CN112035483B - Knowledge storage and retrieval method and device for knowledge base - Google Patents
Knowledge storage and retrieval method and device for knowledge base Download PDFInfo
- Publication number
- CN112035483B CN112035483B CN202010905086.8A CN202010905086A CN112035483B CN 112035483 B CN112035483 B CN 112035483B CN 202010905086 A CN202010905086 A CN 202010905086A CN 112035483 B CN112035483 B CN 112035483B
- Authority
- CN
- China
- Prior art keywords
- knowledge
- data
- degree
- knowledge data
- storage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000003062 neural network model Methods 0.000 claims abstract description 48
- 238000004590 computer program Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 15
- 238000012795 verification Methods 0.000 claims description 10
- 238000012423 maintenance Methods 0.000 claims description 5
- 230000002349 favourable effect Effects 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2453—Query optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a knowledge storage and retrieval method and device of a knowledge base, wherein the knowledge storage method of the knowledge base comprises the following steps: predicting the use degree of knowledge data by using a pre-established neural network model; dividing the knowledge data according to the using degree of the knowledge data and with preset dimensions to obtain knowledge data with different dimensions; slicing knowledge data of different dimensions according to a preset server storage threshold; and storing the sliced knowledge data with different dimensions in different servers according to the using degree of the knowledge data so as to establish a knowledge base. The invention provides a novel knowledge base knowledge storage mode which is favorable for quickly searching the knowledge to be searched, and the knowledge to be searched can be searched from a corresponding server according to the using degree of knowledge data. Compared with the prior art, the situation that the whole knowledge base needs to be traversed in each retrieval is avoided, and the retrieval waiting time of a user is shortened.
Description
Technical Field
The invention relates to the technical field of databases, in particular to a knowledge storage and retrieval method and device of a knowledge base.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
With the continuous use of intelligent knowledge bases of banks, more and more knowledge is accumulated and deposited in the knowledge bases, but the data is often stored by a relational database or a knowledge graph, and the storage mode is unordered storage. When searching the knowledge base stored by the conventional technology, the knowledge to be searched needs to be traversed in the whole knowledge base until the matched knowledge data is found. The whole knowledge base is required to be searched when searching, so that the searching speed of the knowledge base is very slow, the waiting time of a user is long, and the use experience is poor.
Disclosure of Invention
The embodiment of the invention provides a knowledge storage method of a knowledge base, which is used for providing a new knowledge storage mode of the knowledge base, wherein the storage mode is beneficial to quickly searching knowledge to be searched, and the method comprises the following steps:
predicting the use degree of knowledge data by using a pre-established neural network model; the neural network model is determined according to knowledge historical storage data and historical use degree;
dividing the knowledge data according to the using degree of the knowledge data and with preset dimensions to obtain knowledge data with different dimensions; the dimension is classification of the use degree of the knowledge data;
slicing knowledge data of different dimensions according to a preset server storage threshold;
and storing the sliced knowledge data with different dimensions in different servers according to the using degree of the knowledge data so as to establish a knowledge base.
The embodiment of the invention also provides a knowledge storage device of the knowledge base, which is used for providing a new knowledge storage mode of the knowledge base, and the storage mode is favorable for quickly searching the knowledge to be searched, and the device comprises:
the prediction module is used for predicting the use degree of the knowledge data by using a pre-established neural network model; the neural network model is determined according to knowledge historical storage data and historical use degree;
the division module is used for dividing the knowledge data according to the use degree of the knowledge data and with preset dimensions to obtain knowledge data with different dimensions; the dimension is classification of the use degree of the knowledge data;
the slicing module is used for slicing knowledge data with different dimensions according to a preset server storage threshold value;
and the storage module is used for storing the sliced knowledge data with different dimensions in different servers according to the using degree of the knowledge data so as to establish a knowledge base.
The embodiment of the invention also provides a knowledge base knowledge retrieval method which is applied to a knowledge base established by adopting the knowledge base knowledge storage method and is used for quickly retrieving knowledge to be retrieved, and the knowledge base knowledge retrieval method comprises the following steps:
receiving a knowledge retrieval request, wherein the knowledge retrieval request carries an identifier corresponding to the knowledge to be retrieved;
and searching the knowledge to be searched from the corresponding server according to the use degree of the knowledge data and the identification corresponding to the knowledge to be searched.
The embodiment of the invention also provides a knowledge retrieval device of the knowledge base, which is applied to the knowledge base established by adopting the knowledge storage method of the knowledge base and is used for quickly retrieving the knowledge to be retrieved, and the device comprises:
the request receiving module is used for receiving a knowledge retrieval request, wherein the knowledge retrieval request carries an identifier corresponding to the knowledge to be retrieved;
and the retrieval module is used for retrieving the knowledge to be retrieved from the corresponding server according to the identification corresponding to the knowledge to be retrieved and the use degree of the knowledge data.
The embodiment of the invention also provides computer equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the knowledge storage method or the knowledge retrieval method of the knowledge base when executing the computer program.
The embodiment of the invention also provides a computer readable storage medium, which stores a computer program for executing the knowledge storage method or the knowledge retrieval method of the knowledge base.
In the embodiment of the invention, the use degree of knowledge data is predicted by a pre-established neural network model; the neural network model is determined according to knowledge historical storage data and historical use degree; dividing the knowledge data according to the using degree of the knowledge data and with preset dimensions to obtain knowledge data with different dimensions; the dimension is classification of the use degree of the knowledge data; slicing knowledge data of different dimensions according to a preset server storage threshold; according to the using degree of the knowledge data, the sliced knowledge data with different dimensionalities are stored in different servers to establish a knowledge base, so that a new knowledge base knowledge storage mode is provided, the storage mode is favorable for quickly searching the knowledge to be searched, and the knowledge to be searched can be searched from the corresponding servers according to the using degree of the knowledge data. Compared with the prior art, if the use degree of the knowledge to be searched is higher, the matched knowledge data can be quickly searched, and the condition that the whole knowledge base needs to be traversed in each search is avoided, so that the knowledge to be searched is quickly searched, the search waiting time of a user is shortened, and the user experience is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
FIG. 1 is a flow chart of a knowledge base knowledge storage method in an embodiment of the invention;
FIG. 2 is a diagram illustrating a knowledge storage method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a knowledge storage device of a knowledge base according to an embodiment of the invention;
FIG. 4 is a diagram illustrating a knowledge storage apparatus according to an embodiment of the invention;
FIG. 5 is a flowchart of a knowledge base knowledge retrieval method according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a knowledge retrieval device for a knowledge base according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present invention and their descriptions herein are for the purpose of explaining the present invention, but are not to be construed as limiting the invention.
The knowledge storage method for the knowledge base provided by the embodiment of the invention, as shown in fig. 1, can include:
step 101: predicting the use degree of knowledge data by using a pre-established neural network model; the neural network model is determined according to knowledge historical storage data and historical use degree;
step 102: dividing the knowledge data according to the using degree of the knowledge data and with preset dimensions to obtain knowledge data with different dimensions; the dimension is classification of the use degree of the knowledge data;
step 103: slicing knowledge data of different dimensions according to a preset server storage threshold;
step 104: and storing the sliced knowledge data with different dimensions in different servers according to the using degree of the knowledge data so as to establish a knowledge base.
In the embodiment of the invention, the use degree of knowledge data is predicted by a pre-established neural network model; the neural network model is determined according to knowledge historical storage data and historical use degree; dividing the knowledge data according to the using degree of the knowledge data and with preset dimensions to obtain knowledge data with different dimensions; the dimension is classification of the use degree of the knowledge data; slicing knowledge data of different dimensions according to a preset server storage threshold; according to the using degree of the knowledge data, the sliced knowledge data with different dimensionalities are stored in different servers to establish a knowledge base, so that a new knowledge base knowledge storage mode is provided, the storage mode is favorable for quickly searching the knowledge to be searched, and the knowledge to be searched can be searched from the corresponding servers according to the using degree of the knowledge data. Compared with the prior art, if the use degree of the knowledge to be searched is higher, the matched knowledge data can be quickly searched, and the condition that the whole knowledge base needs to be traversed in each search is avoided, so that the knowledge to be searched is quickly searched, the search waiting time of a user is shortened, and the user experience is improved.
In the specific implementation, firstly, predicting the use degree of knowledge data by using a pre-established neural network model; the neural network model is determined according to knowledge historical storage data and historical use degree.
In an embodiment, the usage level of the knowledge data may include, for example: most commonly used, moderately used, generally used and cold doors. Wherein, the most common use is that the use times in a preset time period are more than K times; the moderate use is that the use times in a preset time period are more than M times and less than or equal to K times; the usage is generally that the usage times in a preset time period are more than N times and less than or equal to M times; the cold door is used for less than or equal to N times in a preset time period; wherein K, M, N is a threshold value of the number of times preset by the staff in the knowledge base according to the use requirement, and K > M > N. The classification storage of the knowledge data in the subsequent steps is facilitated by predicting the use degree of the knowledge data, and the division of the use degree of the knowledge data is facilitated.
In specific implementation, the knowledge base knowledge storage method provided by the embodiment of the invention can further include: the neural network model is pre-established as follows: acquiring knowledge history storage data and history use degree; establishing a neural network model according to preset knowledge related parameters; the knowledge related parameters comprise one or any combination of a knowledge keyword list, a knowledge label, knowledge month access times, knowledge maintenance times and problem reporting times; generating a training set and a verification set of the model according to knowledge historical storage data and historical use degree; and training and verifying the established neural network model according to the training set and the verification set of the model to obtain a final neural network model.
In an embodiment, pre-building the neural network model may include building a three-layer neural network model. According to kolmogorov (kolmogorov) principle, a three-layer BP (back propagation) neural network (a multi-layer feedforward neural network trained according to an error-back propagation algorithm) is sufficient to accomplish arbitrary n-dimensional to m-dimensional mapping. First, a certain amount of knowledge history data in a knowledge base is selected, and a history use degree of the knowledge history data is determined. And secondly, presetting knowledge related parameters such as one or any combination of a knowledge keyword list, a knowledge label, knowledge month access times, knowledge maintenance times and problem reporting times. Then, according to preset knowledge related parameters, a neural network model is established, for example, the preset knowledge related parameters are used as input parameters of the neural network model, the using degree value of knowledge data is used as output of the neural network model, and according to knowledge historical storage data and historical using degree, a training set and a verification set of the model are generated; and continuously training and verifying the established neural network model according to the training set and the verification set of the model to obtain a final neural network model.
In the above embodiment, by establishing the neural network model, the prediction of the usage degree of the knowledge data can be realized, which is beneficial to the division of the knowledge data in the subsequent steps.
In the specific implementation, after the use degree of knowledge data is predicted by a pre-established neural network model, the knowledge data is divided by preset dimensions according to the use degree of the knowledge data, so that knowledge data with different dimensions are obtained; the dimension is a classification of the degree of use of the knowledge data.
In the embodiment, after predicting the use degree of the knowledge data to be stored, dividing the knowledge data according to the use degree of the knowledge data and with preset dimensions; the dimension is a classification of the usage degree of the knowledge data, and for example, the dimension may include the following four dimensions: most commonly used, moderately used, generally used and cold doors.
In the above embodiment, knowledge data with different dimensions can be obtained by dividing the knowledge data with preset dimensions, which is helpful for dividing the knowledge data to be stored and improving the retrieval speed of the knowledge base. The knowledge base is divided into multiple dimensions, so that the knowledge retrieval range is reduced.
In the implementation, the knowledge data are divided according to the use degree of the knowledge data and the preset dimensionality, so that the knowledge data with different dimensionalities are obtained, and then the knowledge data with different dimensionalities are respectively sliced according to the preset server storage threshold value.
In an embodiment, according to a preset server storage threshold, a plurality of methods for slicing knowledge data in different dimensions respectively may be included, for example, as shown in fig. 2, which may include:
step 201: for knowledge data of each dimension, determining the number of slices of the knowledge data of the dimension according to a preset server storage threshold;
step 201: slicing the knowledge data of the dimension according to the slicing quantity of the knowledge data of the dimension.
The preset server storage threshold value can be set according to the performance requirements of the business departments and the physical parameters of the database. For example, a server such as an 8-core 16g may require a response time of about 2 seconds when storing knowledge data of 100 ten thousand data, and if the response time meets the performance requirements of the business department, the storage threshold of the server may be set to 100 ten thousand data. When slicing knowledge data of different dimensions, the knowledge data of the dimension can be sliced according to a storage threshold of a server with 100 ten thousand data volume.
In the embodiment, by slicing the knowledge data in different dimensions, slicing storage of knowledge data in any dimension can be realized, the purpose of storing knowledge data in the dimension on different servers is realized, and the retrieval speed of a knowledge base is improved when retrieving knowledge. When retrieving the knowledge to be retrieved, all servers storing knowledge data with different dimensions can be synchronously retrieved, so that the retrieval speed of the knowledge base can be further improved.
In the implementation, after knowledge data in different dimensions are respectively sliced according to a preset server storage threshold, the sliced knowledge data in different dimensions are stored in different servers according to the using degree of the knowledge data so as to establish a knowledge base.
In an embodiment, according to the usage degree of knowledge data, there are various methods for storing the sliced knowledge data in different dimensions in different servers, for example, the method may include: reordering the knowledge data of each slice according to the use degree of the knowledge data; the reordered knowledge data for each slice is stored in a different server.
In the above embodiment, knowledge data of different dimensions after slicing is stored in different servers according to the usage degree of the knowledge data, so as to realize the storage of the knowledge data of different dimensions after slicing. Knowledge data of different dimensions after slicing is stored in different servers, so that the knowledge base built by the knowledge base knowledge storage method provided by the embodiment of the invention can be quickly searched. During retrieval, the knowledge to be retrieved can be retrieved from the corresponding server according to the using degree of the knowledge data. Compared with the prior art, if the use degree of the knowledge to be searched is higher, the matched knowledge data can be quickly searched, and the situation that the whole knowledge base needs to be traversed in each search is avoided.
In practice, there are various methods for reordering knowledge data of each slice according to the usage degree of knowledge data, for example, the methods may include: re-sequencing the knowledge data of each slice by using a preset knowledge graph label and a knowledge individual label; the knowledge graph label is a label when knowledge builds a knowledge graph; the knowledge personality tags include click rate and collection times of knowledge.
In the embodiment, the knowledge data of each slice is reordered by using the preset knowledge graph label and the knowledge individual label, and the preset knowledge graph label and the knowledge individual label can be used as the distinguishing degree index of the knowledge data, so that the knowledge data is individualized and distinguished, and the retrieval speed is improved. Wherein, the map label is an inherent label of knowledge, namely, a necessary filling item of knowledge. For example, for the "mid-silver-rich personal notification deposit introduction" knowledge, it has two atlas labels of product and customer type, where the product is the rich notification deposit and the customer type is the personal customer, i.e. the knowledge applies to the personal customer. When reordering, according to the use habit of the bank agent, for example, most agent sources select the map labels and then select the individual labels when retrieving knowledge, and when reordering, the map labels can be classified and summarized, and then summarized according to the individual labels, knowledge with the same map labels is reordered according to the click rate and collection times in sequence. The knowledge on the slice is reordered according to the degree of distinction, so that the retrieval speed of the seat personnel to the knowledge to be retrieved can be increased.
In the embodiment of the invention, the use degree of knowledge data is predicted by a pre-established neural network model; the neural network model is determined according to knowledge historical storage data and historical use degree; dividing the knowledge data according to the using degree of the knowledge data and with preset dimensions to obtain knowledge data with different dimensions; the dimension is classification of the use degree of the knowledge data; slicing knowledge data of different dimensions according to a preset server storage threshold; according to the using degree of the knowledge data, the sliced knowledge data with different dimensionalities are stored in different servers to establish a knowledge base, so that a new knowledge base knowledge storage mode is provided, the storage mode is favorable for quickly searching the knowledge to be searched, and the knowledge to be searched can be searched from the corresponding servers according to the using degree of the knowledge data. Compared with the prior art, if the use degree of the knowledge to be searched is higher, the matched knowledge data can be quickly searched, and the condition that the whole knowledge base needs to be traversed in each search is avoided, so that the knowledge to be searched is quickly searched, the search waiting time of a user is shortened, and the user experience is improved.
As described above, the embodiment of the invention can segment according to the comprehensive service requirement and the server capability, and reorder the segments according to the user using strategy and the distinguishing index, thereby improving the query hit rate of the system, reducing the waiting time of the user and effectively improving the using experience of the system.
The embodiment of the invention also provides a knowledge storage device of the knowledge base, which is described in the following embodiment. Because the principle of the device for solving the problems is similar to that of the knowledge storage method of the knowledge base, the implementation of the device can refer to the implementation of the knowledge storage method of the knowledge base, and the repetition is omitted.
The embodiment of the invention also provides a knowledge storage device of the knowledge base, as shown in fig. 3, which may include:
the prediction module 01 is used for predicting the use degree of the knowledge data by using a pre-established neural network model; the neural network model is determined according to knowledge historical storage data and historical use degree;
the division module 02 is used for dividing the knowledge data according to the use degree of the knowledge data and with preset dimensions to obtain knowledge data with different dimensions; the dimension is classification of the use degree of the knowledge data;
the slicing module 03 is used for slicing knowledge data of different dimensions according to a preset server storage threshold;
and the storage module 04 is used for storing the sliced knowledge data with different dimensions in different servers according to the using degree of the knowledge data so as to establish a knowledge base.
In one embodiment, as shown in fig. 4, the knowledge base knowledge storage apparatus provided by the embodiment of the present invention may further include: the modeling module 05 is configured to pre-establish a neural network model as follows:
acquiring knowledge history storage data and history use degree;
establishing a neural network model according to preset knowledge related parameters; the knowledge related parameters comprise one or any combination of a knowledge keyword list, a knowledge label, knowledge month access times, knowledge maintenance times and problem reporting times;
generating a training set and a verification set of the model according to knowledge historical storage data and historical use degree;
and training and verifying the established neural network model according to the training set and the verification set of the model to obtain a final neural network model.
In one embodiment, the slicing module is specifically configured to:
for knowledge data of each dimension, determining the number of slices of the knowledge data of the dimension according to a preset server storage threshold;
slicing the knowledge data of the dimension according to the slicing quantity of the knowledge data of the dimension.
In one embodiment, the storage module is specifically configured to: reordering the knowledge data of each slice according to the use degree of the knowledge data; the reordered knowledge data for each slice is stored in a different server.
In one embodiment, the storage module is specifically configured to: according to the using degree of the knowledge data, reordering the knowledge data of each slice by using a preset knowledge graph label and a knowledge individual label; the knowledge graph label is a label when knowledge builds a knowledge graph; the knowledge personality tags include click rate and collection times of knowledge.
The embodiment of the invention also provides a knowledge retrieval method of the knowledge base, which is applied to the knowledge base established by adopting the knowledge storage method of the knowledge base, and as shown in fig. 5, the method can comprise the following steps:
step 501: receiving a knowledge retrieval request, wherein the knowledge retrieval request carries an identifier corresponding to the knowledge to be retrieved;
step 502: and searching the knowledge to be searched from the corresponding server according to the use degree of the knowledge data and the identification corresponding to the knowledge to be searched.
In the implementation, firstly, a knowledge retrieval request is received, wherein the knowledge retrieval request carries an identifier corresponding to the knowledge to be retrieved.
In an embodiment, a knowledge retrieval request is received first, and an identifier corresponding to knowledge to be retrieved, which is carried in the knowledge retrieval request, is obtained.
In the above embodiment, by receiving the knowledge retrieval request, the bank staff is facilitated to acquire the knowledge retrieval request of the client, and at the same time, the subsequent retrieval of the knowledge to be retrieved is facilitated.
In the implementation, after receiving the knowledge retrieval request, retrieving the knowledge to be retrieved from a corresponding server according to the identification corresponding to the knowledge to be retrieved and the use degree of the knowledge data.
In an embodiment, according to the identifier corresponding to the knowledge to be searched, according to the usage degree of the knowledge data, there are various methods for searching the knowledge to be searched from the corresponding server, for example, the method may include: and searching the knowledge to be searched from the corresponding server according to the identification corresponding to the knowledge to be searched in the order from big to small according to the using degree of the knowledge data.
In the above embodiment, the knowledge to be searched is searched from the corresponding server according to the order of the using degree of the knowledge data from large to small, which is favorable for realizing the quick search of the knowledge to be searched, and once the knowledge to be searched is searched from the server with the previous order of the using degree of the knowledge data from large to small, the search can be stopped and the search result is returned.
In an embodiment, according to the identifier corresponding to the knowledge to be searched, according to the usage degree of the knowledge data, there are various methods for searching the knowledge to be searched from the corresponding server, for example, the method may further include: and searching the knowledge to be searched from the corresponding server according to the use degree of the knowledge data and within the use degree range of the preset knowledge data according to the identification corresponding to the knowledge to be searched.
In the above embodiment, the knowledge to be searched is searched within the preset using degree range according to the using degree of the knowledge data, which is favorable for realizing the quick search of the knowledge to be searched. By presetting the use degree range of the knowledge data, the purpose of searching the knowledge to be searched in the server corresponding to the use degree range of the knowledge data can be achieved, so that when the knowledge to be searched is determined to be knowledge with a certain use degree by a worker, the knowledge searching range of a knowledge base can be effectively reduced during searching, and the knowledge to be searched can be searched only by searching in the server corresponding to the use degree range of the knowledge data. Compared with the prior art, the situation that the whole knowledge base needs to be traversed in each retrieval is avoided, so that the knowledge to be retrieved is facilitated to be quickly retrieved, the retrieval waiting time of a user is shortened, and the user experience is improved.
The embodiment of the invention also provides a knowledge retrieval device of the knowledge base, which is described in the following embodiment. Because the principle of the device for solving the problems is similar to that of the knowledge base knowledge retrieval method, the implementation of the device can refer to the implementation of the knowledge base knowledge retrieval method, and the repetition is omitted.
The knowledge retrieval device for a knowledge base provided by the embodiment of the invention is applied to the knowledge base established by adopting the knowledge base knowledge storage method, and as shown in fig. 6, the device can comprise:
the request receiving module 01 is used for receiving a knowledge retrieval request, wherein the knowledge retrieval request carries an identifier corresponding to the knowledge to be retrieved;
and the retrieval module 02 is used for retrieving the knowledge to be retrieved from the corresponding server according to the corresponding identification of the knowledge to be retrieved and the use degree of the knowledge data.
In one embodiment, the retrieval module is specifically configured to: and searching the knowledge to be searched from the corresponding server according to the identification corresponding to the knowledge to be searched in the order from big to small according to the using degree of the knowledge data.
The embodiment of the invention also provides computer equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the knowledge storage method or the knowledge retrieval method of the knowledge base when executing the computer program.
The embodiment of the invention also provides a computer readable storage medium, which stores a computer program for executing the knowledge storage method or the knowledge retrieval method of the knowledge base.
In the embodiment of the invention, the use degree of knowledge data is predicted by a pre-established neural network model; the neural network model is determined according to knowledge historical storage data and historical use degree; dividing the knowledge data according to the using degree of the knowledge data and with preset dimensions to obtain knowledge data with different dimensions; the dimension is classification of the use degree of the knowledge data; slicing knowledge data of different dimensions according to a preset server storage threshold; according to the using degree of the knowledge data, the sliced knowledge data with different dimensionalities are stored in different servers to establish a knowledge base, so that a new knowledge base knowledge storage mode is provided, the storage mode is favorable for quickly searching the knowledge to be searched, and the knowledge to be searched can be searched from the corresponding servers according to the using degree of the knowledge data. Compared with the prior art, if the use degree of the knowledge to be searched is higher, the matched knowledge data can be quickly searched, and the condition that the whole knowledge base needs to be traversed in each search is avoided, so that the knowledge to be searched is quickly searched, the search waiting time of a user is shortened, and the user experience is improved.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention 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 invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. 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.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (10)
1. A knowledge base knowledge storage method, comprising:
predicting the use degree of knowledge data by using a pre-established neural network model; the neural network model is determined according to knowledge historical storage data and historical use degree;
dividing the knowledge data according to the using degree of the knowledge data and with preset dimensions to obtain knowledge data with different dimensions; the dimension is classification of the use degree of the knowledge data;
slicing knowledge data of different dimensions according to a preset server storage threshold;
according to the using degree of the knowledge data, storing the sliced knowledge data with different dimensions in different servers to establish a knowledge base;
further comprises: the neural network model is pre-established as follows: acquiring knowledge history storage data and history use degree; establishing a neural network model according to preset knowledge related parameters; the knowledge related parameters comprise one or any combination of a knowledge keyword list, a knowledge label, knowledge month access times, knowledge maintenance times and problem reporting times; generating a training set and a verification set of the model according to knowledge historical storage data and historical use degree; training and verifying the established neural network model according to the training set and the verification set of the model to obtain a final neural network model;
slicing knowledge data of different dimensions according to a preset server storage threshold, including: for knowledge data of each dimension, determining the number of slices of the knowledge data of the dimension according to a preset server storage threshold; slicing the knowledge data of the dimension according to the slicing quantity of the knowledge data of the dimension.
2. The method of claim 1, wherein storing the sliced knowledge data of different dimensions in different servers based on a degree of use of the knowledge data, comprises:
reordering the knowledge data of each slice according to the use degree of the knowledge data;
the reordered knowledge data for each slice is stored in a different server.
3. The method of claim 2, wherein reordering knowledge data for each slice based on a degree of use of knowledge data comprises:
according to the using degree of the knowledge data, reordering the knowledge data of each slice by using a preset knowledge graph label and a knowledge individual label; the knowledge graph label is a label when knowledge builds a knowledge graph; the knowledge personality tags include click rate and collection times of knowledge.
4. A knowledge base knowledge storage apparatus, comprising:
the prediction module is used for predicting the use degree of the knowledge data by using a pre-established neural network model; the neural network model is determined according to knowledge historical storage data and historical use degree;
the division module is used for dividing the knowledge data according to the use degree of the knowledge data and with preset dimensions to obtain knowledge data with different dimensions; the dimension is classification of the use degree of the knowledge data;
the slicing module is used for slicing knowledge data with different dimensions according to a preset server storage threshold value;
the storage module is used for storing the sliced knowledge data with different dimensions in different servers according to the using degree of the knowledge data so as to establish a knowledge base;
further comprises: the modeling module is used for pre-establishing a neural network model as follows: acquiring knowledge history storage data and history use degree; establishing a neural network model according to preset knowledge related parameters; the knowledge related parameters comprise one or any combination of a knowledge keyword list, a knowledge label, knowledge month access times, knowledge maintenance times and problem reporting times; generating a training set and a verification set of the model according to knowledge historical storage data and historical use degree; training and verifying the established neural network model according to the training set and the verification set of the model to obtain a final neural network model;
the slicing module is specifically used for: for knowledge data of each dimension, determining the number of slices of the knowledge data of the dimension according to a preset server storage threshold; slicing the knowledge data of the dimension according to the slicing quantity of the knowledge data of the dimension.
5. A knowledge retrieval method for a knowledge base, applied to a knowledge base built by the method of any one of claims 1-3, comprising:
receiving a knowledge retrieval request, wherein the knowledge retrieval request carries an identifier corresponding to the knowledge to be retrieved;
and searching the knowledge to be searched from the corresponding server according to the use degree of the knowledge data and the identification corresponding to the knowledge to be searched.
6. The method of claim 5, wherein retrieving the knowledge to be retrieved from the corresponding server according to the identification corresponding to the knowledge to be retrieved and the usage degree of the knowledge data, comprises:
and searching the knowledge to be searched from the corresponding server according to the identification corresponding to the knowledge to be searched in the order from big to small according to the using degree of the knowledge data.
7. A knowledge base knowledge retrieval device for use in a knowledge base built by the method of any of claims 1-3, comprising:
the request receiving module is used for receiving a knowledge retrieval request, wherein the knowledge retrieval request carries an identifier corresponding to the knowledge to be retrieved;
and the retrieval module is used for retrieving the knowledge to be retrieved from the corresponding server according to the identification corresponding to the knowledge to be retrieved and the use degree of the knowledge data.
8. The apparatus of claim 7, wherein the retrieval module is configured to:
and searching the knowledge to be searched from the corresponding server according to the identification corresponding to the knowledge to be searched in the order from big to small according to the using degree of the knowledge data.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1-3,5-6 when executing the computer program.
10. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program for executing the method of any one of claims 1-3, 5-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010905086.8A CN112035483B (en) | 2020-09-01 | 2020-09-01 | Knowledge storage and retrieval method and device for knowledge base |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010905086.8A CN112035483B (en) | 2020-09-01 | 2020-09-01 | Knowledge storage and retrieval method and device for knowledge base |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112035483A CN112035483A (en) | 2020-12-04 |
CN112035483B true CN112035483B (en) | 2024-04-16 |
Family
ID=73590928
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010905086.8A Active CN112035483B (en) | 2020-09-01 | 2020-09-01 | Knowledge storage and retrieval method and device for knowledge base |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112035483B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113254571B (en) * | 2021-06-23 | 2024-02-23 | 中国银行股份有限公司 | Knowledge point storage method, device, server and medium |
CN113535685B (en) * | 2021-07-28 | 2024-05-17 | 深圳供电局有限公司 | Method for constructing event knowledge base of intelligent power grid dispatching |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9189528B1 (en) * | 2013-03-15 | 2015-11-17 | Google Inc. | Searching and tagging media storage with a knowledge database |
CN107992518A (en) * | 2017-10-31 | 2018-05-04 | 厦门快商通信息技术有限公司 | A kind of automatic question-answering method and system for lifting Intelligent dialogue speed |
CN110413748A (en) * | 2019-07-03 | 2019-11-05 | 北京智齿博创科技有限公司 | Based on big data robot service knowledge base entry recommender system |
CN111552818A (en) * | 2020-04-27 | 2020-08-18 | 中国银行股份有限公司 | Customer service knowledge base query method and device |
-
2020
- 2020-09-01 CN CN202010905086.8A patent/CN112035483B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9189528B1 (en) * | 2013-03-15 | 2015-11-17 | Google Inc. | Searching and tagging media storage with a knowledge database |
CN107992518A (en) * | 2017-10-31 | 2018-05-04 | 厦门快商通信息技术有限公司 | A kind of automatic question-answering method and system for lifting Intelligent dialogue speed |
CN110413748A (en) * | 2019-07-03 | 2019-11-05 | 北京智齿博创科技有限公司 | Based on big data robot service knowledge base entry recommender system |
CN111552818A (en) * | 2020-04-27 | 2020-08-18 | 中国银行股份有限公司 | Customer service knowledge base query method and device |
Also Published As
Publication number | Publication date |
---|---|
CN112035483A (en) | 2020-12-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Xiong et al. | Temporal collaborative filtering with bayesian probabilistic tensor factorization | |
CN106933956B (en) | Data mining method and device | |
US9965531B2 (en) | Data storage extract, transform and load operations for entity and time-based record generation | |
CN112035483B (en) | Knowledge storage and retrieval method and device for knowledge base | |
WO2015001558A1 (en) | System and method for predicting sales | |
JP2003519828A (en) | Probabilistic record link model derived from training data | |
US11216855B2 (en) | Server computer and networked computer system for evaluating, storing, and managing labels for classification model evaluation and training | |
CN110322093B (en) | Information processing method, information display method, information processing device and computing equipment | |
CN106776695B (en) | Method for automatically identifying value of document and file | |
CN105117442B (en) | A kind of big data querying method based on probability | |
CN107181776A (en) | A kind of data processing method and relevant device, system | |
CA3114298A1 (en) | Recommendation method and system and method and system for improving a machine learning system | |
CN113627995A (en) | Commodity recommendation list updating method and device, equipment, medium and product thereof | |
WO2016113747A1 (en) | A query processing engine recommendation method and system | |
CN111738778A (en) | User portrait generation method and device, computer equipment and storage medium | |
CN115062676A (en) | Data processing method, device and computer readable storage medium | |
CN113536085B (en) | Method and system for scheduling subject term search crawlers based on combined prediction method | |
CN111133467B (en) | Quick learning recommendation system for cargo basket | |
Haw et al. | Improving the Prediction Resolution Time for Customer Support Ticket System | |
US11636381B1 (en) | Event streams in a machine learning system for demand forecasting | |
CN106600053A (en) | Spatial-temporal trajectory and social network user attribute prediction system | |
CN112085566A (en) | Product recommendation method and device based on intelligent decision and computer equipment | |
Vlassopoulos et al. | Dynamic graph management for streaming social media analytics | |
CN117272048A (en) | Data set processing method and device based on machine learning platform | |
CN117633165B (en) | Intelligent AI customer service dialogue guiding method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |