CN113946657A - Knowledge reasoning-based automatic identification method for power service intention - Google Patents
Knowledge reasoning-based automatic identification method for power service intention Download PDFInfo
- Publication number
- CN113946657A CN113946657A CN202111233832.4A CN202111233832A CN113946657A CN 113946657 A CN113946657 A CN 113946657A CN 202111233832 A CN202111233832 A CN 202111233832A CN 113946657 A CN113946657 A CN 113946657A
- Authority
- CN
- China
- Prior art keywords
- retrieval
- text
- expansion
- data
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000004458 analytical method Methods 0.000 claims abstract description 31
- 230000011218 segmentation Effects 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 17
- 238000013473 artificial intelligence Methods 0.000 claims description 16
- 230000002787 reinforcement Effects 0.000 claims description 7
- 238000012163 sequencing technique Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 3
- 230000003190 augmentative effect Effects 0.000 claims description 2
- 238000012360 testing method Methods 0.000 description 6
- 238000003062 neural network model Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a knowledge reasoning-based automatic identification method for power business intentions, which belongs to the technical field of power industry and comprises the following specific steps: the method comprises the following steps: acquiring a keyword retrieval module and a keyword expansion module, and performing keyword retrieval by a user through the keyword retrieval module to obtain a plurality of retrieval texts; a user performs keyword expansion through a keyword expansion module to obtain an expansion text; step two: analyzing the extended text and the retrieval text by utilizing a cosine similarity function to obtain a retrieval text most similar to the extended text, and marking the corresponding retrieval text as an analysis text; step three: acquiring user information and a user history retrieval record, and integrating and marking the user information, the user history retrieval record and the analysis text as intention analysis data; step four: and acquiring an intention analysis model, and inputting intention analysis data into the intention analysis model to acquire the user retrieval purpose.
Description
Technical Field
The invention belongs to the technical field of power industry, and particularly relates to a knowledge reasoning-based automatic identification method for power business intentions.
Background
The power business is various, the data carried by different businesses are inconsistent, and the related application content is updated quickly. At present, a client message source and a channel are blocked and single, a consultation and handling of the power service can be performed only through an incoming call visiting form, and the consultation and handling of the power service are easily limited by service personnel, such as service capability, working state and the like, so that the understanding of the intention of the client is deviated, the repeated labor of the client is caused, and the experience of the client is influenced, and therefore, a method for automatically identifying the intention of the power service based on knowledge reasoning is urgently needed to be provided for solving the problem that the intention of the user cannot be accurately known.
Disclosure of Invention
In order to solve the problems existing in the scheme, the invention provides a power service intention automatic identification method based on knowledge reasoning.
The purpose of the invention can be realized by the following technical scheme:
a knowledge reasoning-based automatic identification method for power service intention comprises the following specific steps:
the method comprises the following steps: acquiring a keyword retrieval module and a keyword expansion module, and performing keyword retrieval by a user through the keyword retrieval module to obtain a plurality of retrieval texts; a user performs keyword expansion through a keyword expansion module to obtain an expansion text;
step two: analyzing the extended text and the retrieval text by utilizing a cosine similarity function to obtain a retrieval text most similar to the extended text, and marking the corresponding retrieval text as an analysis text;
step three: acquiring user information and a user history retrieval record, and integrating and marking the user information, the user history retrieval record and the analysis text as intention analysis data;
step four: and acquiring an intention analysis model, and inputting intention analysis data into the intention analysis model to acquire the user retrieval purpose.
Further, the keyword retrieval module in the first step is used for retrieving according to the keyword, and the specific method comprises the following steps:
setting a voice recognition node, obtaining a keyword input by a user, describing the keyword through the voice recognition node, recognizing the content described by the voice of the user, establishing a retrieval model, marking the keyword and the content described by the user as retrieval input data, inputting the retrieval input data into the retrieval model to obtain a retrieval formula, and performing content retrieval in a database according to the retrieval formula to obtain a retrieval text.
Further, the acquisition reinforcement learning unit feeds back the content retrieved by using the retrieval formula of the retrieval model through the reinforcement learning unit, and relearns the retrieval model according to the feedback result.
Further, acquiring recorded data searched according to a search formula, setting a rating table according to the searched recorded data, sending the rating table to a corresponding user for evaluation, when the rating is qualified, not performing operation, when the rating is unqualified, acquiring corresponding recorded data, modifying the search formula, integrating the modified search formula and corresponding input data into self-learning data, and inputting the self-learning data into a search model for relearning.
Further, in the first step, the keyword expansion module is used for text expansion according to the keywords, and the specific method comprises the following steps:
collecting electric power text data, segmenting the electric power text data to generate segmented data, preprocessing the segmented data, extracting core words in the segmented data, integrating and marking the segmented data and the corresponding core words as sentence expansion training set data, acquiring an artificial intelligence model, training the artificial intelligence model through the sentence expansion training set data, marking the trained artificial intelligence model as a sentence expansion model, identifying key words input by a user, acquiring a word division library, inputting the key words into the word division library to obtain a word expansion formula, inputting the word expansion formula into the sentence expansion model to obtain a plurality of expansion sentences, and sequencing the expansion sentences according to heuristic rules to form text data; the text data is marked as augmented text.
Further, the method for acquiring the word segmentation library comprises the following steps:
establishing a word segmentation database, acquiring core words extracted from segmented data, acquiring the probability of the core words appearing in different power text data, establishing a word expansion model, inputting the core words, the probability of the core words appearing in the different power text data and the power text data into the word expansion model, and acquiring word expansion formulas, direction words and corresponding word expansion formula classification descriptions; and storing the word expansion formula, the direction words and the corresponding word expansion formula classification descriptions into a word segmentation database, wherein a matching unit is arranged in the word segmentation database and is used for matching the keywords input into the word segmentation database.
Further, the method for obtaining the word expansion formula comprises the following steps:
the method comprises the steps of inputting keywords into a word segmentation database, matching the keywords with stored directional words by a matching unit, obtaining corresponding word expansion formulas and word expansion formula classification descriptions according to the matched directional words, sequencing the obtained word expansion formulas and word expansion formula classification descriptions, establishing a word expansion formula description table, sending the word expansion formula description table to a user, and selecting the word expansion formulas meeting the requirements of the user in the word expansion formula description table.
Further, the user history retrieval record is retrieval data within a current D month, wherein D is a positive integer, and the value range of D is [1,3 ].
Compared with the prior art, the invention has the beneficial effects that: the method comprises the steps of obtaining an expanded text and a retrieval text according to keywords, and obtaining an analysis text which can be most close to the user intention by comparing the expanded text with the retrieval text, so that the subsequent judgment of the user intention is more accurate, and the defect of analyzing through a single expanded text or retrieval text is overcome by combining the two aspects; by the method, the intention of the user about the power business can be accurately known, and corresponding countermeasures can be made by the corresponding power enterprises.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, a method for automatically identifying an electric power service intention based on knowledge inference specifically includes:
the method comprises the following steps: acquiring a keyword retrieval module and a keyword expansion module, and performing keyword retrieval by a user through the keyword retrieval module to obtain a plurality of retrieval texts; a user performs keyword expansion through a keyword expansion module to obtain an expansion text;
step two: analyzing the extended text and the retrieval text by utilizing a cosine similarity function to obtain a retrieval text most similar to the extended text, and marking the corresponding retrieval text as an analysis text;
the method comprises the steps of obtaining an expanded text and a retrieval text according to keywords, and obtaining an analysis text which can be most close to the user intention by comparing the expanded text with the retrieval text, so that the subsequent judgment of the user intention is more accurate, and the defect of analyzing through a single expanded text or retrieval text is overcome by combining the two aspects;
step three: acquiring user information and a user history retrieval record, wherein the user information comprises information such as user industry, user occupation, user position and the like; the user history retrieval record is retrieval data within D months from the current time, wherein D is a positive integer and the value range of D is [1,3], and the retrieval data is equivalent to data browsed by a user according to a retrieval result; integrating and marking the user information, the user history retrieval records and the analysis texts as intention analysis data;
step four: acquiring an intention analysis model, and inputting intention analysis data into the intention analysis model to acquire a user retrieval purpose;
the keyword retrieval module in the first step is used for retrieving according to the keywords, and the specific method comprises the following steps:
the method comprises the steps of setting a voice recognition node, wherein the voice recognition node is used for recognizing voice content of a user, acquiring keywords input by the user, further describing the keywords through the voice recognition node, limiting a retrieval range through further describing the keywords, avoiding the problem that writing is difficult because some thought dictations are easy to write, recognizing the content described by the voice of the user, establishing a retrieval model, marking the keywords and the content described by the user as retrieval input data, inputting the retrieval input data into the retrieval model to obtain a retrieval formula, and retrieving the content in a database according to the retrieval formula to obtain a retrieval text;
the acquisition reinforcement learning unit feeds back the content searched by using the search formula of the search model through the reinforcement learning unit, and relearns the search model according to the feedback result;
the working method of the reinforcement learning unit comprises the following steps:
acquiring recorded data searched according to a search formula, setting a rating table according to the searched recorded data, sending the rating table to a corresponding user for evaluation, when the rating is qualified, not performing operation, when the rating is unqualified, acquiring corresponding recorded data, modifying the search formula, integrating the modified search formula and corresponding input data into self-learning data, and inputting the self-learning data into a search model for relearning;
the retrieval model acquisition specifically comprises the following steps: obtaining historical retrieval data, wherein the historical retrieval data comprises keywords and user narrative content, setting a retrieval formula for the historical retrieval data, and constructing an artificial intelligence model, wherein the artificial intelligence model is a neural network model; dividing historical retrieval data and corresponding retrieval formulas into a training set, a test set and a check set; training, testing and verifying the artificial intelligent model through a training set, a testing set and a verifying set; marking the trained artificial intelligence model as a retrieval model;
the method comprises the following steps that a keyword expansion module is used for text expansion according to keywords, and the specific method comprises the following steps:
collecting electric power text data, segmenting the electric power text data to generate segmented data, wherein the segmented data are sentences in the electric power text data, are equivalent to one sentence, and can be segmented according to paragraphs and sentence numbers; performing data preprocessing on the segmented data, wherein the data preprocessing comprises cleaning and extracting the data, and extracting core words in the segmented data, and the segmented data is the data subjected to the data preprocessing; extracting keywords is a conventional technology and is not an improvement point of the method, so that detailed description is not needed, and a neural network model can be used for training; integrating and marking the segmented data and the corresponding core words as sentence expansion training set data to obtain an artificial intelligence model, wherein the artificial intelligence model is a neural network model; training an artificial intelligence model through sentence expansion training set data, marking the trained artificial intelligence model as a sentence expansion model, expanding input keywords into sentences, identifying the keywords input by a user, obtaining a word segmentation library, inputting the keywords into the word segmentation library to obtain a word expansion formula, inputting the word expansion formula into the sentence expansion model to obtain a plurality of expansion sentences, and sequencing the expansion sentences according to heuristic rules to form text data; heuristic rules are common knowledge in the art and are therefore not described in detail; marking the text data as an expanded text;
the method for acquiring the word segmentation library comprises the following steps:
establishing a word segmentation database, acquiring core words extracted from segmented data, acquiring the probability of the core words appearing in different electric power text data, namely the proportion of the number of times of the different core words appearing in the electric power text data, wherein the probability is equivalent to the probability of the key word A, B, C, D, E, F appearing simultaneously, establishing a word expansion model, wherein the word expansion model is a neural network model, and training is performed through the probability of the core words and the core words appearing in the different electric power text data, the electric power text data and correspondingly set word expansion formulas, direction words and word expansion formula classification descriptions; inputting the core words, the probability of the core words appearing in different electric power text data and the electric power text data into a word expansion type model to obtain word expansion types, direction words and corresponding word expansion type classification descriptions; the word expansion type classification description is the content of which category the word expansion type belongs to according to the word expansion type and the corresponding electric power text data analysis; the directional words are words which can represent the word expansion formula most in the word expansion formula, the directional words and corresponding word expansion formula classification descriptions are stored in a word segmentation database, a matching unit is arranged in the word segmentation database, and the matching unit is used for matching keywords input into the word segmentation database.
The method for obtaining the word expansion formula comprises the following steps:
the method comprises the steps of inputting keywords into a word segmentation database, matching the keywords with stored directional words by a matching unit, obtaining corresponding word expansion formulas and word expansion formula classification descriptions according to the matched directional words, sequencing the obtained word expansion formulas and word expansion formula classification descriptions, arranging the sequencing sequence according to the sequence of time, size and the like, establishing a word expansion formula description table, wherein the word expansion formula description table is a table established according to the sequenced word expansion formulas and word expansion formula classification descriptions, sending the word expansion formula description table to a user, and selecting the word expansion formulas meeting the requirements of the user in the word expansion formula description table.
The method for acquiring the intention analysis model in the fourth step comprises the following steps: acquiring historical analysis data, wherein the historical retrieval data comprises user information, user historical retrieval records and analysis texts, setting a corresponding user retrieval purpose for the historical retrieval data, and constructing an artificial intelligence model, wherein the artificial intelligence model is a neural network model; dividing historical analysis data and corresponding user retrieval purposes into a training set, a test set and a check set; training, testing and verifying the artificial intelligent model through a training set, a testing set and a verifying set; marking the trained artificial intelligence model as an intention analysis model;
in the second step, the cosine similarity function is used for analyzing and comparing the two articles, and the similarity is judged to be common knowledge in the field, such as similarity comparison of course interest;
construction of cosine similarity function
Wherein i and j are interestingness vectors of student i and student j respectively; the smaller the included angle between i and j is, the higher the similarity is; the interestingness vector may include: the number of times of course visit, the learning duration of the course, the course score and the like; the student can grade any course through the human-computer interaction interface; the course score is the score given to any course by the student;
illustratively, the format of the interestingness vector is a triple (x1, x2, x3), and the interestingness function of the student is determined according to the access record, the learning duration and the course score:
wherein alpha is1、α2、α3To adjust the coefficient, α1、α2、α3Has a value range of [0, 1 ]]F, t and r are respectively the access times, the learning duration and the course score of the student; the access times, the learning duration and the course score are respectively set as initial values and values read from a database;
fij represents the access times of the user i to the course resource j, fmin is the minimum access time recorded in the database, and fmax is the maximum access time recorded in the database; tij is the learning duration of the user i on the course resource j, tmax is the maximum learning duration recorded in the database, and tmin is the minimum learning duration recorded in the database; rij is the course score for i for course resource j; rmax is the maximum curriculum score recorded in the database; rmin is the minimum curriculum score recorded in the database;
adjustment factor alpha1、α2、α3Can be within a specified range, i.e., [0, 1 ]]Random numbers are generated, after which the coefficients are optimized by genetic algorithms.
The above formulas are all calculated by removing dimensions and taking numerical values thereof, the formula is a formula which is obtained by acquiring a large amount of data and performing software simulation to obtain the closest real situation, and the preset parameters and the preset threshold value in the formula are set by the technical personnel in the field according to the actual situation or obtained by simulating a large amount of data.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and there may be other divisions when the actual implementation is performed; the modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the method of the embodiment.
It will also be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above examples are only intended to illustrate the technical process of the present invention and not to limit the same, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that modifications or equivalent substitutions may be made to the technical process of the present invention without departing from the spirit and scope of the technical process of the present invention.
Claims (8)
1. A knowledge reasoning-based automatic identification method for power service intention is characterized by comprising the following specific steps:
the method comprises the following steps: acquiring a keyword retrieval module and a keyword expansion module, and performing keyword retrieval by a user through the keyword retrieval module to obtain a plurality of retrieval texts; a user performs keyword expansion through a keyword expansion module to obtain an expansion text;
step two: analyzing the extended text and the retrieval text by utilizing a cosine similarity function to obtain a retrieval text most similar to the extended text, and marking the corresponding retrieval text as an analysis text;
step three: acquiring user information and a user history retrieval record, and integrating and marking the user information, the user history retrieval record and the analysis text as intention analysis data;
step four: and acquiring an intention analysis model, and inputting intention analysis data into the intention analysis model to acquire the user retrieval purpose.
2. The method for automatically identifying the power service intention based on the knowledge inference as claimed in claim 1, wherein a keyword retrieval module in the first step is used for retrieving according to keywords, and the specific method comprises the following steps:
setting a voice recognition node, obtaining a keyword input by a user, describing the keyword through the voice recognition node, recognizing the content described by the voice of the user, establishing a retrieval model, marking the keyword and the content described by the user as retrieval input data, inputting the retrieval input data into the retrieval model to obtain a retrieval formula, and performing content retrieval in a database according to the retrieval formula to obtain a retrieval text.
3. The method for automatically identifying the power business intention based on the knowledge inference as claimed in claim 2, wherein the obtaining reinforcement learning unit feeds back the content of the retrieval by using the retrieval formula of the retrieval model through the reinforcement learning unit, and relearns the retrieval model according to the feedback result.
4. The method for automatically identifying power service intention based on knowledge inference as claimed in claim 3, wherein the recorded data retrieved according to a search formula is obtained, a scoring table is set according to the retrieved recorded data, the scoring table is sent to a corresponding user for evaluation, when the scoring is qualified, no operation is performed, when the scoring is unqualified, the corresponding recorded data is obtained, the search formula is modified, the modified search formula and the corresponding input data are integrated into self-learning data, and the self-learning data is input into a search model for relearning.
5. The method for automatically identifying the power service intention based on the knowledge inference as claimed in claim 1, wherein in the first step, the keyword expansion module is used for text expansion according to keywords, and the specific method comprises the following steps:
collecting electric power text data, segmenting the electric power text data to generate segmented data, preprocessing the segmented data, extracting core words in the segmented data, integrating and marking the segmented data and the corresponding core words as sentence expansion training set data, acquiring an artificial intelligence model, training the artificial intelligence model through the sentence expansion training set data, marking the trained artificial intelligence model as a sentence expansion model, identifying key words input by a user, acquiring a word division library, inputting the key words into the word division library to obtain a word expansion formula, inputting the word expansion formula into the sentence expansion model to obtain a plurality of expansion sentences, and sequencing the expansion sentences according to heuristic rules to form text data; the text data is marked as augmented text.
6. The method for automatically identifying the power service intention based on the knowledge inference as claimed in claim 5, wherein the method for obtaining the word segmentation library comprises the following steps:
establishing a word segmentation database, acquiring core words extracted from segmented data, acquiring the probability of the core words appearing in different power text data, establishing a word expansion model, inputting the core words, the probability of the core words appearing in the different power text data and the power text data into the word expansion model, and acquiring word expansion formulas, direction words and corresponding word expansion formula classification descriptions; and storing the word expansion formula, the direction words and the corresponding word expansion formula classification descriptions into a word segmentation database, wherein a matching unit is arranged in the word segmentation database and is used for matching the keywords input into the word segmentation database.
7. The method for automatically identifying the power service intention based on the knowledge inference as claimed in claim 5, wherein the method for obtaining the word expansion formula comprises:
the method comprises the steps of inputting keywords into a word segmentation database, matching the keywords with stored directional words by a matching unit, obtaining corresponding word expansion formulas and word expansion formula classification descriptions according to the matched directional words, sequencing the obtained word expansion formulas and word expansion formula classification descriptions, establishing a word expansion formula description table, sending the word expansion formula description table to a user, and selecting the word expansion formulas meeting the requirements of the user in the word expansion formula description table.
8. The method for automatically identifying the power service intention based on the knowledge inference as claimed in claim 1, wherein the historical retrieval records of the user are retrieval data within D months from the current time, wherein D is a positive integer, and the value range of D is [1,3 ].
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111233832.4A CN113946657A (en) | 2021-10-22 | 2021-10-22 | Knowledge reasoning-based automatic identification method for power service intention |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111233832.4A CN113946657A (en) | 2021-10-22 | 2021-10-22 | Knowledge reasoning-based automatic identification method for power service intention |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113946657A true CN113946657A (en) | 2022-01-18 |
Family
ID=79332293
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111233832.4A Pending CN113946657A (en) | 2021-10-22 | 2021-10-22 | Knowledge reasoning-based automatic identification method for power service intention |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113946657A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116804691A (en) * | 2023-06-28 | 2023-09-26 | 国网安徽省电力有限公司青阳县供电公司 | Fault monitoring method for dispatching automation equipment of power system |
| CN117540107A (en) * | 2024-01-09 | 2024-02-09 | 浙江同花顺智能科技有限公司 | Data processing method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104598445A (en) * | 2013-11-01 | 2015-05-06 | 腾讯科技（深圳）有限公司 | Automatic question-answering system and method |
| CN109344336A (en) * | 2018-12-25 | 2019-02-15 | 北京时光荏苒科技有限公司 | Searching method, search set creation method, device, medium, terminal and server |
| CN111177351A (en) * | 2019-12-20 | 2020-05-19 | 北京淇瑀信息科技有限公司 | Method, device and system for acquiring natural language expression intention based on rule |
| CN111444722A (en) * | 2020-03-06 | 2020-07-24 | 中国平安人寿保险股份有限公司 | Intent classification method, device, equipment and storage medium based on voting decision |
| CN111858936A (en) * | 2020-07-21 | 2020-10-30 | 龙马智芯（珠海横琴）科技有限公司 | Intention identification method and device, identification equipment and readable storage medium |
-
2021
- 2021-10-22 CN CN202111233832.4A patent/CN113946657A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104598445A (en) * | 2013-11-01 | 2015-05-06 | 腾讯科技（深圳）有限公司 | Automatic question-answering system and method |
| CN109344336A (en) * | 2018-12-25 | 2019-02-15 | 北京时光荏苒科技有限公司 | Searching method, search set creation method, device, medium, terminal and server |
| CN111177351A (en) * | 2019-12-20 | 2020-05-19 | 北京淇瑀信息科技有限公司 | Method, device and system for acquiring natural language expression intention based on rule |
| CN111444722A (en) * | 2020-03-06 | 2020-07-24 | 中国平安人寿保险股份有限公司 | Intent classification method, device, equipment and storage medium based on voting decision |
| CN111858936A (en) * | 2020-07-21 | 2020-10-30 | 龙马智芯（珠海横琴）科技有限公司 | Intention identification method and device, identification equipment and readable storage medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116804691A (en) * | 2023-06-28 | 2023-09-26 | 国网安徽省电力有限公司青阳县供电公司 | Fault monitoring method for dispatching automation equipment of power system |
| CN116804691B (en) * | 2023-06-28 | 2024-02-13 | 国网安徽省电力有限公司青阳县供电公司 | Fault monitoring method for dispatching automation equipment of power system |
| CN117540107A (en) * | 2024-01-09 | 2024-02-09 | 浙江同花顺智能科技有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN117540107B (en) * | 2024-01-09 | 2024-05-07 | 浙江同花顺智能科技有限公司 | Data processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Neculoiu et al. | Learning text similarity with siamese recurrent networks | |
| CN106570708B (en) | Management method and system of intelligent customer service knowledge base | |
| CN112667794A (en) | Intelligent question-answer matching method and system based on twin network BERT model | |
| CN111444344B (en) | Entity classification method, entity classification device, computer equipment and storage medium | |
| CN109299271A (en) | Training sample generation, text data, public sentiment event category method and relevant device | |
| CN108549647B (en) | Method for realizing active prediction of emergency in mobile customer service field without marking corpus based on SinglePass algorithm | |
| CN111414479A (en) | Label extraction method based on short text clustering technology | |
| CN113094578B (en) | Deep learning-based content recommendation method, device, equipment and storage medium | |
| CN109446423B (en) | System and method for judging sentiment of news and texts | |
| CN113505586A (en) | Seat-assisted question-answering method and system integrating semantic classification and knowledge graph | |
| CN113946657A (en) | Knowledge reasoning-based automatic identification method for power service intention | |
| CN109710766B (en) | Complaint tendency analysis early warning method and device for work order data | |
| CN110046264A (en) | A kind of automatic classification method towards mobile phone document | |
| Verma et al. | A novel approach for text summarization using optimal combination of sentence scoring methods | |
| CN112685550A (en) | Intelligent question answering method, device, server and computer readable storage medium | |
| CN115659947A (en) | Multi-item selection answering method and system based on machine reading understanding and text summarization | |
| CN116070599A (en) | Intelligent question bank generation and auxiliary management system | |
| CN110362828B (en) | Network information risk identification method and system | |
| CN116628173A (en) | Intelligent customer service information generation system and method based on keyword extraction | |
| CN115577080A (en) | Question reply matching method, system, server and storage medium | |
| CN112668284B (en) | Legal document segmentation method and system | |
| CN112434126B (en) | Information processing method, device, equipment and storage medium | |
| CN112579666A (en) | Intelligent question-answering system and method and related equipment | |
| CN113095073A (en) | Corpus tag generation method and device, computer equipment and storage medium | |
| CN113821571A (en) | Food safety relation extraction method based on BERT and improved PCNN |
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 |