CN112733492A - Knowledge base-based aided design method and device, terminal and storage medium - Google Patents
Knowledge base-based aided design method and device, terminal and storage medium Download PDFInfo
- Publication number
- CN112733492A CN112733492A CN202011643855.8A CN202011643855A CN112733492A CN 112733492 A CN112733492 A CN 112733492A CN 202011643855 A CN202011643855 A CN 202011643855A CN 112733492 A CN112733492 A CN 112733492A
- Authority
- CN
- China
- Prior art keywords
- phrase
- target
- standard
- knowledge base
- phrases
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/103—Formatting, i.e. changing of presentation of documents
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses an auxiliary design method, a device, a terminal and a storage medium based on a knowledge base, wherein the method comprises the steps of obtaining at least one phrase, carrying out clustering processing on the at least one phrase to obtain N phrase sets, determining a target screening mode corresponding to a target scene, and screening a standard phrase from each phrase set based on the target screening mode to obtain N standard phrases; constructing a target knowledge base corresponding to a target scene based on the N phrase sets and the N standard phrases; when a reference phrase input in a target scene is detected, determining a target phrase set corresponding to the reference phrase from a target knowledge base, and determining a target standard phrase in the target phrase set; and performing auxiliary design on the reference phrases based on the target standard phrase group. By implementing the method, a knowledge base can be constructed, and in the process of writing data by a user, the auxiliary design is carried out based on the knowledge base, so that the normative of the written data is improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an auxiliary design method, an auxiliary design device, a terminal and a storage medium based on a knowledge base.
Background
The data standard is the main reference and basis for carrying out data standardization and disambiguating data services. Traditional data standard management emphasizes the management of existing data, regulating architecture and maintenance flow by formulating rules.
Specifically, some rules are formulated to determine whether the data written by the user meets the data standard, such as formulated language rules, font rules, punctuation rules, and the like, however, the formulation of the rules can only enable the user to find the problems in the form of the written data, and the problems of the normalization of words used in the written data, the encumbrance of sentences, and the like cannot be known, which results in lower normalization of the data written by the user.
Disclosure of Invention
The embodiment of the invention provides an auxiliary design method, an auxiliary design device, a terminal and a storage medium based on a knowledge base.
In one aspect, an embodiment of the present invention provides an aided design method based on a knowledge base, where the method includes:
acquiring at least one phrase, and clustering the at least one phrase to obtain N phrase sets, wherein N is a positive integer;
determining a target screening mode corresponding to a target scene, and screening a standard phrase from each phrase set based on the target screening mode to obtain N standard phrases;
constructing a target knowledge base corresponding to the target scene based on the N phrase sets and the N standard phrases;
when a reference phrase input in the target scene is detected, determining a target phrase set corresponding to the reference phrase from the target knowledge base, and determining a target standard phrase in the target phrase set;
and performing auxiliary design on the reference phrase based on the target standard phrase, wherein the auxiliary design mode comprises at least one of phrase recommendation, phrase scoring and phrase replacement.
In one aspect, an embodiment of the present invention provides an aided design apparatus based on a knowledge base, where the apparatus includes:
an obtaining module for obtaining at least one phrase,
the clustering module is used for clustering the at least one phrase to obtain N phrase sets, wherein N is a positive integer;
the determining module is used for determining a target screening mode corresponding to a target scene;
the screening module is used for screening a standard phrase from each phrase set based on the target screening mode to obtain N standard phrases;
the construction module is used for constructing a target knowledge base corresponding to the target scene based on the N phrase sets and the N standard phrases;
the determining module is further configured to determine, when a reference phrase input in the target scene is detected, a target phrase set corresponding to the reference phrase from the target knowledge base, and determine a target standard phrase in the target phrase set;
and the auxiliary module is used for carrying out auxiliary design on the reference word group based on the target standard word group, wherein the auxiliary design mode comprises at least one of word group recommendation, word group grading and word group replacement.
In one aspect, an embodiment of the present invention provides a terminal, including a processor, an input interface, an output interface, and a memory, where the processor, the input interface, the output interface, and the memory are connected to each other, where the memory is used to store a computer program, and the computer program includes program instructions, and the processor is configured to call the program instructions to execute the data analysis-based questionnaire data processing method.
In one aspect, an embodiment of the present invention provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, where the computer program includes program instructions, and the program instructions, when executed by a processor, cause the processor to execute the knowledge-base-based aided design method.
In the embodiment of the invention, a terminal acquires at least one phrase, performs clustering processing on the at least one phrase to obtain N phrase sets, determines a target screening mode corresponding to a target scene, and screens out a standard phrase from each phrase set based on the target screening mode to obtain N standard phrases; constructing a target knowledge base corresponding to a target scene based on the N phrase sets and the N standard phrases; when a reference phrase input in a target scene is detected, determining a target phrase set corresponding to the reference phrase from a target knowledge base, and determining a target standard phrase in the target phrase set; and performing auxiliary design on the reference phrases based on the target standard phrase group. By implementing the method, a knowledge base can be constructed, and in the process of writing data by a user, the auxiliary design is carried out based on the knowledge base, so that the normative of the written data is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a knowledge-base-based aided design method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of another knowledge-base-based aided design method provided by the embodiment of the invention;
FIG. 3 is a schematic structural diagram of an aided design apparatus based on a knowledge base according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a terminal according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The auxiliary design method based on the knowledge base is realized on a terminal, and the terminal comprises electronic equipment such as a smart phone, a tablet computer, a digital audio and video player, an electronic reader, a handheld game machine or vehicle-mounted electronic equipment.
Fig. 1 is a schematic flow chart of an aided design method based on a knowledge base in an embodiment of the present invention, and as shown in fig. 1, the flow of the aided design method based on the knowledge base in the embodiment may include:
s101, obtaining at least one phrase, and clustering the at least one phrase to obtain N phrase sets.
In the embodiment of the present invention, the terminal may obtain at least one phrase from all phrases in the data source, where the data source includes a database, a data warehouse, a database lake, a data marsh, and the like, and optionally, the data source may include all phrases used by different users in a scenario, for example, all phrases used in a scenario of compiling an analysis report, all phrases used in a scenario of compiling a paper, and the like. After the terminal acquires at least one phrase, clustering the at least one phrase to obtain N phrase sets, wherein N is a positive integer; the clustering processing mode includes clustering based on semantics, clustering based on part of speech, or clustering based on data sources.
In an implementation manner, the clustering of the at least one phrase by the terminal includes clustering based on semantics, and specifically, the terminal determines semantic information of each phrase in the at least one phrase and clusters each phrase based on the semantic information of each phrase to obtain N phrase sets, where each phrase set includes phrases having the same semantic information. The terminal may determine semantic information of each phrase based on an encyclopedia tool, for example, if the semantic information of the phrase "school", and the phrase "college" are determined by the encyclopedia tool to be "mechanisms for planning, organizing, and leadingly performing system education", it is determined that the "school", and "college" have the same semantic information, and the "school", and "college" are categorized in the same set.
In an implementation manner, the clustering process performed on the at least one word group by the terminal includes clustering based on word vectors, specifically, the terminal calls a vectorization model to perform vectorization on the at least one word group to obtain the at least one word vector, calculates a distance between the word vectors, and classifies the word groups with the distance smaller than a preset distance into the same set, where the vectorization model may be obtained by pre-training, word groups with similar word senses, and after the processing of the warp-wise quantization model, the obtained distances between the word vectors are closer. Through the method, phrases with similar word senses can be grouped into one category.
In an implementation manner, the clustering of the at least one phrase by the terminal includes clustering based on the part of speech, specifically, the terminal determines the part of speech of each phrase in the at least one phrase, and clusters each phrase based on the part of speech of each phrase to obtain N phrase sets, each phrase set includes phrases with the same part of speech, wherein the part of speech includes verbs, nouns, adjectives, adverbs and the like.
In one implementation, the terminal may receive operation information input by a user for at least one phrase, and perform clustering processing on the at least one phrase based on the operation information, that is, perform clustering on the phrases based on manual operation.
S102, determining a target screening mode corresponding to the target scene, and screening a standard phrase from each phrase set based on the target screening mode to obtain N standard phrases.
In the embodiment of the invention, after the terminal obtains N phrase sets, a target screening mode corresponding to a target scene can be determined, and a standard phrase is screened from each phrase set based on the target screening mode to obtain N standard phrases. In a specific implementation, the target scenario may be a compiling scenario, which is specifically divided into a scenario for compiling a medical report, a scenario for compiling a financial analysis report, a scenario for compiling a test report, and the like, and standard descriptions of phrases are different in different scenarios, for example, a phrase "teacher" is a standard description in a scenario for compiling a baby text, and a phrase "teacher" is a standard description in a scenario for compiling an analysis report. Therefore, for different scenes, the corresponding modes for screening the standard descriptions from the phrase set are different, and therefore, the modes for screening the standard phrases are also different in different scenes.
In a specific implementation, the terminal may determine a target screening manner corresponding to the target scene based on a pre-established correspondence between the scene and the screening manner, where the target screening manner is used to screen out a standard phrase meeting the writing standard of the target scene from the phrase set. Further, the terminal screens out a standard phrase from each phrase set based on the target screening manner, and the following specifically explains a manner in which the terminal screens out a standard phrase from each phrase set based on the target screening manner in a manner that the terminal screens out a standard phrase from any one phrase set among the N phrase sets.
In an implementation manner, the target screening manner is to screen based on the occurrence frequency of the phrases in the target scene, and specifically, the phrase with the highest occurrence frequency in the target scene in each phrase set may be used as the standard phrase of each phrase set. The method for screening a standard phrase from a first phrase set by a terminal based on a target screening mode includes that the terminal obtains the occurrence frequency of each phrase in the first phrase set under a target scene, and screens out the phrase with the highest occurrence frequency from the first phrase set as the standard phrase in the first phrase set. For example, the first phrase set includes phrases "teacher", "teacher" and "teacher", the target scene is a scene for writing baby periodicals, the occurrence frequency of "teacher" is found to be 100, the occurrence frequency of "teacher" is found to be 5, the occurrence frequency of "teacher" is found to be 2 from each collected baby periodicals, it is determined that the phrase "teacher" occurs most frequently, and the standard phrase in the first phrase set is "teacher". For another example, the target scenario is a scenario for writing analysis reports, and if it is found from the collected analysis reports that the occurrence frequency of "teacher" is 10, the occurrence frequency of "teacher" is 500, and the occurrence frequency of "teacher" is 22, it is determined that the phrase "teacher" occurs most frequently, and the standard phrase in the first phrase set is "teacher". By the method, phrases meeting the standard description are screened from the phrase set by adopting different screening modes according to different scenes.
In one implementation, the target screening method is based on the source of the phrases in the target scene, specifically, the phrase having the highest priority source in each phrase set may be used as the standard phrase of each phrase set, specifically, for any one first phrase set in the N phrase sets, the method for the terminal to screen one standard phrase from the first phrase set based on the target screening method includes that the terminal determines the data source of each phrase in the first phrase set, determines the priority of each phrase based on the corresponding relationship between the data source and the priority, and uses the phrase having the highest priority as the standard phrase in the first phrase set, for example, the first phrase set includes phrase 1 and phrase 2, where the phrase 1 is from a national periodical, the phrase 2 is from a local dialect periodical, and the priority of the national periodical under the target scene is higher than the local dialect periodical, then phrase 1 is determined as the standard phrase in the first phrase set in the target scenario. In an implementation manner, the terminal may also comprehensively determine a target standard phrase based on the source and the frequency of occurrence of each phrase, for example, determine the weight of the phrase based on the source of the phrase, perform weighting processing on the frequency of occurrence by using the weight to obtain the weighted frequency of each phrase, and determine the phrase with the highest weighted frequency as the standard phrase.
In one implementation, the terminal may determine a target screening manner in a target scene based on an operation input by the user, that is, screen out a standard phrase from each set based on the operation input by the user.
S103, constructing a target knowledge base corresponding to the target scene based on the N phrase sets and the N standard phrases.
In the embodiment of the invention, after the terminal determines the N phrase sets and the standard phrases in each phrase set, a target knowledge base corresponding to a target scene is constructed based on the N phrase sets and the N standard phrases. In a specific implementation, the terminal may store the N phrase sets and the N standard phrases into the database, so as to obtain the target knowledge base.
In one implementation mode, the storage positions of different phrase sets in the database are determined by corresponding standard phrases, the specific way of constructing a target knowledge base corresponding to a target scene by the terminal based on the N phrase sets and the N standard phrases can be that the terminal determines the correlation between the N standard phrases and the target scene, and the correlation is determined by the occurrence frequency of the standard phrases in the target scene; determining a storage position corresponding to a phrase set where each standard phrase is located based on the correlation between each standard phrase and a target scene; and storing each phrase set in corresponding storage positions in a database to obtain a target knowledge base, wherein the phrase sets stored in different storage positions have different calling priorities. Specifically, the higher the correlation between the standard phrases in the phrase set and the target scene is, the higher the calling priority of the storage location corresponding to the phrase set is. By the method, the corresponding calling priority can be set for each phrase set based on the correlation between the standard phrases in the phrase sets and the target scene, so that phrases with higher priorities are preferentially called when the phrase calls conflict. Moreover, the relevance is determined by the occurrence frequency of the standard phrases in the target scene, namely, the calling priority of the set where the high-frequency phrases are located is higher, and the storage position where the phrase set with the higher priority is located can be queried more quickly, so that in the subsequent process of using the target knowledge base, the common data can be found from the target knowledge base more quickly, and the query efficiency of the data in the target knowledge base is improved.
In one implementation, the storage locations of different phrase sets in the database are determined by the relevance between standard phrases in different phrase sets, the specific way of the terminal for constructing a target knowledge base corresponding to a target scene based on N phrase sets and N standard phrases may be that, the terminal determines the relevance between the standard phrases in each phrase set, the relevance between different standard phrases is determined by the co-occurrence frequency of the standard phrases in the same text, for any first standard phrase in each phrase set, the specific way of the terminal determining the relevance between a second standard phrase and a first standard phrase in other phrase sets may be that, the terminal determines the occurrence frequency of the first standard phrase and the second standard phrase in the same text in the target scene, and determines the relevance between the first standard phrase and the second standard phrase according to the corresponding relationship between the occurrence frequency and the relevance, the more the co-occurrence frequency, the higher the correlation. Through the method, the terminal can determine the relevance between the standard phrases in each phrase set, further, the terminal determines the relevance between the standard phrases in each phrase set as the relevance between the phrase sets, the terminal randomly screens out one first phrase set from the N phrase sets to be stored at the first position in the database, and determines the distance between the storage of other N-1 phrase sets and the first position based on the relevance between the phrase sets, wherein the higher the relevance is, the closer the distance is. If the second phrase set with the highest relevance with the first phrase set is determined from other N-1 phrase sets, the second phrase set is stored at a second position adjacent to the first position in the database. By the method, the relevance between the phrase sets can be determined, the storage positions of the phrase sets are determined based on the relevance, the storage positions of the phrase sets with the larger relevance are close to each other, the storage positions of the phrase sets with the smaller relevance are far from each other, and in the subsequent data retrieval process of the target knowledge base, after one phrase set is retrieved, other phrase sets with the higher relevance to the phrase set can be quickly inquired, so that the data retrieval efficiency is improved.
And S104, when the reference phrase input in the target scene is detected, determining a target phrase set corresponding to the reference phrase from the target knowledge base, and determining a target standard phrase in the target phrase set.
In the embodiment of the invention, after the terminal constructs the target knowledge base corresponding to the target scene, the information input in the target scene can be detected, when the reference phrase input in the target scene is detected, the target phrase set corresponding to the reference phrase is determined from the target knowledge base, and the target standard phrase in the target phrase set is determined.
In an implementation manner, a specific manner of determining, by the terminal, a target phrase set corresponding to the reference phrase from the target knowledge base may be that the terminal determines a matching phrase matched with the reference phrase from the target knowledge base, where, when the reference phrase is stored in the target knowledge base, the matching phrase is the same as the reference phrase; when the target knowledge base stores the reference phrases, the phrases with the most similar meaning to the reference phrases are matched. And the terminal determines the phrase set where the matched phrases are located as a target phrase set corresponding to the reference phrase.
In an implementation manner, the specific manner in which the terminal determines the target phrase set corresponding to the reference phrase from the target knowledge base may be that the terminal determines a first word vector of the reference phrase and a second word vector of each phrase in the target knowledge base; calculating the distance between the first word vector and each second word vector, and determining a target second word vector which is closest to the first word vector; and determining the phrase corresponding to the target second word vector as a matching phrase matched with the reference phrase, and determining the phrase set in which the matching phrase is located as a target phrase set corresponding to the reference phrase.
In an embodiment, the terminal may determine the first word vector of the reference word group and the second word vector of each word group in the target knowledge base in a manner that the terminal may pre-establish a dictionary, in which correspondence between the word vectors and the word groups is stored, it is to be noted that word senses of the word groups in the dictionary are similar, distances between the word vectors of the word groups are also similar, when the word groups are the same, corresponding word vectors are also the same, and distances between the same word vectors are the closest. And the terminal carries out word vectorization processing on the reference word group and each word group in the target knowledge base based on the dictionary to obtain a first word vector and each second word vector. In a specific implementation, the terminal may obtain K phrases in a target scene in advance, and establish a K-dimensional vector dictionary based on the K phrases, where the phrases with similar meaning are similar in distance, and K may specifically be the number of all phrases in the network. For example, for 3 phrases "school", "college", "school", and "college" that are closer in word meaning, and "college" that are closer, the terminal may obtain a dictionary based on the above 3 phrases, where a word vector corresponding to "school" is "100", a word vector corresponding to "college" is "010", and a word vector corresponding to "college" is "001". After the terminal acquires the word group, the word vector corresponding to the word group is inquired based on the dictionary. The distance may specifically be a euclidean distance, a hamming distance, or the like, and is not limited herein, or a word vector model may be constructed and trained, so that the trained word vector model may output a word vector corresponding to each word group, and the closer the word senses are, the closer the word vector distance corresponding to the word group is, the terminal inputs the reference word group and each word group in the target knowledge base into the trained word vector model, and the word vector model outputs the first word vector and each second word vector.
Further, after the terminal determines a target phrase set corresponding to the reference phrase from the target knowledge base, a standard phrase, that is, a target standard phrase, in the target phrase set may be selected.
And S105, performing auxiliary design on the reference phrases based on the target standard phrase group.
In the embodiment of the invention, after the terminal determines the target standard phrase in the target phrase set, the terminal can perform auxiliary design on the reference phrase based on the target standard phrase, and the auxiliary design mode comprises at least one of phrase recommendation, phrase scoring and phrase replacement.
In an implementation manner, the auxiliary design manner includes phrase recommendation, and the manner of the terminal performing auxiliary design on the reference phrase based on the target standard phrase may be that the terminal recommends the target standard phrase in a display page where the reference phrase is located, so as to implement phrase recommendation on the reference phrase based on the target standard phrase. For example, if the reference phrase is "teacher" and the target standard phrase is "teacher", the terminal may recommend "teacher" on the display page. Optionally, the terminal may also display each phrase in the phrase set where the target standard phrase is located, so as to implement phrase recommendation on the reference phrase based on the target standard phrase. Optionally, the terminal may further display an association standard phrase having an association relationship with the target standard phrase to implement phrase recommendation on the reference phrase based on the target standard phrase, where the association relationship between the phrases may be set in the target knowledge base in advance by a developer.
In an implementation manner, the auxiliary design manner includes phrase scoring, and the terminal performs auxiliary design on the reference phrase based on the target standard phrase may be that the terminal determines a similarity between the target standard phrase and the reference phrase, and determines a score of the reference phrase based on a corresponding relationship between the similarity and the score, so as to implement phrase scoring on the reference phrase based on the target standard phrase. The calculation method of the similarity between the target standard phrase and the reference phrase may be to obtain the number of the same characters in the target standard phrase and the reference phrase and the total number of the characters in the reference phrase, and determine the ratio between the number of the same characters and the total number as the similarity between the target standard phrase and the reference phrase. For example, if the reference phrase is "teacher" and the target standard phrase is "teacher", the terminal determines that the ratio between the number of the same characters and the total number is 50%, that is, the similarity between the reference phrase and the target standard phrase is 50%, and further determines that the score of the reference phrase is 50 points based on the correspondence between the similarity and the score. Or determining a target word vector of the target standard phrase and a reference word vector of the reference phrase, and determining the similarity between the target phrase and the reference phrase based on the distance between the target word vector and the reference word vector, wherein the smaller the distance, the higher the similarity, for example, the similarity is the reciprocal of the distance. The correspondence between the similarity and the score may be set by a developer in advance, where the similarity is higher and the score is higher.
In an implementation manner, the auxiliary design manner includes phrase replacement, and the manner of the terminal performing auxiliary design on the reference phrase based on the target standard phrase may be that, when a selection operation input for the target standard phrase is received, the reference phrase is replaced with the target standard phrase, so as to implement phrase replacement on the reference phrase based on the target standard phrase. For example, if the reference phrase is "teacher" and the target standard phrase is "teacher", the terminal may replace the reference phrase "teacher" with the target standard phrase "teacher".
In one implementation mode, the auxiliary design mode comprises phrase scoring, phrase recommendation and phrase replacement, the mode of the terminal for auxiliary design of the reference phrase based on the target standard phrase can be that the terminal recommends the target standard phrase in a display page where the reference phrase is located so as to implement phrase recommendation of the reference phrase based on the target standard phrase; determining similarity between the target standard phrase and the reference phrase, and determining the score of the reference phrase based on the corresponding relation between the similarity and the score so as to realize phrase scoring on the reference phrase based on the target standard phrase; and when receiving a selection operation aiming at the recommended target standard phrase, replacing the reference phrase with the target standard phrase so as to realize phrase replacement of the reference phrase based on the target standard phrase.
In the embodiment of the invention, a terminal acquires at least one phrase, performs clustering processing on the at least one phrase to obtain N phrase sets, determines a target screening mode corresponding to a target scene, and screens out a standard phrase from each phrase set based on the target screening mode to obtain N standard phrases; constructing a target knowledge base corresponding to a target scene based on the N phrase sets and the N standard phrases; when a reference phrase input in a target scene is detected, determining a target phrase set corresponding to the reference phrase from a target knowledge base, and determining a target standard phrase in the target phrase set; and performing auxiliary design on the reference phrases based on the target standard phrase group. By implementing the method, a knowledge base can be constructed, and the auxiliary design is carried out based on the knowledge base in the data compiling process of the user, so that the data compiled by the user accords with the data specification, and the normalization of data compiling is improved.
Fig. 2 is a schematic flow chart of another knowledge-base-based aided design method in the embodiment of the present invention, and as shown in fig. 2, the flow of the knowledge-base-based aided design method in the embodiment may include:
s201, obtaining at least one phrase, and determining semantic information of each phrase in the at least one phrase.
In the embodiment of the present invention, the terminal may obtain all phrases stored in the database to obtain at least one phrase, the terminal may determine semantic information of each phrase in the at least one phrase, and the semantic information may be a definition of the phrase, for example, for the phrase "school", a corresponding definition of the phrase is "an organization performing system education with planning, organization and leadership". Alternatively, the semantic information may be other language expressions of the phrase, such as "school" for the phrase, and its corresponding english expression is "school". Optionally, the phrase in the present scheme may also be a program code, and then the semantic information of the phrase is the annotation of the phrase.
S202, clustering each phrase based on semantic information of each phrase to obtain N phrase sets, wherein each phrase set comprises phrases with the same semantic information.
In the embodiment of the invention, after the terminal determines the semantic information of each phrase, the terminal can perform clustering processing on each phrase based on the semantic information of each phrase to obtain N phrase sets, wherein each phrase set comprises phrases with the same semantic information. For example, if the phrase "school" and the phrase "college" are both "planned, organized, and leadership organizations for system education" as determined by an encyclopedia tool, the "school" and the "college" are put into the same collection, i.e., grouped into one category. Or, determining that the English expressions of the phrase "school" and the phrase "college" are both "school" through an encyclopedia tool, and putting the "school" and the "college" into the same set, namely, grouping the words into one group. For another example, if program code 1 and program code 2 are both used to create an object, then program code 1 and program code 2 may be put into the same collection, i.e., grouped into a class, where program code 1 and program code 2 may be code written in different languages.
S203, determining a target screening mode corresponding to the target scene, and screening a standard phrase from each phrase set based on the target screening mode to obtain N standard phrases.
In the embodiment of the invention, after the terminal obtains N phrase sets, a target screening mode corresponding to a target scene can be determined, and a standard phrase is screened from each phrase set based on the target screening mode to obtain N standard phrases. In specific implementation, the target scene may be a compiling scene, which is specifically divided into a scene for compiling a medical report, a scene for compiling a financial analysis report, a scene for compiling a test report, a scene for compiling a book, and the like, and the standard descriptions of the phrases in the scenes are different for different scenes, for example, for a scene for compiling a book for a baby, the phrase "teacher" is the standard description, and for a scene for compiling an analysis report, the phrase "teacher" is the standard description. Therefore, for different scenes, the corresponding modes for screening the standard descriptions from the phrase set are different, and therefore, the modes for screening the standard phrases are also different in different scenes. For a target scene, the terminal may determine a target screening manner corresponding to the target scene, and screen out a standard phrase from each phrase set based on the target screening manner, where the standard phrase is a standard description in the target scene.
And S204, constructing a target knowledge base corresponding to the target scene based on the N phrase sets and the N standard phrases.
In the embodiment of the invention, after the terminal determines the N phrase sets and the standard phrases in each phrase set, a target knowledge base corresponding to a target scene is constructed based on the N phrase sets and the N standard phrases. In a specific implementation, the terminal may store the N phrase sets and the N standard phrases into the database, so as to obtain the target knowledge base.
S205, when the reference phrase input in the target scene is detected, determining a target phrase set corresponding to the reference phrase from the target knowledge base, and determining a target standard phrase in the target phrase set.
In the embodiment of the invention, after the terminal constructs the target knowledge base corresponding to the target scene, the information input in the target scene can be detected, when the reference phrase input in the target scene is detected, the target phrase set corresponding to the reference phrase is determined from the target knowledge base, and the target standard phrase in the target phrase set is determined.
And S206, performing auxiliary design on the reference phrases based on the target standard phrase group.
In the embodiment of the invention, after the terminal determines the target standard phrase in the target phrase set, the terminal can perform auxiliary design on the reference phrase based on the target standard phrase, and the auxiliary design mode comprises at least one of phrase recommendation, phrase scoring and phrase replacement.
And S207, if the reference phrase does not exist in the target knowledge base, checking whether a matching phrase having the same semantic information as the reference phrase exists in the target knowledge base.
In the embodiment of the invention, aiming at a reference phrase input by a user, the terminal can check whether the reference phrase exists in the target knowledge base, and if the reference phrase does not exist, the target knowledge base can be updated based on the reference phrase. The specific updating method may be that the terminal checks whether a matching phrase having the same semantic information as the reference phrase exists in the target knowledge base, if so, performs step S208, and if not, performs step S209. In specific implementation, the terminal can obtain semantic information of each phrase in the target indication library and semantic information of the reference phrase, and if a phrase with the same semantic information as the reference phrase exists in the target knowledge library, the phrase is determined as a matching phrase matched with the reference phrase. For example, if the reference phrase is "college", the semantic information of which is "institution performing system education", and the phrase "college" is stored in the target knowledge base, and the semantic information of which is also "institution performing system education", the terminal determines "school" as a matching phrase having the same semantic information as the reference phrase.
And S208, if the matched phrase exists, adding the reference phrase into the phrase set where the matched phrase is located.
In the embodiment of the invention, after the terminal determines that the target knowledge base has the matching phrase with the same semantic information as the reference phrase, the reference phrase can be added into the phrase set where the matching phrase is located, so as to update the target knowledge base.
S209, if no matching phrase exists, a new phrase set is created in the target knowledge base, and the reference phrase is added to the new phrase set.
In the embodiment of the invention, after the terminal determines that the target knowledge base does not have the matching phrase with the same semantic information as the reference phrase, a new phrase set can be created in the target knowledge base, and the reference phrase is added into the new phrase set, so that the target knowledge base is updated.
In the embodiment of the invention, a terminal acquires at least one phrase, performs clustering processing on the at least one phrase to obtain N phrase sets, determines a target screening mode corresponding to a target scene, and screens out a standard phrase from each phrase set based on the target screening mode to obtain N standard phrases; constructing a target knowledge base corresponding to a target scene based on the N phrase sets and the N standard phrases; when a reference phrase input in a target scene is detected, determining a target phrase set corresponding to the reference phrase from a target knowledge base, and determining a target standard phrase in the target phrase set; and performing auxiliary design on the reference phrases based on the target standard phrase group, and updating the target knowledge base based on the reference phrases. By implementing the method, the knowledge base can be constructed, and the auxiliary design is carried out based on the knowledge base in the process of writing data by the user, so that the data written by the user accords with the data specification, the normalization of writing data is improved, the input data can be continuously received, the automatic update of the knowledge base is realized, and the update efficiency of the knowledge base is improved.
The knowledge-base-based aided design apparatus provided by the embodiment of the present invention will be described in detail with reference to fig. 3. It should be noted that the knowledge base-based aided design apparatus shown in fig. 3 is used for executing the method of the embodiment of the present invention shown in fig. 1-2, for convenience of description, only the portion related to the embodiment of the present invention is shown, and specific technical details are not disclosed, and reference is made to the embodiment of the present invention shown in fig. 1-2.
Referring to fig. 3, a schematic structural diagram of an auxiliary design device based on a knowledge base according to the present invention is shown, where the auxiliary design device 30 based on a knowledge base includes: an acquisition module 301, a clustering module 302, a determination module 303, a screening module 304, a construction module 305, and an assistance module 306.
An obtaining module 301, configured to obtain at least one phrase,
a clustering module 302, configured to perform clustering processing on the at least one phrase to obtain N phrase sets, where N is a positive integer;
a determining module 303, configured to determine a target screening manner corresponding to a target scene;
a screening module 304, configured to screen one standard phrase from each phrase set based on the target screening manner, so as to obtain N standard phrases;
a building module 305, configured to build a target knowledge base corresponding to the target scene based on the N phrase sets and the N standard phrases;
the determining module 303 is further configured to determine, when a reference phrase input in the target scene is detected, a target phrase set corresponding to the reference phrase from the target knowledge base, and determine a target standard phrase in the target phrase set;
an auxiliary module 306, configured to perform auxiliary design on the reference phrase based on the target standard phrase, where the auxiliary design manner includes at least one of phrase recommendation, phrase scoring, and phrase replacement.
In an implementation, the clustering module 302 is specifically configured to:
determining semantic information of each phrase in the at least one phrase;
and clustering each phrase based on the semantic information of each phrase to obtain N phrase sets, wherein each phrase set comprises phrases with the same semantic information.
In an implementation manner, the target screening manner includes screening based on the occurrence frequency of the phrases in the target scene, and the screening module 304 is specifically configured to:
acquiring the occurrence frequency of each phrase in the first phrase set under a target scene;
and screening out the phrases with the highest frequency of occurrence from the first phrase set as standard phrases in the first phrase set.
In one implementation, the building module 305 is specifically configured to:
determining the correlation between the N standard phrases and the target scene, wherein the correlation is determined by the occurrence frequency of the standard phrases in the target scene;
determining a storage position corresponding to a phrase set where each standard phrase is located in a database based on the correlation between each standard phrase and the target scene;
and storing each phrase set in corresponding storage positions in the database to obtain a target knowledge base, wherein the phrase sets stored in different storage positions have different calling priorities.
In an implementation manner, the determining module 303 is specifically configured to:
determining a first word vector of the reference word group and a second word vector of each word group in the target knowledge base;
calculating the distance between the first word vector and each second word vector, and determining a target second word vector closest to the first word vector;
and determining the phrase corresponding to the target second word vector as a matching phrase matched with the reference phrase, and determining the phrase set in which the matching phrase is located as a target phrase set corresponding to the reference phrase.
In an implementation manner, the auxiliary module 306 is specifically configured to:
recommending the target standard word group in a display page where the reference word group is located so as to realize word group recommendation of the reference word group based on the target standard word group;
determining similarity between the target standard word group and the reference word group, and determining the grade of the reference word group based on the corresponding relation between the similarity and the grade so as to realize the word group grade of the reference word group based on the target standard word group;
and when receiving a selection operation aiming at the recommended target standard phrase, replacing the reference phrase with the target standard phrase so as to realize phrase replacement of the reference phrase based on the target standard phrase.
In one implementation, the auxiliary module 306 is further configured to:
if the reference phrase does not exist in the target knowledge base, checking whether a matching phrase having the same semantic information as the reference phrase exists in the target knowledge base;
if the matched phrase exists, adding the reference phrase into a phrase set where the matched phrase is located;
and if the matched phrase does not exist, creating a new phrase set in the target knowledge base, and adding the reference phrase into the new phrase set.
In the embodiment of the present invention, an obtaining module 301 obtains at least one phrase, a clustering module 302 performs clustering processing on the at least one phrase to obtain N phrase sets, a determining module 303 determines a target screening manner corresponding to a target scene, and a screening module 304 screens out a standard phrase from each phrase set based on the target screening manner to obtain N standard phrases; the construction module 305 constructs a target knowledge base corresponding to the target scene based on the N phrase sets and the N standard phrases; when a reference phrase input in a target scene is detected, the determining module 303 determines a target phrase set corresponding to the reference phrase from the target knowledge base, and determines a target standard phrase in the target phrase set; the assisting module 306 performs an assisting design on the reference phrase based on the target standard phrase set. By implementing the method, a knowledge base can be constructed, and in the process of writing data by a user, the auxiliary design is carried out based on the knowledge base, so that the normative of the written data is improved.
Fig. 4 is a schematic structural diagram of a terminal according to an embodiment of the present invention. As shown in fig. 4, the terminal includes: at least one processor 401, input devices 403, output devices 404, memory 405, at least one communication bus 402. Wherein a communication bus 402 is used to enable connective communication between these components. The input device 403 may be a control panel or a microphone, and the output device 404 may be a display screen. The memory 405 may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one disk memory. The memory 405 may alternatively be at least one storage device located remotely from the aforementioned processor 401. Wherein the processor 401 may be combined with the apparatus described in fig. 3, the memory 405 stores a set of program codes, and the processor 401, the input device 403, and the output device 404 call the program codes stored in the memory 405 to perform the following operations:
the processor 401 is configured to obtain at least one phrase, and perform clustering on the at least one phrase to obtain N phrase sets, where N is a positive integer;
the processor 401 is configured to determine a target screening manner corresponding to a target scene, and screen out one standard phrase from each phrase set based on the target screening manner to obtain N standard phrases;
a processor 401, configured to construct a target knowledge base corresponding to the target scene based on the N phrase sets and the N standard phrases;
a processor 401, configured to determine, when a reference phrase input in the target scene is detected, a target phrase set corresponding to the reference phrase from the target knowledge base, and determine a target standard phrase in the target phrase set;
a processor 401, configured to perform an auxiliary design on the reference phrase based on the target standard phrase, where the auxiliary design includes at least one of a phrase recommendation, a phrase score, and a phrase replacement.
In one implementation, the processor 401 is specifically configured to:
determining semantic information of each phrase in the at least one phrase;
and clustering each phrase based on the semantic information of each phrase to obtain N phrase sets, wherein each phrase set comprises phrases with the same semantic information.
In one implementation, the processor 401 is specifically configured to:
acquiring the occurrence frequency of each phrase in the first phrase set under a target scene;
and screening out the phrases with the highest frequency of occurrence from the first phrase set as standard phrases in the first phrase set.
In one implementation, the processor 401 is specifically configured to:
determining the correlation between the N standard phrases and the target scene, wherein the correlation is determined by the occurrence frequency of the standard phrases in the target scene;
determining a storage position corresponding to a phrase set where each standard phrase is located in a database based on the correlation between each standard phrase and the target scene;
and storing each phrase set in corresponding storage positions in the database to obtain a target knowledge base, wherein the phrase sets stored in different storage positions have different calling priorities.
In one implementation, the processor 401 is specifically configured to:
determining a first word vector of the reference word group and a second word vector of each word group in the target knowledge base;
calculating the distance between the first word vector and each second word vector, and determining a target second word vector closest to the first word vector;
and determining the phrase corresponding to the target second word vector as a matching phrase matched with the reference phrase, and determining the phrase set in which the matching phrase is located as a target phrase set corresponding to the reference phrase.
In one implementation, the processor 401 is specifically configured to:
recommending the target standard word group in a display page where the reference word group is located so as to realize word group recommendation of the reference word group based on the target standard word group;
determining similarity between the target standard word group and the reference word group, and determining the grade of the reference word group based on the corresponding relation between the similarity and the grade so as to realize the word group grade of the reference word group based on the target standard word group;
and when receiving a selection operation aiming at the recommended target standard phrase, replacing the reference phrase with the target standard phrase so as to realize phrase replacement of the reference phrase based on the target standard phrase.
In one implementation, the processor 401 is specifically configured to:
if the reference phrase does not exist in the target knowledge base, checking whether a matching phrase having the same semantic information as the reference phrase exists in the target knowledge base;
if the matched phrase exists, adding the reference phrase into a phrase set where the matched phrase is located;
and if the matched phrase does not exist, creating a new phrase set in the target knowledge base, and adding the reference phrase into the new phrase set.
In the embodiment of the present invention, the processor 401 obtains at least one phrase, performs clustering processing on the at least one phrase to obtain N phrase sets, determines a target screening manner corresponding to a target scene, and screens a standard phrase from each phrase set based on the target screening manner to obtain N standard phrases; constructing a target knowledge base corresponding to a target scene based on the N phrase sets and the N standard phrases; when a reference phrase input in a target scene is detected, determining a target phrase set corresponding to the reference phrase from a target knowledge base, and determining a target standard phrase in the target phrase set; and performing auxiliary design on the reference phrases based on the target standard phrase group. By implementing the method, a knowledge base can be constructed, and in the process of writing data by a user, the auxiliary design is carried out based on the knowledge base, so that the normative of the written data is improved.
The module in the embodiment of the present invention may be implemented by a general-purpose Integrated Circuit, such as a CPU (central Processing Unit), or an ASIC (application Specific Integrated Circuit).
It should be understood that, in the embodiments of the present invention, the Processor 401 may be a Central Processing Unit (CPU), and the Processor may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The bus 402 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like, and the bus 402 may be divided into an address bus, a data bus, a control bus, and the like, where fig. 4 only shows one thick line for convenience of illustration, but does not show only one bus or one type of bus.
It will be understood by those skilled in the art that all or part of the processes of the methods of the above embodiments may be implemented by a computer program, which may be stored in a computer storage medium and may include the processes of the embodiments of the methods described above when executed. The computer storage medium may be a magnetic disk, an optical disk, a Read-only Memory (ROM), a Random Access Memory (RAM), or the like.
The computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism and an encryption algorithm. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is therefore to be understood that the invention is not limited by the scope of the appended claims.
Claims (10)
1. An aided design method based on a knowledge base is characterized by comprising the following steps:
acquiring at least one phrase, and clustering the at least one phrase to obtain N phrase sets, wherein N is a positive integer;
determining a target screening mode corresponding to a target scene, and screening a standard phrase from each phrase set based on the target screening mode to obtain N standard phrases;
constructing a target knowledge base corresponding to the target scene based on the N phrase sets and the N standard phrases;
when a reference phrase input in the target scene is detected, determining a target phrase set corresponding to the reference phrase from the target knowledge base, and determining a target standard phrase in the target phrase set;
and performing auxiliary design on the reference phrase based on the target standard phrase, wherein the auxiliary design mode comprises at least one of phrase recommendation, phrase scoring and phrase replacement.
2. The method according to claim 1, wherein the clustering process includes clustering the at least one phrase based on semantic clustering, and obtaining N phrase sets includes:
determining semantic information of each phrase in the at least one phrase;
and clustering each phrase based on the semantic information of each phrase to obtain N phrase sets, wherein each phrase set comprises phrases with the same semantic information.
3. The method according to claim 1, wherein the target screening means includes screening based on the occurrence frequency of phrases in a target scene, and the means for screening a phrase from any one first phrase set among N phrase sets based on the target screening means as a standard phrase in the phrase set includes:
acquiring the occurrence frequency of each phrase in the first phrase set under a target scene;
and screening out the phrases with the highest frequency of occurrence from the first phrase set as standard phrases in the first phrase set.
4. The method of claim 1, wherein the constructing a target knowledge base corresponding to the target scene based on the N phrase sets and the N standard phrases comprises:
determining the correlation between the N standard phrases and the target scene, wherein the correlation is determined by the occurrence frequency of the standard phrases in the target scene;
determining a storage position corresponding to a phrase set where each standard phrase is located in a database based on the correlation between each standard phrase and the target scene;
and storing each phrase set in corresponding storage positions in the database to obtain a target knowledge base, wherein the phrase sets stored in different storage positions have different calling priorities.
5. The method according to any one of claims 1 to 4, wherein the determining the target phrase set corresponding to the reference phrase from the target knowledge base includes:
determining a first word vector of the reference word group and a second word vector of each word group in the target knowledge base;
calculating the distance between the first word vector and each second word vector, and determining a target second word vector closest to the first word vector;
and determining the phrase corresponding to the target second word vector as a matching phrase matched with the reference phrase, and determining the phrase set in which the matching phrase is located as a target phrase set corresponding to the reference phrase.
6. The method of claim 1, wherein the auxiliary design manner includes phrase recommendation, phrase scoring and phrase replacement, and the auxiliary design of the reference phrase based on the target standard phrase includes:
recommending the target standard word group in a display page where the reference word group is located so as to realize word group recommendation of the reference word group based on the target standard word group;
determining similarity between the target standard word group and the reference word group, and determining the grade of the reference word group based on the corresponding relation between the similarity and the grade so as to realize the word group grade of the reference word group based on the target standard word group;
and when receiving a selection operation aiming at the recommended target standard phrase, replacing the reference phrase with the target standard phrase so as to realize phrase replacement of the reference phrase based on the target standard phrase.
7. The method of claim 2, wherein after the aided design of the reference phrase based on the target standard phrase, the method further comprises:
if the reference phrase does not exist in the target knowledge base, checking whether a matching phrase having the same semantic information as the reference phrase exists in the target knowledge base;
if the matched phrase exists, adding the reference phrase into a phrase set where the matched phrase is located;
and if the matched phrase does not exist, creating a new phrase set in the target knowledge base, and adding the reference phrase into the new phrase set.
8. A knowledge-base-based aided design apparatus, the apparatus comprising:
an obtaining module for obtaining at least one phrase,
the clustering module is used for clustering the at least one phrase to obtain N phrase sets, wherein N is a positive integer;
the determining module is used for determining a target screening mode corresponding to a target scene;
the screening module is used for screening a standard phrase from each phrase set based on the target screening mode to obtain N standard phrases;
the construction module is used for constructing a target knowledge base corresponding to the target scene based on the N phrase sets and the N standard phrases;
the determining module is further configured to determine, when a reference phrase input in the target scene is detected, a target phrase set corresponding to the reference phrase from the target knowledge base, and determine a target standard phrase in the target phrase set;
and the auxiliary module is used for carrying out auxiliary design on the reference word group based on the target standard word group, wherein the auxiliary design mode comprises at least one of word group recommendation, word group grading and word group replacement.
9. A terminal, comprising a processor, an input interface, an output interface, and a memory, the processor, the input interface, the output interface, and the memory being interconnected, wherein the memory is configured to store a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the method of any of claims 1-7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program comprising program instructions that, when executed by a processor, cause the processor to carry out the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011643855.8A CN112733492B (en) | 2020-12-31 | 2020-12-31 | Knowledge base-based aided design method and device, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011643855.8A CN112733492B (en) | 2020-12-31 | 2020-12-31 | Knowledge base-based aided design method and device, terminal and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112733492A true CN112733492A (en) | 2021-04-30 |
| CN112733492B CN112733492B (en) | 2022-05-03 |
Family
ID=75609234
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011643855.8A Active CN112733492B (en) | 2020-12-31 | 2020-12-31 | Knowledge base-based aided design method and device, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112733492B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160092549A1 (en) * | 2014-09-26 | 2016-03-31 | International Business Machines Corporation | Information Handling System and Computer Program Product for Deducing Entity Relationships Across Corpora Using Cluster Based Dictionary Vocabulary Lexicon |
| CN107590124A (en) * | 2017-09-06 | 2018-01-16 | 陈飞 | The method replaced to synonym by scene and compared according to the standard phrase sorted out by scene |
| CN108664595A (en) * | 2018-05-08 | 2018-10-16 | 和美（深圳）信息技术股份有限公司 | Domain knowledge base construction method, device, computer equipment and storage medium |
| CN108804414A (en) * | 2018-05-04 | 2018-11-13 | 科沃斯商用机器人有限公司 | Text modification method, device, smart machine and readable storage medium storing program for executing |
| CN109033162A (en) * | 2018-06-19 | 2018-12-18 | 深圳市元征科技股份有限公司 | A kind of data processing method, server and computer-readable medium |
| CN110969008A (en) * | 2019-12-03 | 2020-04-07 | 北京中科院软件中心有限公司 | Method and system for converting processing procedure description sentences into triple structures |
| CN111931477A (en) * | 2020-09-29 | 2020-11-13 | 腾讯科技（深圳）有限公司 | Text matching method and device, electronic equipment and storage medium |
| CN111950729A (en) * | 2020-07-19 | 2020-11-17 | 中国建设银行股份有限公司 | Knowledge base construction method and device, electronic equipment and readable storage device |
-
2020
- 2020-12-31 CN CN202011643855.8A patent/CN112733492B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160092549A1 (en) * | 2014-09-26 | 2016-03-31 | International Business Machines Corporation | Information Handling System and Computer Program Product for Deducing Entity Relationships Across Corpora Using Cluster Based Dictionary Vocabulary Lexicon |
| CN107590124A (en) * | 2017-09-06 | 2018-01-16 | 陈飞 | The method replaced to synonym by scene and compared according to the standard phrase sorted out by scene |
| CN108804414A (en) * | 2018-05-04 | 2018-11-13 | 科沃斯商用机器人有限公司 | Text modification method, device, smart machine and readable storage medium storing program for executing |
| CN108664595A (en) * | 2018-05-08 | 2018-10-16 | 和美（深圳）信息技术股份有限公司 | Domain knowledge base construction method, device, computer equipment and storage medium |
| CN109033162A (en) * | 2018-06-19 | 2018-12-18 | 深圳市元征科技股份有限公司 | A kind of data processing method, server and computer-readable medium |
| CN110969008A (en) * | 2019-12-03 | 2020-04-07 | 北京中科院软件中心有限公司 | Method and system for converting processing procedure description sentences into triple structures |
| CN111950729A (en) * | 2020-07-19 | 2020-11-17 | 中国建设银行股份有限公司 | Knowledge base construction method and device, electronic equipment and readable storage device |
| CN111931477A (en) * | 2020-09-29 | 2020-11-13 | 腾讯科技（深圳）有限公司 | Text matching method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 刘贯昂: "基于深度学习的农业生产智能问答系统的研究与开发", 《中国硕士电子期刊》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112733492B (en) | 2022-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108647205B (en) | Fine-grained emotion analysis model construction method and device and readable storage medium | |
| CN109635298B (en) | Group state identification method and device, computer equipment and storage medium | |
| CN112215008B (en) | Entity identification method, device, computer equipment and medium based on semantic understanding | |
| CN111680159A (en) | Data processing method and device and electronic equipment | |
| CN111930792B (en) | Labeling method and device for data resources, storage medium and electronic equipment | |
| US11651015B2 (en) | Method and apparatus for presenting information | |
| US9632998B2 (en) | Claim polarity identification | |
| US11966698B2 (en) | System and method for automatically tagging customer messages using artificial intelligence models | |
| CN111767714B (en) | Text smoothness determination method, device, equipment and medium | |
| CN112579733A (en) | Rule matching method, rule matching device, storage medium and electronic equipment | |
| CN116402166B (en) | Training method and device of prediction model, electronic equipment and storage medium | |
| CN117390170B (en) | Method and device for matching data standards, electronic equipment and readable storage medium | |
| CN112559725A (en) | Text matching method, device, terminal and storage medium | |
| CN116796730A (en) | Text error correction method, device, equipment and storage medium based on artificial intelligence | |
| CN114141384A (en) | Method, apparatus and medium for retrieving medical data | |
| CN112559711B (en) | Synonymous text prompting method and device and electronic equipment | |
| CN112529743B (en) | Contract element extraction method, device, electronic equipment and medium | |
| CN112632956A (en) | Text matching method, device, terminal and storage medium | |
| CN109684467A (en) | A kind of classification method and device of text | |
| CN110750967B (en) | Pronunciation labeling method and device, computer equipment and storage medium | |
| CN112527967A (en) | Text matching method, device, terminal and storage medium | |
| CN110287270B (en) | Entity relationship mining method and equipment | |
| Putri et al. | Software feature extraction using infrequent feature extraction | |
| CN112733492B (en) | Knowledge base-based aided design method and device, terminal and storage medium | |
| CN113792230B (en) | Service linking method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220525 Address after: 518000 China Aviation Center 2901, No. 1018, Huafu Road, Huahang community, Huaqiang North Street, Futian District, Shenzhen, Guangdong Province Patentee after: Shenzhen Ping An medical and Health Technology Service Co.,Ltd. Address before: Room 12G, Area H, 666 Beijing East Road, Huangpu District, Shanghai 200001 Patentee before: PING AN MEDICAL AND HEALTHCARE MANAGEMENT Co.,Ltd. |