CN113918689A - Optimization method and device of knowledge graph question-answering system - Google Patents
Optimization method and device of knowledge graph question-answering system Download PDFInfo
- Publication number
- CN113918689A CN113918689A CN202111094235.8A CN202111094235A CN113918689A CN 113918689 A CN113918689 A CN 113918689A CN 202111094235 A CN202111094235 A CN 202111094235A CN 113918689 A CN113918689 A CN 113918689A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- feedback
- answering system
- question
- graph question
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000004590 computer program Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 abstract description 8
- 238000001228 spectrum Methods 0.000 description 25
- 238000012544 monitoring process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides an optimization method and device of a knowledge graph question-answering system, wherein the optimization method comprises the following steps: acquiring a feedback log generated by a knowledge graph question-answering system; performing computer linguishing on the feedback log to obtain feedback characteristics; and optimizing the knowledge-graph question-answering system by using the feedback characteristics. According to the knowledge-graph question-answering system optimization method and system, the knowledge-graph question-answering system is optimized based on the feedback logs generated by the knowledge-graph question-answering system, the knowledge-graph question-answering system can be automatically and continuously optimized by utilizing the logs generated by the knowledge-graph question-answering system, maintenance personnel are not needed to monitor and optimize, and the optimization efficiency is improved while the accuracy of the knowledge-graph question-answering system is improved.
Description
Technical Field
The application relates to the technical field of system optimization, in particular to an optimization method and device of a knowledge-graph question-answering system.
Background
In the current information explosion era, the problems caused by information redundancy are well solved by automatic question answering, and the knowledge graph question answering (KBQA) can better utilize semantic associated information rich in graphs and can deeply understand the problems of users and give answers.
However, the KBQA technology has many disadvantages, and how to continuously perform iterative optimization on a KBQA system becomes a problem to be solved urgently.
Disclosure of Invention
In view of this, the embodiment of the present application provides an optimization method and an optimization device for a knowledge-graph question-answering system, so as to solve the problem in the prior art that the accuracy rate of identifying abnormal traffic is low.
In a first aspect, an embodiment of the present application provides an optimization method for a knowledge-graph question-answering system, where the method includes:
acquiring a feedback log generated by a knowledge graph question-answering system;
performing computer linguishing on the feedback log to obtain feedback characteristics;
and optimizing the knowledge-graph question-answering system by using the feedback characteristics.
In one possible embodiment, the feedback log includes user generated question and answer information using the knowledge-graph question and answer system and usage information fed back by the user based on the question and answer information.
In a possible implementation, the computer-speaking the feedback log to obtain the feedback feature includes:
and converting the text information in the feedback log into a machine language by using a preset rule to obtain the feedback characteristic.
In a possible embodiment, the optimizing the knowledge-graph question-answering system by using the feedback features includes:
clustering the feedback characteristics to obtain a cluster;
determining whether the closeness of the clustered cluster is greater than or equal to a first threshold and determining whether the number of samples in the clustered cluster is greater than or equal to a second threshold;
retraining the knowledge-graph question-answering system with the feedback features if the closeness is greater than or equal to the first threshold and/or the number of samples is greater than or equal to the second threshold.
In one possible embodiment, the optimization method further includes:
and sending the question-answer information corresponding to the cluster to a maintainer so that the maintainer can optimize the knowledge graph question-answer system.
In a second aspect, an embodiment of the present application further provides an optimization apparatus for a knowledge-graph question-answering system, where the optimization apparatus includes:
an acquisition module configured to acquire a feedback log generated by the knowledge-graph question-answering system;
the processing module is used for carrying out computer language conversion on the feedback log in a configuration mode to obtain feedback characteristics;
an optimization module configured to optimize the knowledge-graph question-answering system using the feedback features.
In a possible implementation, the processing module is specifically configured to:
and converting the text information in the feedback log into a machine language by using a preset rule to obtain the feedback characteristic.
In a possible implementation, the optimization module is specifically configured to:
clustering the feedback characteristics to obtain a cluster;
determining whether the closeness of the clustered cluster is greater than or equal to a first threshold and determining whether the number of samples in the clustered cluster is greater than or equal to a second threshold;
retraining the knowledge-graph question-answering system with the feedback features if the closeness is greater than or equal to the first threshold and/or the number of samples is greater than or equal to the second threshold.
In a third aspect, an embodiment of the present application further provides a storage medium, where the computer readable storage medium stores a computer program, and the computer program is executed by a processor to perform the following steps:
acquiring a feedback log generated by a knowledge graph question-answering system;
performing computer linguishing on the feedback log to obtain feedback characteristics;
and optimizing the knowledge-graph question-answering system by using the feedback characteristics.
In a fourth aspect, an embodiment of the present application further provides an electronic device, where the electronic device includes: a processor and a memory, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating over a bus when an electronic device is operating, the machine-readable instructions when executed by the processor performing the steps of:
acquiring a feedback log generated by a knowledge graph question-answering system;
performing computer linguishing on the feedback log to obtain feedback characteristics;
and optimizing the knowledge-graph question-answering system by using the feedback characteristics.
The knowledge-spectrum question-answering system is optimized based on the feedback logs generated by the knowledge-spectrum question-answering system, the knowledge-spectrum question-answering system can be automatically and continuously optimized by using the logs generated by the knowledge-spectrum question-answering system, the monitoring and optimization by maintenance personnel are not needed, and the optimization efficiency is improved while the accuracy of the knowledge-spectrum question-answering system is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.
FIG. 1 is a flow chart illustrating a method for optimizing a knowledge-graph question-answering system provided by the present application;
FIG. 2 is a flow chart illustrating the optimization of a knowledge-graph question-answering system using feedback features in the optimization method of the knowledge-graph question-answering system provided by the present application;
FIG. 3 is a schematic diagram of an optimization apparatus of a knowledge-graph question-answering system provided in the present application;
fig. 4 shows a schematic structural diagram of an electronic device provided in the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings of the embodiments of the present application. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the application without any inventive step, are within the scope of protection of the application.
Unless defined otherwise, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this application belongs. As used in this application, the terms "first," "second," and the like do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
Detailed descriptions of known functions and known components are omitted in the present application in order to keep the following description of the embodiments of the present application clear and concise.
As shown in fig. 1, which is a flowchart of an optimization method of a knowledge-graph question-answering system provided in the first aspect of the present application, the specific steps include S101-S103.
And S101, obtaining a feedback log generated by the knowledge-graph question-answering system.
In practical application, after a user uses the knowledge-graph question-answering system to perform question-answering operation, namely after the knowledge-graph question-answering system operates, a corresponding feedback log is generated, wherein the feedback log comprises question-answering information generated by the user using the knowledge-graph question-answering system, use information fed back by the user based on the question-answering information, and the like.
The question-answering information comprises a question of a user, the time for generating the question, an answer returned by the knowledge-graph question-answering system in response to the question and the like, and the use information comprises the satisfaction degree of the user on the answer returned by the knowledge-graph question-answering system in response to the question, the opinion on the answer and the like.
The execution main body of the optimization method in the embodiment of the application may be a processor of the electronic device, or may also be a server, and the processor or the server may both establish communication connection with the knowledge-graph question-answering system, so as to obtain the feedback log generated by the knowledge-graph question-answering system in a communication manner. Of course, other ways may also be used to obtain the feedback log generated by the knowledge-graph question-answering system, which is not specifically limited in this embodiment of the present application.
And S102, carrying out computer language transformation on the feedback log to obtain feedback characteristics.
Here, the feedback log generated by the knowledge-graph question-answering system includes a large amount of text information, and in order to enable a subsequent processor or server to better utilize the feedback log, the feedback log is subjected to computer language to obtain feedback characteristics, and the feedback characteristics are directly available to the processor or server, such as reading, analysis and the like.
Specifically, the text information in the feedback log is converted into the machine language by using preset rules such as embedding, lexical, syntactic and other multidimensional, so as to obtain the feedback characteristics, wherein the feedback characteristics can be directly recognized and executed by a computer represented by binary codes.
And S103, optimizing the knowledge-graph question-answering system by using the feedback characteristics.
After the feedback characteristics which can be directly utilized by the processor or the server are obtained, the knowledge-graph question-answering system is optimized by utilizing the feedback characteristics so as to improve the performance, namely the accuracy, of the knowledge-graph question-answering system.
Specifically, the way the knowledge-graph question-answering system is optimized by using feedback features is referred to the method flow chart shown in fig. 2, wherein the steps include S201-S203.
S201, clustering the feedback characteristics to obtain a cluster.
S202, whether the closeness of the cluster is larger than or equal to a first threshold value or not is determined, and whether the number of samples in the cluster is larger than or equal to a second threshold value or not is determined.
S203, in the case that the compactness is larger than or equal to a first threshold value and/or the number of samples is larger than or equal to a second threshold value, the knowledge-graph question-answering system is retrained by using the feedback features.
Here, the feedback feature is subjected to clustering processing to perform clustering processing according to a preset criterion, such as a low degree of satisfaction in use information, to obtain a cluster. The feedback features within the cluster all represent feedback logs with low satisfaction.
After the cluster is obtained, the closeness of the cluster is determined, wherein the closeness represents the degree of meeting the corresponding standard, and the number of samples in the cluster can be counted, and the number of samples is the number of feedback logs meeting the standard. And then, determining whether the compactness of the clustering cluster is greater than or equal to a first threshold, and if the sample number in the clustering cluster is greater than or equal to a second threshold, retraining the knowledge-graph question-answering system by using the feedback characteristics under the condition that the compactness is greater than or equal to the first threshold and/or the sample number is greater than or equal to the second threshold, so as to achieve the purpose of automatically optimizing by using a feedback log of the knowledge-graph question-answering system, improve the accuracy of the knowledge-graph question-answering system, and have higher automation degree and optimization efficiency.
Of course, the question and answer information corresponding to the cluster can be sent to the maintainer, so that the maintainer can optimize the knowledge graph question and answer system based on the question and answer information corresponding to the cluster, and the optimization efficiency and the accuracy of the knowledge graph question and answer system are further improved.
The knowledge-spectrum question-answering system is optimized based on the feedback logs generated by the knowledge-spectrum question-answering system, the knowledge-spectrum question-answering system can be automatically and continuously optimized by using the logs generated by the knowledge-spectrum question-answering system, the monitoring and optimization by maintenance personnel are not needed, and the optimization efficiency is improved while the accuracy of the knowledge-spectrum question-answering system is improved.
Based on the same inventive concept, the second aspect of the present application further provides an optimization device of a knowledge-graph question-answering system corresponding to the optimization method of the knowledge-graph question-answering system, and as the problem solving principle of the optimization device of the knowledge-graph question-answering system in the present application is similar to that of the optimization method of the knowledge-graph question-answering system in the present application, the implementation of the optimization device of the knowledge-graph question-answering system can refer to the implementation of the method, and repeated parts are not repeated.
Fig. 3 is a schematic diagram illustrating an optimization apparatus of a knowledge-graph question-answering system according to an embodiment of the present application, which specifically includes:
an acquisition module 301 configured to acquire a feedback log generated by the knowledge-graph question-answering system;
a processing module 302 configured to perform computer-based language on the feedback log to obtain feedback characteristics;
an optimization module 303 configured to optimize the knowledge-graph question-answering system using the feedback features.
In another embodiment, the processing module 302 is specifically configured to:
and converting the text information in the feedback log into a machine language by using a preset rule to obtain the feedback characteristic.
In another embodiment, the optimization module 303 is specifically configured to:
clustering the feedback characteristics to obtain a cluster;
determining whether the closeness of the clustered cluster is greater than or equal to a first threshold and determining whether the number of samples in the clustered cluster is greater than or equal to a second threshold;
retraining the knowledge-graph question-answering system with the feedback features if the closeness is greater than or equal to the first threshold and/or the number of samples is greater than or equal to the second threshold.
In another embodiment, the optimizing device of the knowledge-graph question-answering system further comprises:
a sending module 304, configured to send the question-answer information corresponding to the cluster to a maintenance staff, so that the maintenance staff optimizes the knowledge graph question-answer system.
The knowledge-spectrum question-answering system is optimized based on the feedback logs generated by the knowledge-spectrum question-answering system, the knowledge-spectrum question-answering system can be automatically and continuously optimized by using the logs generated by the knowledge-spectrum question-answering system, the monitoring and optimization by maintenance personnel are not needed, and the optimization efficiency is improved while the accuracy of the knowledge-spectrum question-answering system is improved.
The storage medium is a computer-readable medium, and stores a computer program, and when the computer program is executed by a processor, the method provided in any embodiment of the present application is implemented, including the following steps S11 to S13:
s11, obtaining a feedback log generated by the knowledge-graph question-answering system;
s12, converting the feedback log into computer language to obtain feedback characteristics;
and S13, optimizing the knowledge-graph question-answering system by using the feedback characteristics.
When the computer program is executed by the processor to perform computer language transformation on the feedback log to obtain the feedback characteristic, the processor specifically executes the following steps: and converting the text information in the feedback log into a machine language by using a preset rule to obtain the feedback characteristic.
When the computer program is executed by the processor to optimize the knowledge-graph question-answering system by using the feedback characteristics, the computer program is also executed by the processor to perform the following steps: clustering the feedback characteristics to obtain a cluster; determining whether the closeness of the clustered cluster is greater than or equal to a first threshold and determining whether the number of samples in the clustered cluster is greater than or equal to a second threshold; retraining the knowledge-graph question-answering system with the feedback features if the closeness is greater than or equal to the first threshold and/or the number of samples is greater than or equal to the second threshold.
When the computer program is executed by the processor to execute the optimization method, the processor further executes the following steps: and sending the question-answer information corresponding to the cluster to a maintainer so that the maintainer can optimize the knowledge graph question-answer system.
The knowledge-spectrum question-answering system is optimized based on the feedback logs generated by the knowledge-spectrum question-answering system, the knowledge-spectrum question-answering system can be automatically and continuously optimized by using the logs generated by the knowledge-spectrum question-answering system, the monitoring and optimization by maintenance personnel are not needed, and the optimization efficiency is improved while the accuracy of the knowledge-spectrum question-answering system is improved.
An electronic device is provided in an embodiment of the present application, and a schematic structural diagram of the electronic device may be as shown in fig. 4, where the electronic device at least includes a memory 401 and a processor 402, a computer program is stored on the memory 401, and the processor 402 implements the method provided in any embodiment of the present application when executing the computer program on the memory 401. Illustratively, the electronic device computer program steps are as follows S21-S23:
s21, obtaining a feedback log generated by the knowledge-graph question-answering system;
s22, converting the feedback log into computer language to obtain feedback characteristics;
and S23, optimizing the knowledge-graph question-answering system by using the feedback characteristics.
When the processor executes the computer language to the feedback log stored in the memory and obtains the feedback characteristic, the processor also executes the following computer program: and converting the text information in the feedback log into a machine language by using a preset rule to obtain the feedback characteristic.
The processor, when executing the optimization of the knowledge-graph question-answering system using the feedback features stored on the memory, further executes the computer program of: clustering the feedback characteristics to obtain a cluster; determining whether the closeness of the clustered cluster is greater than or equal to a first threshold and determining whether the number of samples in the clustered cluster is greater than or equal to a second threshold; retraining the knowledge-graph question-answering system with the feedback features if the closeness is greater than or equal to the first threshold and/or the number of samples is greater than or equal to the second threshold.
The processor, when executing the optimization method stored on the memory, further executes the computer program: and sending the question-answer information corresponding to the cluster to a maintainer so that the maintainer can optimize the knowledge graph question-answer system.
The knowledge-spectrum question-answering system is optimized based on the feedback logs generated by the knowledge-spectrum question-answering system, the knowledge-spectrum question-answering system can be automatically and continuously optimized by using the logs generated by the knowledge-spectrum question-answering system, the monitoring and optimization by maintenance personnel are not needed, and the optimization efficiency is improved while the accuracy of the knowledge-spectrum question-answering system is improved.
Optionally, in this embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes. Optionally, in this embodiment, the processor executes the method steps described in the above embodiments according to the program code stored in the storage medium. Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and this embodiment is not described herein again. It will be apparent to those skilled in the art that the modules or steps of the present application described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present application is not limited to any specific combination of hardware and software.
Moreover, although exemplary embodiments have been described herein, the scope thereof includes any and all embodiments based on the present application with equivalent elements, modifications, omissions, combinations (e.g., of various embodiments across), adaptations or alterations. The elements of the claims are to be interpreted broadly based on the language employed in the claims and not limited to examples described in the present specification or during the prosecution of the application, which examples are to be construed as non-exclusive. It is intended, therefore, that the specification and examples be considered as exemplary only, with a true scope and spirit being indicated by the following claims and their full scope of equivalents.
The above description is intended to be illustrative and not restrictive. For example, the above-described examples (or one or more versions thereof) may be used in combination with each other. For example, other embodiments may be used by those of ordinary skill in the art upon reading the above description. In addition, in the above detailed description, various features may be grouped together to streamline the application. This should not be interpreted as an intention that a disclosed feature not claimed is essential to any claim. Rather, subject matter of the present application can lie in less than all features of a particular disclosed embodiment. Thus, the following claims are hereby incorporated into the detailed description as examples or embodiments, with each claim standing on its own as a separate embodiment, and it is contemplated that these embodiments may be combined with each other in various combinations or permutations. The scope of the application should be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.
The embodiments of the present application have been described in detail, but the present application is not limited to these specific embodiments, and those skilled in the art can make various modifications and modified embodiments based on the concept of the present application, and these modifications and modified embodiments should fall within the scope of the present application.
Claims (10)
1. An optimization method of a knowledge-graph question-answering system is characterized by being applied to the knowledge-graph question-answering system and comprising the following steps:
acquiring a feedback log generated by a knowledge graph question-answering system;
performing computer linguishing on the feedback log to obtain feedback characteristics;
and optimizing the knowledge-graph question-answering system by using the feedback characteristics.
2. The optimization method according to claim 1, wherein the feedback log comprises user-generated question-answer information using the knowledge-graph question-answer system and user-fed use information based on the question-answer information.
3. The optimization method of claim 1, wherein the computer-speaking the feedback log to obtain the feedback features comprises:
and converting the text information in the feedback log into a machine language by using a preset rule to obtain the feedback characteristic.
4. The optimization method according to claim 1, wherein the optimizing the knowledge-graph question-answering system using the feedback features comprises:
clustering the feedback characteristics to obtain a cluster;
determining whether the closeness of the clustered cluster is greater than or equal to a first threshold and determining whether the number of samples in the clustered cluster is greater than or equal to a second threshold;
retraining the knowledge-graph question-answering system with the feedback features if the closeness is greater than or equal to the first threshold and/or the number of samples is greater than or equal to the second threshold.
5. The optimization method of claim 4, further comprising:
and sending the question-answer information corresponding to the cluster to a maintainer so that the maintainer can optimize the knowledge graph question-answer system.
6. An optimization device of a knowledge-graph question-answering system, which is applied to the knowledge-graph question-answering system, the optimization device comprises:
an acquisition module configured to acquire a feedback log generated by the knowledge-graph question-answering system;
the processing module is used for carrying out computer language conversion on the feedback log in a configuration mode to obtain feedback characteristics;
an optimization module configured to optimize the knowledge-graph question-answering system using the feedback features.
7. The identification device of claim 6, wherein the processing module is specifically configured to:
and converting the text information in the feedback log into a machine language by using a preset rule to obtain the feedback characteristic.
8. The identification device of claim 6, wherein the optimization module is specifically configured to:
clustering the feedback characteristics to obtain a cluster;
determining whether the closeness of the clustered cluster is greater than or equal to a first threshold and determining whether the number of samples in the clustered cluster is greater than or equal to a second threshold;
retraining the knowledge-graph question-answering system with the feedback features if the closeness is greater than or equal to the first threshold and/or the number of samples is greater than or equal to the second threshold.
9. A storage medium, having a computer program stored thereon, the computer program when executed by a processor performing the steps of:
acquiring a feedback log generated by a knowledge graph question-answering system;
performing computer linguishing on the feedback log to obtain feedback characteristics;
and optimizing the knowledge-graph question-answering system by using the feedback characteristics.
10. An electronic device, comprising: a processor and a memory, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating over a bus when an electronic device is operating, the machine-readable instructions when executed by the processor performing the steps of:
acquiring a feedback log generated by a knowledge graph question-answering system;
performing computer linguishing on the feedback log to obtain feedback characteristics;
and optimizing the knowledge-graph question-answering system by using the feedback characteristics.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111094235.8A CN113918689A (en) | 2021-09-17 | 2021-09-17 | Optimization method and device of knowledge graph question-answering system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111094235.8A CN113918689A (en) | 2021-09-17 | 2021-09-17 | Optimization method and device of knowledge graph question-answering system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113918689A true CN113918689A (en) | 2022-01-11 |
Family
ID=79235256
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111094235.8A Pending CN113918689A (en) | 2021-09-17 | 2021-09-17 | Optimization method and device of knowledge graph question-answering system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113918689A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018000280A1 (en) * | 2016-06-29 | 2018-01-04 | 深圳狗尾草智能科技有限公司 | Multi-mode based intelligent robot interaction method and intelligent robot |
| CN108776684A (en) * | 2018-05-25 | 2018-11-09 | 华东师范大学 | Optimization method, device, medium, equipment and the system of side right weight in knowledge mapping |
-
2021
- 2021-09-17 CN CN202111094235.8A patent/CN113918689A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018000280A1 (en) * | 2016-06-29 | 2018-01-04 | 深圳狗尾草智能科技有限公司 | Multi-mode based intelligent robot interaction method and intelligent robot |
| CN108776684A (en) * | 2018-05-25 | 2018-11-09 | 华东师范大学 | Optimization method, device, medium, equipment and the system of side right weight in knowledge mapping |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3540612A1 (en) | Cluster processing method and device for questions in automatic question and answering system | |
| CN108920675B (en) | Information processing method and device, computer storage medium and terminal | |
| CN110704521A (en) | Interface data access method and system | |
| CN112035599B (en) | Query method and device based on vertical search, computer equipment and storage medium | |
| CN110135590B (en) | Information processing method, information processing apparatus, information processing medium, and electronic device | |
| CN112559865B (en) | Information processing system, computer-readable storage medium, and electronic device | |
| CN112182174A (en) | Business question-answer knowledge query method and device, computer equipment and storage medium | |
| CN112307318B (en) | Content publishing method, system and device | |
| CN112346775A (en) | General index data processing method, electronic device and storage medium | |
| US11568344B2 (en) | Systems and methods for automated pattern detection in service tickets | |
| CN113051384B (en) | User portrait extraction method based on dialogue and related device | |
| WO2022123490A1 (en) | Systems and methods for managing connections in scalable clusters | |
| CN112200465B (en) | Electric power AI method and system based on multimedia information intelligent analysis | |
| CN111563037B (en) | Test optimization method and device based on test questions, storage medium and terminal | |
| CN109145092B (en) | Database updating and intelligent question and answer management method, device and equipment | |
| CN109145124B (en) | Information storage method and device, storage medium and electronic device | |
| CN116701604A (en) | Question and answer corpus construction method and device, question and answer method, equipment and medium | |
| CN113918689A (en) | Optimization method and device of knowledge graph question-answering system | |
| CN114282940A (en) | Method and apparatus for intention recognition, storage medium, and electronic device | |
| CN110008291B (en) | Data early warning method and device, storage medium and electronic equipment | |
| CN113177418A (en) | Session theme determining method and device, storage medium and electronic equipment | |
| CN112612841A (en) | Knowledge extraction construction method, device, equipment and storage medium | |
| CN109086207A (en) | Page response failure analysis methods, computer readable storage medium and terminal device | |
| CN116757203B (en) | Natural language matching method, device, computer equipment and storage medium | |
| CN117112846B (en) | Multi-information source license information management method, system and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |