with the to-be-supplemented knowledge types as candidate users, and determine a work terminal of each candidate user as an editing terminal.

The specific working principle of the device for supplementing a knowledge base provided in the embodiments of the present application may refer to corresponding steps in the method for supplementing a knowledge base provided in any embodiment of the present application, and details thereof are not described here.

The application provides a device for supplementing a knowledge base, which comprises an acquisition unit 401 for acquiring all unanswered questions received in a preset time period; unanswered questions including questions which are provided by the user and have no corresponding answers in the knowledge base and questions which are fed back by the knowledge base and have incorrect answers; the analysis unit 402 performs clustering analysis on the unanswered questions to obtain the type of knowledge to be supplemented in the knowledge base; the communication unit 403 sends knowledge supplementing tasks corresponding to the types of knowledge to be supplemented to the plurality of editing terminals, and receives the supplementary knowledge fed back by each editing terminal in response to the knowledge supplementing tasks; the writing unit 404 writes the supplementary knowledge into the knowledge base. The scheme automatically determines the type of the knowledge needing to be supplemented by analyzing unanswered questions in a preset time period, and then obtains the supplementary knowledge through the editing terminal and writes the supplementary knowledge into the knowledge base. Therefore, the scheme can automatically adapt to the occurrence frequency of new knowledge, and timely supplements the new business knowledge to the knowledge base when the new business knowledge appears.

Referring to fig. 5, the server may include a memory 501 and a processor 502.

The memory 501 is used for storing a computer program, among other things.

The processor 502 is configured to execute the above-mentioned computer program, and is specifically configured to implement the method for supplementing the knowledge base provided in any embodiment of the present application.

The embodiments of the present application further provide a computer storage medium for storing a computer program, and when the computer program is executed, the computer storage medium is specifically used for implementing the method for supplementing a knowledge base provided in any embodiment of the present application.

Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, 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 an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

It should be noted that the terms "first", "second", and the like in the present invention are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

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

Claims

1. A method of supplementing a knowledge base, comprising:

writing the supplemental knowledge to the knowledge base.

2. The supplemental method of claim 1, wherein prior to writing the supplemental knowledge to the knowledge base, further comprising:

3. The method of claim 2, wherein identifying the repeated supplemental knowledge from the received plurality of items of supplemental knowledge comprises:

4. The supplementing method according to claim 1, wherein before sending the knowledge supplementing task corresponding to the type of knowledge to be supplemented to the plurality of editing terminals, the method further comprises:

5. An apparatus for supplementing a knowledge base, comprising:

6. The supplemental device of claim 5, further comprising:

7. The supplement apparatus according to claim 6, wherein the deleting unit, when recognizing the repeated supplementary knowledge from the received plurality of items of supplementary knowledge, is configured to:

8. The supplemental device of claim 6, further comprising:

9. A server, comprising a memory and a processor;

wherein the memory is for storing a computer program;

the processor is adapted to execute the computer program, in particular to implement a method of supplementing the knowledge base according to any of claims 1 to 4.

10. A computer storage medium for storing a computer program, which, when executed, is particularly adapted to carry out a method of supplementing a knowledge base according to any one of claims 1 to 4.