CN109635287A - Method, apparatus, computer equipment and the storage medium of policy dynamics analysis - Google Patents
Method, apparatus, computer equipment and the storage medium of policy dynamics analysis Download PDFInfo
- Publication number
- CN109635287A CN109635287A CN201811431271.7A CN201811431271A CN109635287A CN 109635287 A CN109635287 A CN 109635287A CN 201811431271 A CN201811431271 A CN 201811431271A CN 109635287 A CN109635287 A CN 109635287A
- Authority
- CN
- China
- Prior art keywords
- policy
- dimension
- emotion
- processed
- words
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000008451 emotion Effects 0.000 claims abstract description 272
- 238000004590 computer program Methods 0.000 claims description 32
- 238000012545 processing Methods 0.000 claims description 12
- 238000005194 fractionation Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 11
- 239000000284 extract Substances 0.000 description 3
- 239000000203 mixture Substances 0.000 description 2
- 230000007935 neutral effect Effects 0.000 description 2
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
This application involves big data technical fields, provide method, apparatus, computer equipment and the storage medium of a kind of policy dynamics analysis.The described method includes: obtaining the emotion dictionary of preset each policy type, obtain policy data to be processed, determine goal and policy type corresponding with the policy type of policy data to be processed, according to the emotion dictionary of preset each policy type, determine the emotion dictionary of goal and policy type, the score that policy data to be processed is determined according to the emotion dictionary of goal and policy type determines policy dynamics according to the score of policy data to be processed.It can realize that the policy dynamics based on sentiment analysis is analyzed in the sphere of policy using this method.
Description
Technical field
This application involves big data technical fields, method, apparatus, computer more particularly to a kind of analysis of policy dynamics
Equipment and storage medium.
Background technique
With the development of big data technology, there is sentiment analysis technology.Sentiment analysis is referred to emotional color
Subjective texts analyzed, handled, being concluded and the process of reasoning, the meaning according to expressed by text and emotion information will be literary
Originally it is divided into and praises or two or more types of derogatory sense.
Sentiment analysis technology can be applied to multiple scenes, but for policy area, currently used sentiment analysis technology without
Method meet demand.
Summary of the invention
Based on this, it is necessary to which in view of the above technical problems, providing one kind can realize in the sphere of policy based on sentiment analysis
Policy dynamics analysis method, apparatus, computer equipment and storage medium.
A kind of method of policy dynamics analysis, which comprises
Obtain the emotion dictionary of preset each policy type；
Policy data to be processed is obtained, determines goal and policy type corresponding with the policy type of policy data to be processed；
According to the emotion dictionary of preset each policy type, the emotion dictionary of goal and policy type is determined；
The score that policy data to be processed is determined according to the emotion dictionary of goal and policy type, according to policy data to be processed
Score, determine policy dynamics.
In one of the embodiments, before the emotion dictionary for obtaining preset each policy type, comprising:
Obtain the seed words of history policy data set, preset policy dimension and preset policy dimension；
According to the seed words of policy dimension, traversal history policy data set determines the emotion set of words of each policy dimension；
According to preset standards of grading, point of each policy dimension emotion word in the emotion set of words of each policy dimension is determined
Number；
According to the emotion set of words of each policy dimension, the emotion dictionary of policy type corresponding with each policy dimension is generated.
In one of the embodiments, according to the seed words of policy dimension, traversal history policy data set determines each political affairs
The emotion set of words of plan dimension includes:
The word in history policy data set is obtained, and generates term vector corresponding with word；
The determining first kind word with the term vector distance of the seed words of policy dimension within the scope of preset distance threshold
Set；
According to the seed words of policy dimension and first kind set of words, traversal history policy data set determines each policy
The emotion set of words of dimension；
Wherein, according to the seed words of policy dimension and first kind set of words, traversal history policy data set is determined each
The emotion set of words of policy dimension includes:
History policy data in history policy data set is split as complete sentence；
Complete language according to the first kind word in the seed words of policy dimension and first kind set of words, after traversal fractionation
Sentence, determines object statement；
The frequency of occurrence for counting each word in object statement determines that frequency of occurrence is greater than the word work of preset frequency threshold value
For the second class word；
According to the second class word, the second class set of words is determined；
According to first kind set of words and the second class set of words, the emotion set of words of each policy dimension is determined.
In one of the embodiments, according to preset standards of grading, determine each in the emotion set of words of each policy dimension
The score of policy dimension emotion word includes:
Determine the seed words of each policy dimension emotion word and corresponding policy dimension in the emotion set of words of each policy dimension
Between term vector distance；
According to term vector distance and preset standards of grading, each policy dimension in the emotion set of words of each policy dimension is determined
The score of emotion word.
In one of the embodiments, according to the emotion set of words of each policy dimension, generate corresponding with each policy dimension
The emotion dictionary of policy type includes:
According to the preset policy type identification that each policy dimension carries, policy class corresponding with each policy dimension is determined
Type；
Generate the emotion dictionary of policy type corresponding with each policy dimension；
By the emotion set of words of each policy dimension, it is stored in the emotion dictionary of policy type corresponding with each policy dimension.
Policy data to be processed, the determining policy type with policy data to be processed are obtained in one of the embodiments,
Corresponding goal and policy type includes:
Policy data to be processed is obtained, the feature of policy data to be processed is extracted；
According to the preset property data base of the characteristic matching of policy data to be processed, the policy of policy data to be processed is determined
Type；
According to the policy type of policy data to be processed, preset policy types of database, determining and political affairs to be processed are matched
The corresponding goal and policy type of the policy type of plan data.
Point of policy data to be processed is determined according to the emotion dictionary of goal and policy type in one of the embodiments,
Number, according to the score of policy data to be processed, the policy dynamics of determination includes:
According to the policy dimension emotion word in the emotion dictionary of goal and policy type, policy data to be processed is traversed；
The number that policy dimension emotion word in statistics emotion dictionary occurs in policy data to be processed；
According to the number of appearance, the score of policy data to be processed is determined；
According to the score of policy data to be processed, policy dynamics is determined.
A kind of device of policy dynamics analysis, described device include:
First obtains module, for obtaining the emotion dictionary of preset each policy type；
Second obtains module, for obtaining policy data to be processed, the determining policy type pair with policy data to be processed
The goal and policy type answered；
First processing module determines the feelings of goal and policy type for the emotion dictionary according to preset each policy type
Feel dictionary；
Second processing module determines the score of policy data to be processed for the emotion dictionary according to goal and policy type,
According to the score of policy data to be processed, policy dynamics is determined.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device performs the steps of when executing the computer program
Obtain the emotion dictionary of preset each policy type；
Policy data to be processed is obtained, determines goal and policy type corresponding with the policy type of policy data to be processed；
According to the emotion dictionary of preset each policy type, the emotion dictionary of goal and policy type is determined；
The score that policy data to be processed is determined according to the emotion dictionary of goal and policy type, according to policy data to be processed
Score, determine policy dynamics.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It is performed the steps of when row
Obtain the emotion dictionary of preset each policy type；
Policy data to be processed is obtained, determines goal and policy type corresponding with the policy type of policy data to be processed；
According to the emotion dictionary of preset each policy type, the emotion dictionary of goal and policy type is determined；
The score that policy data to be processed is determined according to the emotion dictionary of goal and policy type, according to policy data to be processed
Score, determine policy dynamics.
Method, apparatus, computer equipment and the storage medium of above-mentioned policy dynamics analysis, obtain preset each policy type
Emotion dictionary, obtain policy data to be processed, determine goal and policy class corresponding with the policy type of policy data to be processed
Type determines the emotion dictionary of goal and policy type, determines policy data to be processed according to the emotion dictionary of goal and policy type
Score determines policy dynamics according to the score of policy data to be processed, in the sphere of policy, is determined by emotion dictionary to be processed
The score of policy determines policy dynamics according to the score of policy to be processed, is commented by score realization the numeralization of policy dynamics
Valence realizes the policy dynamics analysis based on sentiment analysis.
Detailed description of the invention
Fig. 1 is the application scenario diagram of the method for policy dynamics analysis in one embodiment；
Fig. 2 is the flow diagram of the method for policy dynamics analysis in one embodiment；
The flow diagram for the step of Fig. 3 is before step S202 in Fig. 2 in one embodiment；
The sub-process schematic diagram that Fig. 4 is step S304 in Fig. 3 in one embodiment；
The sub-process schematic diagram that Fig. 5 is step S406 in Fig. 4 in one embodiment；
The sub-process schematic diagram that Fig. 6 is step S306 in Fig. 3 in one embodiment；
The sub-process schematic diagram that Fig. 7 is step S308 in Fig. 3 in one embodiment；
The sub-process schematic diagram that Fig. 8 is step S204 in Fig. 2 in one embodiment；
The sub-process schematic diagram that Fig. 9 is step S208 in Fig. 2 in one embodiment；
Figure 10 is the structural block diagram of the device of policy dynamics analysis in one embodiment；
Figure 11 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
The method of policy dynamics analysis provided by the present application, can be applied in application environment as shown in Figure 1.Wherein,
Terminal 102 is communicated with server 104 by network by network.Server 104 obtains the feelings of preset each policy type
Feel dictionary, obtain policy data to be processed, determines goal and policy type corresponding with the policy type of policy data to be processed, root
According to the emotion dictionary of preset each policy type, the emotion dictionary of goal and policy type is determined, according to the feelings of goal and policy type
Sense dictionary determines that the score of policy data to be processed determines policy dynamics, push wait locate according to the score of policy data to be processed
The score and policy dynamics for managing policy data are to terminal 102.Wherein, terminal 102 can be, but not limited to be various individual calculus
Machine, laptop, smart phone, tablet computer and portable wearable device, server 104 can use independent server
The either server cluster of multiple servers composition is realized.
In one embodiment, as shown in Fig. 2, providing a kind of method of policy dynamics analysis, it is applied in this way
It is illustrated for server in Fig. 1, comprising the following steps:
S202: the emotion dictionary of preset each policy type is obtained.
The emotion dictionary of each policy type refers to the emotion set of words of each policy dimension corresponding with each policy type
Set, each policy type and each policy dimension can be voluntarily correspondingly arranged as required, in the emotion set of words of each policy dimension
Including multiple according to scheduled standards of grading, the policy dimension emotion word of score is determined.
S204: obtaining policy data to be processed, determines goal and policy corresponding with the policy type of policy data to be processed
Type.
Server obtains policy data to be processed, the policy type of policy data to be processed is determined, according to policy to be processed
The preset policy types of database of the policy type matching of data determines mesh corresponding with the policy type of policy data to be processed
Mark policy type.
S206: according to the emotion dictionary of preset each policy type, the emotion dictionary of goal and policy type is determined.
Preset each policy type is traversed according to goal and policy type, finds policy class corresponding with goal and policy type
Type, and then determine the emotion dictionary of goal and policy type.
S208: determining the score of policy data to be processed according to the emotion dictionary of goal and policy type, according to political affairs to be processed
The score of plan data determines policy dynamics.
Server determines the emotion dictionary of goal and policy type, according to goal and policy according to corresponding goal and policy type
Policy dimension emotion word in the emotion dictionary of type, traverses policy data to be processed, according to policy dimension feelings in emotion dictionary
The number that sense word occurs in policy data to be processed, determines the score of policy data to be processed, according to policy data to be processed
Score, determine policy dynamics.Wherein, the number occurred according to policy dimension emotion word determines point of policy data to be processed
Number includes: to determine political affairs to be processed according to the score of policy dimension emotion word, the number of appearance and preset number Weight algorithm
The score of plan data.It is corresponding according to preset number Weight algorithm when the number that policy dimension emotion word occurs is more
Score also can be higher, and preset number Weight algorithm can self-setting as required.
The method of above-mentioned policy dynamics analysis, obtains the emotion dictionary of preset each policy type, obtains policy to be processed
Data determine goal and policy type corresponding with the policy type of policy data to be processed, determine the emotion of goal and policy type
Dictionary determines the score of policy data to be processed according to the emotion dictionary of goal and policy type, according to policy data to be processed
Score determines policy dynamics, in the sphere of policy, the score of policy to be processed is determined by emotion dictionary, according to policy to be processed
Score, determine policy dynamics, realized by score and the numeralization of policy dynamics is evaluated, realize the policy based on sentiment analysis
Dynamics analysis.
In one of the embodiments, as shown in figure 3, before S202, comprising:
S302: the seed words of history policy data set, preset policy dimension and preset policy dimension are obtained.
History policy data set refers to the set for the published policy data collected, what preset policy dimension referred to
It is policy direction, different policy types has different policy directions, and the seed words of policy dimension refer to illustrate policy
The word of the policy dynamics in direction.For example, when policy type is financial policy, it is right if policy dimension is interest rate policy
The seed words for the policy dimension answered can be rise or drop, if policy dimension is monetary policy, corresponding policy dimension
Seed words can be steady, loose and deflation.
S304: according to the seed words of policy dimension, traversal history policy data set determines the emotion word of each policy dimension
Set.
It include policy dimension emotion word in the emotion set of words of each policy dimension, policy dimension emotion word refers to and policy
The word of the corresponding policy dynamics that can embody policy direction of the seed words of dimension.Server obtains in history policy data set
Word, and corresponding with word term vector is generated, according to the seed words of policy dimension, traversal history policy data set, root
According to each word in history policy data set and the seed words of policy dimension term vector distance and jointly appear in it is same
Number in sentence determines the policy dimension emotion word of each policy dimension, and then according to the policy dimension emotion of each policy dimension
Word determines the emotion set of words of each policy dimension.For example, when the seed words of policy dimension are steady, in policy data
In with the steadily and surely word that occurs jointly may be neutral, reasonable, balanced and substantially etc..
S306: according to preset standards of grading, each policy dimension emotion word in the emotion set of words of each policy dimension is determined
Score.
Server determines that each policy dimension emotion word is tieed up with corresponding policy in the emotion set of words of each policy dimension first
Term vector distance between the seed words of degree determines the feelings of each policy dimension according to term vector distance and preset standards of grading
Feel the score of word.Wherein, preset standards of grading can self-setting as required.
S308: according to the emotion set of words of each policy dimension, the emotion of policy type corresponding with each policy dimension is generated
Dictionary.
Each policy dimension carries preset policy type identification, and server can carry default according to each policy dimension
Policy type identification, determine corresponding with each policy dimension policy type, generation policy type corresponding with each policy dimension
Emotion dictionary the emotion set of words of each policy dimension is stored in the emotion dictionary of policy type corresponding with each policy dimension.
Wherein, the preset policy type identification that each policy dimension carries is according to the policy type in preset policy types of database
Determining, each policy dimension has corresponding policy type, can determine policy dimension according to preset policy type identification
The policy type of ownership.For example, monetary policy and interest rate policy just carry the preset policy type mark of financial policy
Know.
Below by one embodiment, to illustrate the scheme of the application.
Server obtains the emotion dictionary of preset each policy type, obtains policy data to be processed, it is determining with it is to be processed
The corresponding goal and policy type of the policy type of policy data is financial policy, according to the emotion word of preset each policy type
Library obtains the emotion dictionary of financial policy, the score of policy data to be processed is determined according to the emotion dictionary of financial policy, according to
The score of policy data to be processed, determines the policy dynamics of financial policy, financial policy may for the financial policy that tightens or
Slack fiscal policy.Wherein, the emotion dictionary of each policy type can be generated by following steps: obtain history financial policy
Data acquisition system, preset policy dimension are monetary policy, and waehrungspolitisch seed words are " steady ", according to the seed of policy dimension
Word " steady ", traversal history policy data set determine waehrungspolitisch emotion set of words, in waehrungspolitisch emotion set of words
Including often appeared in jointly with " steady " word " neutrality " in history financial policy data acquisition system, " reasonable ", " balanced " with
And the words such as " basic " determine the score of each policy dimension emotion word, according to waehrungspolitisch feelings according to preset standards of grading
Feel set of words, generates the emotion dictionary of financial policy corresponding with monetary policy.
In one of the embodiments, as shown in figure 4, S304 includes:
S402: the word in history policy data set is obtained, and generates term vector corresponding with word；
S404: the determining first kind with the term vector distance of the seed words of policy dimension within the scope of preset distance threshold
Set of words；
S406: according to the seed words of policy dimension and first kind set of words, traversal history policy data set is determined each
The emotion set of words of policy dimension.
Server obtains the word in history policy data set, and generates term vector corresponding with word, according to policy
The term vector of the seed words of dimension and the term vector of the word in history policy data set are determined in history policy data collection
In the word of conjunction, with the first kind word collection of the term vector distances of the seed words of policy dimension within the scope of preset distance threshold
It closes, according to the seed words of policy dimension and first kind set of words, traversal history policy data set determines each policy dimension
Emotion set of words.Wherein, preset distance threshold range can self-setting as required, in the emotion set of words of each policy dimension
Seed words and first kind set of words including policy dimension.
Above-described embodiment, according to each word in the term vector of the seed words of policy dimension and history policy data set
Term vector, realizes the acquisition to first kind set of words, and then according to the seed words of first kind set of words and policy dimension,
Traversal history policy data set realizes the acquisition of the emotion word to each policy dimension.
In one of the embodiments, as shown in figure 5, S406 includes:
S502: the history policy data in history policy data set is split as complete sentence；
S504: according to the first kind word in the seed words of policy dimension and first kind set of words, after traversal is split
Complete sentence determines object statement；
S506: the frequency of occurrence of each word in statistics object statement determines that frequency of occurrence is greater than preset frequency threshold value
Word is as the second class word；
S508: according to the second class word, the second class set of words is determined；
S510: according to first kind set of words and the second class set of words, the emotion set of words of each policy dimension is determined.
History policy data in history policy data set is split as complete sentence by server, according to policy dimension
First kind word in seed words and first kind set of words, the complete sentence after traversal fractionation, determines object statement, target language
Include the seed words and/or first kind word of policy dimension in sentence, counts the frequency of occurrence of each word in object statement, determine mesh
Frequency of occurrence is greater than the word of preset frequency threshold value as the second class word in poster sentence, according to the second class word, determines the
Two class set of words obtain the adjective in first kind set of words and the adjective in the second class set of words, according to the
The adjective in adjective and the second class set of words in a kind of set of words, determines the emotion word set of each policy dimension
It closes.Wherein, preset frequency threshold value can self-setting as required, include the second class word in the emotion set of words of each policy dimension
The adjective of language.For example, being appeared in object statement jointly when the seed words of policy dimension are steady with a steady word
Adjective can for it is neutral, rationally, it is balanced and substantially etc..
Above-described embodiment, according to the first kind word in the seed words of policy dimension and first kind set of words, traversal is torn open
Complete sentence after point, the common appearance of determination and the first quasi-sentence in the seed words and first kind set of words of policy dimension
Number is greater than the word of preset frequency threshold value, determines the second class word collection according to the second class word as the second class word
It closes, and then according to first kind set of words and the second class set of words, realizes obtaining to the emotion set of words of each policy dimension
It takes.
In one of the embodiments, as shown in fig. 6, S306 includes:
S602: the kind of each policy dimension emotion word and corresponding policy dimension in the emotion set of words of each policy dimension is determined
Term vector distance between sub- word；
S604: according to term vector distance and preset standards of grading, each political affairs in the emotion set of words of each policy dimension are determined
The score of plan dimension emotion word.
Server determines each policy dimension emotion word and corresponding policy dimension in the emotion set of words of each policy dimension
Term vector distance between seed words determines the emotion word of each policy dimension according to term vector distance and preset standards of grading
The score of each policy dimension emotion word in set.Wherein, preset standards of grading can self-setting as required.For example,
The fraction range of settable each policy dimension emotion word is 0 point -10 points, the kind of policy dimension corresponding with policy dimension emotion word
The score of sub- word is 10 points, determine term vector between each policy dimension emotion word and the seed words of corresponding policy dimension away from
From score of the term vector apart from smaller policy dimension emotion word is higher.Further, ten can be set by term vector distance
One different grade, corresponding 0 point -10 points of score can be by each policy after the score for determining each policy dimension emotion word
The fractional marks of dimension emotion word facilitate subsequent fractional statistics to work in policy dimension emotion word.
Above-described embodiment is tieed up according to policy dimension emotion word each in the emotion set of words of each policy dimension with corresponding policy
Term vector distance and preset standards of grading between the seed words of degree, determine each political affairs in the emotion set of words of each policy dimension
The score of plan dimension emotion word realizes the conjunction of the score of each policy dimension emotion word in the emotion set of words to each policy dimension
Reason is formulated.
In one of the embodiments, as shown in fig. 7, S308 includes:
S702: the preset policy type identification carried according to each policy dimension determines political affairs corresponding with each policy dimension
Plan type；
S704: the emotion dictionary of policy type corresponding with each policy dimension is generated；
S706: by the emotion set of words of each policy dimension, it is stored in the emotion word of policy type corresponding with each policy dimension
Library.
Server obtains the preset policy type identification that each policy dimension carries, and is carried according to each policy dimension default
Policy type identification, determine corresponding with each policy dimension policy type, generation policy type corresponding with each policy dimension
Emotion dictionary the emotion set of words of each policy dimension is stored in the emotion dictionary of policy type corresponding with each policy dimension.
Wherein, the emotion set of words of multiple policy dimensions can belong to the emotion dictionary of the same policy type.
Above-described embodiment generates policy type corresponding with each policy dimension according to the emotion set of words of each policy dimension
Emotion dictionary, realize the acquisition of the emotion dictionary to each policy type.
In one of the embodiments, as shown in figure 8, S204 includes:
S802: obtaining policy data to be processed, extracts the feature of policy data to be processed；
S804: according to the preset property data base of the characteristic matching of policy data to be processed, policy data to be processed is determined
Policy type；
S806: according to the policy type of policy data to be processed, matching preset policy types of database, determine with wait locate
Manage the corresponding goal and policy type of policy type of policy data.
Goal and policy type refers to, policy comprising emotion dictionary corresponding with the policy type of policy data to be processed
Type.Server obtains policy data to be processed, the feature of policy data to be processed is extracted, according to the spy of policy data to be processed
Sign matches preset property data base, the policy type of policy data to be processed is determined, according to the policy of policy data to be processed
Type matches preset policy types of database, determines goal and policy class corresponding with the policy type of policy data to be processed
Type.Wherein the feature of policy data to be processed can for the most project name of frequency of occurrence in policy data to be processed and to
The corresponding technical field of processing policy data can determine according to project name, technical field and preset property data base
The policy type of policy data to be processed.
Above-described embodiment obtains policy data to be processed, extracts the feature of policy data to be processed, according to policy to be processed
The preset property data base of the characteristic matching of data determines the policy type of policy data to be processed, according to policy number to be processed
According to policy type, match preset policy types of database, determine mesh corresponding with the policy type of policy data to be processed
Mark policy type, realizes the acquisition to goal and policy type.
In one of the embodiments, as shown in figure 9, S208 includes:
S902: according to the policy dimension emotion word in the emotion dictionary of goal and policy type, policy data to be processed is traversed；
S904: the number that the policy dimension emotion word in statistics emotion dictionary occurs in policy data to be processed；
S906: according to the number of appearance, the score of policy data to be processed is determined；
S908: according to the score of policy data to be processed, policy dynamics is determined.
Server traverses policy number to be processed according to the policy dimension emotion word in the emotion dictionary of goal and policy type
According to the number that the policy dimension emotion word in statistics emotion dictionary occurs in policy data to be processed, according to policy dimension feelings
Feel the number that word occurs, determines the score of policy data to be processed, according to the score of policy data to be processed, determine policy power
Degree.Wherein, the number occurred according to policy dimension emotion word, determines that the score of policy data to be processed includes: to tie up according to policy
The score of emotion word, the number and preset number Weight algorithm of appearance are spent, determines the score of policy data to be processed.It is in power
When the number that plan dimension emotion word occurs is more, according to preset number Weight algorithm, corresponding score also can be higher, presets
Number Weight algorithm can self-setting as required.For example, number Weight algorithm can be with are as follows: policy dimension emotion word
Frequency of occurrence and number coefficient are at corresponding relationship, and the coefficient occurred for the first time is 1, and second of coefficient occurred is 0.9, third time
The number of appearance is 0.8, and so on, policy dimension is calculated by the frequency of occurrence and number coefficient of policy dimension emotion word
The fractional weight of emotion word determines that policy dimension emotion word exists further according to the score and fractional weight of policy dimension emotion word
Score in policy data to be processed is determined by calculating score of each policy dimension emotion word in policy data to be processed
The score of policy data to be processed determines policy dynamics according to the score of policy data to be processed, and score is higher, illustrates policy
Dynamics is bigger.
Above-described embodiment traverses political affairs to be processed according to the policy dimension emotion word in the emotion dictionary of goal and policy type
Plan data count the number that policy dimension emotion word occurs in policy data to be processed in emotion dictionary, according to time of appearance
Number, determines the score of policy data to be processed, according to the score of policy data to be processed, determines policy dynamics, passes through score reality
Now the numeralization of policy dynamics is evaluated, realizes the policy dynamics analysis based on sentiment analysis.
It should be understood that although each step in the flow chart of Fig. 2-9 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-9
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in Figure 10, a kind of device of policy dynamics analysis is provided, comprising: first obtains
Module 102, second obtains module 104, first processing module 106 and Second processing module 108, in which:
First obtains module 102, for obtaining the emotion dictionary of preset each policy type；
Second obtains module 104, for obtaining policy data to be processed, the determining policy type with policy data to be processed
Corresponding goal and policy type；
First processing module 106 determines goal and policy type for the emotion dictionary according to preset each policy type
Emotion dictionary；
Second processing module 108 determines point of policy data to be processed for the emotion dictionary according to goal and policy type
Number, according to the score of policy data to be processed, determines policy dynamics.
The device of above-mentioned policy dynamics analysis, obtains the emotion dictionary of preset each policy type, obtains policy to be processed
Data determine goal and policy type corresponding with the policy type of policy data to be processed, determine the emotion of goal and policy type
Dictionary determines the score of policy data to be processed according to the emotion dictionary of goal and policy type, according to policy data to be processed
Score determines policy dynamics, in the sphere of policy, the score of policy to be processed is determined by emotion dictionary, according to policy to be processed
Score, determine policy dynamics, realized by score and the numeralization of policy dynamics is evaluated, realize the policy based on sentiment analysis
Dynamics analysis.
The device of policy dynamics analysis further includes dictionary generation module, dictionary generation module in one of the embodiments,
For obtaining the seed words of history policy data set, preset policy dimension and preset policy dimension, tieed up according to policy
The seed words of degree, traversal history policy data set determine the emotion set of words of each policy dimension, are marked according to preset scoring
Standard determines the score of each policy dimension emotion word in the emotion set of words of each policy dimension, according to the emotion word of each policy dimension
Set generates the emotion dictionary of policy type corresponding with each policy dimension.
Dictionary generation module is also used to obtain the word in history policy data set in one of the embodiments, and
Term vector corresponding with word is generated, the term vector distance of determining and policy dimension seed words is in preset distance threshold range
Interior first kind set of words, according to the seed words of policy dimension and first kind set of words, traversal history policy data set,
Determine the emotion set of words of each policy dimension.
Dictionary generation module is also used to the history policy number in history policy data set in one of the embodiments,
According to complete sentence is split as, according to the first kind word in the seed words of policy dimension and first kind set of words, traversal is split
Complete sentence afterwards determines object statement, counts the frequency of occurrence of each word in object statement, and it is default to determine that frequency of occurrence is greater than
The word of frequency threshold value the second class set of words is determined, according to first kind word according to the second class word as the second class word
Language set and the second class set of words, determine the emotion set of words of each policy dimension.
Dictionary generation module is also used to determine each political affairs in the emotion set of words of each policy dimension in one of the embodiments,
Term vector distance between plan dimension emotion word and the seed words of corresponding policy dimension according to term vector distance and preset is commented
Minute mark is quasi-, determines the score of each policy dimension emotion word in the emotion set of words of each policy dimension.
Dictionary generation module is also used to the preset policy class carried according to each policy dimension in one of the embodiments,
Type mark, determines policy type corresponding with each policy dimension, generates the emotion word of policy type corresponding with each policy dimension
The emotion set of words of each policy dimension is stored in the emotion dictionary of policy type corresponding with each policy dimension by library.
The second acquisition module is also used to obtain policy data to be processed in one of the embodiments, extracts political affairs to be processed
The feature of plan data determines policy data to be processed according to the preset property data base of the characteristic matching of policy data to be processed
Policy type preset policy types of database is matched according to the policy type of policy data to be processed, it is determining with it is to be processed
The corresponding goal and policy type of the policy type of policy data.
Second processing module is also used to the political affairs in the emotion dictionary according to goal and policy type in one of the embodiments,
Plan dimension emotion word traverses policy data to be processed, counts the policy dimension emotion word in emotion dictionary in policy number to be processed
The score of policy data to be processed is determined according to the number of appearance according to the number of middle appearance, according to point of policy data to be processed
Number, determines policy dynamics.
The specific of device about the analysis of policy dynamics limits the method that may refer to analyze above for policy dynamics
Restriction, details are not described herein.Modules in the device of above-mentioned policy dynamics analysis can be fully or partially through software, hard
Part and combinations thereof is realized.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment,
It can also be stored in a software form in the memory in computer equipment, execute the above modules in order to which processor calls
Corresponding operation.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in figure 11.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing history policy data, emotion dictionary, characteristic and policy categorical data.The computer
The network interface of equipment is used to communicate with external terminal by network connection.The computer program is executed by processor Shi Yishi
A kind of method of existing policy dynamics analysis.
It will be understood by those skilled in the art that structure shown in Figure 11, only part relevant to application scheme
The block diagram of structure, does not constitute the restriction for the computer equipment being applied thereon to application scheme, and specific computer is set
Standby may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with
Computer program, the processor perform the steps of when executing computer program
Obtain the emotion dictionary of preset each policy type；
Policy data to be processed is obtained, determines goal and policy type corresponding with the policy type of policy data to be processed；
According to the emotion dictionary of preset each policy type, the emotion dictionary of goal and policy type is determined；
The score that policy data to be processed is determined according to the emotion dictionary of goal and policy type, according to policy data to be processed
Score, determine policy dynamics.
The computer equipment of above-mentioned policy dynamics analysis, obtains the emotion dictionary of preset each policy type, obtains wait locate
Policy data is managed, goal and policy type corresponding with the policy type of policy data to be processed is determined, determines goal and policy type
Emotion dictionary, the score of policy data to be processed is determined according to the emotion dictionary of goal and policy type, according to policy to be processed
The score of data determines policy dynamics, in the sphere of policy, the score of policy to be processed is determined by emotion dictionary, according to wait locate
The score of reason policy determines policy dynamics, realizes that the numeralization to policy dynamics is evaluated by score, realizes and be based on sentiment analysis
Policy dynamics analysis.
In one embodiment, it is also performed the steps of when processor executes computer program
Obtain the seed words of history policy data set, preset policy dimension and preset policy dimension；
According to the seed words of policy dimension, traversal history policy data set determines the emotion set of words of each policy dimension；
According to preset standards of grading, point of each policy dimension emotion word in the emotion set of words of each policy dimension is determined
Number；
According to the emotion set of words of each policy dimension, the emotion dictionary of policy type corresponding with each policy dimension is generated.
In one embodiment, it is also performed the steps of when processor executes computer program
The word in history policy data set is obtained, and generates term vector corresponding with word；
The determining first kind word with the term vector distance of the seed words of policy dimension within the scope of preset distance threshold
Set；
According to the seed words of policy dimension and first kind set of words, traversal history policy data set determines each policy
The emotion set of words of dimension.
In one embodiment, it is also performed the steps of when processor executes computer program
History policy data in history policy data set is split as complete sentence；
Complete language according to the first kind word in the seed words of policy dimension and first kind set of words, after traversal fractionation
Sentence, determines object statement；
The frequency of occurrence for counting each word in object statement determines that frequency of occurrence is greater than the word work of preset frequency threshold value
For the second class word；
According to the second class word, the second class set of words is determined；
According to first kind set of words and the second class set of words, the emotion set of words of each policy dimension is determined.
In one embodiment, it is also performed the steps of when processor executes computer program
Determine the seed words of each policy dimension emotion word and corresponding policy dimension in the emotion set of words of each policy dimension
Between term vector distance；
According to term vector distance and preset standards of grading, each policy dimension in the emotion set of words of each policy dimension is determined
The score of emotion word.
In one embodiment, it is also performed the steps of when processor executes computer program
According to the preset policy type identification that each policy dimension carries, policy class corresponding with each policy dimension is determined
Type；
Generate the emotion dictionary of policy type corresponding with each policy dimension；
By the emotion set of words of each policy dimension, it is stored in the emotion dictionary of policy type corresponding with each policy dimension.
In one embodiment, it is also performed the steps of when processor executes computer program
Policy data to be processed is obtained, the feature of policy data to be processed is extracted；
According to the preset property data base of the characteristic matching of policy data to be processed, the policy of policy data to be processed is determined
Type；
According to the policy type of policy data to be processed, preset policy types of database, determining and political affairs to be processed are matched
The corresponding goal and policy type of the policy type of plan data.
In one embodiment, it is also performed the steps of when processor executes computer program
According to the policy dimension emotion word in the emotion dictionary of goal and policy type, policy data to be processed is traversed；
The number that policy dimension emotion word in statistics emotion dictionary occurs in policy data to be processed；
According to the number of appearance, the score of policy data to be processed is determined；
According to the score of policy data to be processed, policy dynamics is determined.In one embodiment, a kind of computer is provided
Readable storage medium storing program for executing is stored thereon with computer program, performs the steps of when computer program is executed by processor
Obtain the emotion dictionary of preset each policy type；
Policy data to be processed is obtained, determines goal and policy type corresponding with the policy type of policy data to be processed；
According to the emotion dictionary of preset each policy type, the emotion dictionary of goal and policy type is determined；
The score that policy data to be processed is determined according to the emotion dictionary of goal and policy type, according to policy data to be processed
Score, determine policy dynamics.
The storage medium of above-mentioned policy dynamics analysis, obtains the emotion dictionary of preset each policy type, obtains to be processed
Policy data determines goal and policy type corresponding with the policy type of policy data to be processed, determines goal and policy type
Emotion dictionary determines the score of policy data to be processed according to the emotion dictionary of goal and policy type, according to policy number to be processed
According to score, determine policy dynamics, in the sphere of policy, the score of policy to be processed determined by emotion dictionary, according to be processed
The score of policy determines policy dynamics, realizes that the numeralization to policy dynamics is evaluated by score, realizes based on sentiment analysis
The analysis of policy dynamics.
In one embodiment, it is also performed the steps of when computer program is executed by processor
Obtain the seed words of history policy data set, preset policy dimension and preset policy dimension；
According to the seed words of policy dimension, traversal history policy data set determines the emotion set of words of each policy dimension；
According to preset standards of grading, point of each policy dimension emotion word in the emotion set of words of each policy dimension is determined
Number；
According to the emotion set of words of each policy dimension, the emotion dictionary of policy type corresponding with each policy dimension is generated.
In one embodiment, it is also performed the steps of when computer program is executed by processor
The word in history policy data set is obtained, and generates term vector corresponding with word；
The determining first kind word with the term vector distance of the seed words of policy dimension within the scope of preset distance threshold
Set；
According to the seed words of policy dimension and first kind set of words, traversal history policy data set determines each policy
The emotion set of words of dimension.
In one embodiment, it is also performed the steps of when computer program is executed by processor
History policy data in history policy data set is split as complete sentence；
Complete language according to the first kind word in the seed words of policy dimension and first kind set of words, after traversal fractionation
Sentence, determines object statement；
The frequency of occurrence for counting each word in object statement determines that frequency of occurrence is greater than the word work of preset frequency threshold value
For the second class word；
According to the second class word, the second class set of words is determined；
According to first kind set of words and the second class set of words, the emotion set of words of each policy dimension is determined.
In one embodiment, it is also performed the steps of when computer program is executed by processor
Determine the seed words of each policy dimension emotion word and corresponding policy dimension in the emotion set of words of each policy dimension
Between term vector distance；
According to term vector distance and preset standards of grading, each policy dimension in the emotion set of words of each policy dimension is determined
The score of emotion word.
In one embodiment, it is also performed the steps of when computer program is executed by processor
According to the preset policy type identification that each policy dimension carries, policy class corresponding with each policy dimension is determined
Type；
Generate the emotion dictionary of policy type corresponding with each policy dimension；
By the emotion set of words of each policy dimension, it is stored in the emotion dictionary of policy type corresponding with each policy dimension.
In one embodiment, it is also performed the steps of when computer program is executed by processor
Policy data to be processed is obtained, the feature of policy data to be processed is extracted；
According to the preset property data base of the characteristic matching of policy data to be processed, the policy of policy data to be processed is determined
Type；
According to the policy type of policy data to be processed, preset policy types of database, determining and political affairs to be processed are matched
The corresponding goal and policy type of the policy type of plan data.
In one embodiment, it is also performed the steps of when computer program is executed by processor
According to the policy dimension emotion word in the emotion dictionary of goal and policy type, policy data to be processed is traversed；
The number that policy dimension emotion word in statistics emotion dictionary occurs in policy data to be processed；
According to the number of appearance, the score of policy data to be processed is determined；
According to the score of policy data to be processed, policy dynamics is determined.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of method of policy dynamics analysis, which comprises
Obtain the emotion dictionary of preset each policy type；
Policy data to be processed is obtained, determines goal and policy type corresponding with the policy type of the policy data to be processed；
According to the emotion dictionary of preset each policy type, the emotion dictionary of the goal and policy type is determined；
The score that the policy data to be processed is determined according to the emotion dictionary of the goal and policy type, according to described to be processed
The score of policy data determines policy dynamics.
2. the method according to claim 1, wherein in the emotion dictionary for obtaining preset each policy type
Before, comprising:
Obtain the seed words of history policy data set, preset policy dimension and preset policy dimension；
According to the seed words of the policy dimension, the history policy data set is traversed, determines the emotion word of each policy dimension
Set；
According to preset standards of grading, point of each policy dimension emotion word in the emotion set of words of each policy dimension is determined
Number；
According to the emotion set of words of each policy dimension, the emotion word of policy type corresponding with each policy dimension is generated
Library.
3. according to the method described in claim 2, it is characterized in that, the seed words according to the policy dimension, traverse institute
History policy data set is stated, determines that the emotion set of words of each policy dimension includes:
The word in the history policy data set is obtained, and generates term vector corresponding with word；
The determining first kind word with the term vector distance of the seed words of the policy dimension within the scope of preset distance threshold
Set；
According to the seed words of the policy dimension and the first kind set of words, the history policy data set is traversed, really
The emotion set of words of fixed each policy dimension；
Wherein, the seed words according to the policy dimension and the first kind set of words, traverse the history policy number
According to set, determine that the emotion set of words of each policy dimension includes:
History policy data in the history policy data set is split as complete sentence；
It is complete after traversal fractionation according to the first kind word in the seed words of the policy dimension and the first kind set of words
Whole sentence, determines object statement；
The frequency of occurrence for counting each word in the object statement determines that frequency of occurrence is greater than the word work of preset frequency threshold value
For the second class word；
According to the second class word, the second class set of words is determined；
According to the first kind set of words and the second class set of words, the emotion set of words of each policy dimension is determined.
4. according to the method described in claim 2, determining each political affairs it is characterized in that, described according to preset standards of grading
The score of each policy dimension emotion word includes: in the emotion set of words of plan dimension
Determine the seed words of each policy dimension emotion word and corresponding policy dimension in the emotion set of words of each policy dimension
Between term vector distance；
According to the term vector distance and preset standards of grading, each policy in the emotion set of words of each policy dimension is determined
The score of dimension emotion word.
5. according to the method described in claim 2, it is characterized in that, the emotion set of words according to each policy dimension,
The emotion dictionary for generating policy type corresponding with each policy dimension includes:
According to the preset policy type identification that each policy dimension carries, determining policy corresponding with each policy dimension
Type；
Generate the emotion dictionary of policy type corresponding with each policy dimension；
By the emotion set of words of each policy dimension, it is stored in the emotion word of policy type corresponding with each policy dimension
Library.
6. obtain policy data to be processed the method according to claim 1, wherein described, it is determining with it is described to
Processing policy data the corresponding goal and policy type of policy type include:
Policy data to be processed is obtained, the feature of the policy data to be processed is extracted；
According to the preset property data base of characteristic matching of the policy data to be processed, the policy data to be processed is determined
Policy type；
According to the policy type of the policy data to be processed, preset policy types of database is matched, is determined with described wait locate
Manage the corresponding goal and policy type of policy type of policy data.
7. the method according to claim 1, wherein the emotion dictionary according to the goal and policy type is true
The score of the fixed policy data to be processed, according to the score of the policy data to be processed, the policy dynamics of determination includes:
According to the policy dimension emotion word in the emotion dictionary of the goal and policy type, the policy data to be processed is traversed；
Count the number that the policy dimension emotion word in the emotion dictionary occurs in the policy data to be processed；
According to the number of appearance, the score of the policy data to be processed is determined；
According to the score of the policy data to be processed, policy dynamics is determined.
8. a kind of device of policy dynamics analysis, which is characterized in that described device includes:
First obtains module, for obtaining the emotion dictionary of preset each policy type；
Second obtains module, for obtaining policy data to be processed, the determining policy type pair with the policy data to be processed
The goal and policy type answered；
First processing module determines the goal and policy type for the emotion dictionary according to preset each policy type
Emotion dictionary；
Second processing module, for determining point of the policy data to be processed according to the emotion dictionary of the goal and policy type
Number, according to the score of the policy data to be processed, determines policy dynamics.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 7 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811431271.7A CN109635287A (en) | 2018-11-26 | 2018-11-26 | Method, apparatus, computer equipment and the storage medium of policy dynamics analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811431271.7A CN109635287A (en) | 2018-11-26 | 2018-11-26 | Method, apparatus, computer equipment and the storage medium of policy dynamics analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109635287A true CN109635287A (en) | 2019-04-16 |
Family
ID=66070001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811431271.7A Pending CN109635287A (en) | 2018-11-26 | 2018-11-26 | Method, apparatus, computer equipment and the storage medium of policy dynamics analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109635287A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112632964A (en) * | 2020-12-24 | 2021-04-09 | 平安科技（深圳）有限公司 | NLP-based industry policy information processing method, device, equipment and medium |
| CN114663208A (en) * | 2022-03-28 | 2022-06-24 | 奕资武汉商务咨询有限公司 | Enterprise tax intelligent management platform based on big data analysis |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106681985A (en) * | 2016-12-13 | 2017-05-17 | 成都数联铭品科技有限公司 | Establishment system of multi-field dictionaries based on theme automatic matching |
| CN107704556A (en) * | 2017-09-28 | 2018-02-16 | 北京车慧互动广告有限公司 | A kind of sentiment analysis method and system in automobile industry subdivision field |
| CN108269216A (en) * | 2018-01-31 | 2018-07-10 | 合肥和钧正策信息技术有限公司 | A kind of Policy Demand analysis method based on big data |
| US20180322583A1 (en) * | 2017-05-02 | 2018-11-08 | Gwendolyn M. Eubanks | Child Support Benefit Policies Service |
-
2018
- 2018-11-26 CN CN201811431271.7A patent/CN109635287A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106681985A (en) * | 2016-12-13 | 2017-05-17 | 成都数联铭品科技有限公司 | Establishment system of multi-field dictionaries based on theme automatic matching |
| US20180322583A1 (en) * | 2017-05-02 | 2018-11-08 | Gwendolyn M. Eubanks | Child Support Benefit Policies Service |
| CN107704556A (en) * | 2017-09-28 | 2018-02-16 | 北京车慧互动广告有限公司 | A kind of sentiment analysis method and system in automobile industry subdivision field |
| CN108269216A (en) * | 2018-01-31 | 2018-07-10 | 合肥和钧正策信息技术有限公司 | A kind of Policy Demand analysis method based on big data |
Non-Patent Citations (1)
| Title |
|---|
| 王小玉 等: "科技政策语义分析方法研究", 情报工程, vol. 1, no. 6, pages 102 - 108 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112632964A (en) * | 2020-12-24 | 2021-04-09 | 平安科技（深圳）有限公司 | NLP-based industry policy information processing method, device, equipment and medium |
| CN114663208A (en) * | 2022-03-28 | 2022-06-24 | 奕资武汉商务咨询有限公司 | Enterprise tax intelligent management platform based on big data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3816812A1 (en) | Question answering method and language model training method, apparatus, device, and storgage medium | |
| US8015239B2 (en) | Method and system to reduce false positives within an automated software-testing environment | |
| CN109766430A (en) | Contract audit method, apparatus, computer equipment and storage medium | |
| CN108363634B (en) | Method, device and equipment for identifying service processing failure reason | |
| US20170060826A1 (en) | Automatic Sentence And Clause Level Topic Extraction And Text Summarization | |
| CN110245475B (en) | Identity verification method and device | |
| CN110175609B (en) | Interface element detection method, device and equipment | |
| CN107622008A (en) | The traversal method and device of a kind of five application page | |
| CN106328145A (en) | Voice correction method and voice correction device | |
| CN115982376B (en) | Method and device for training model based on text, multimode data and knowledge | |
| CN110135888A (en) | Product information method for pushing, device, computer equipment and storage medium | |
| CN110532522A (en) | Error-detecting method, device, computer equipment and the storage medium of audio mark | |
| CN110955608B (en) | Test data processing method, device, computer equipment and storage medium | |
| CN102033872A (en) | Method and equipment for generating capital association relationship | |
| CN110598008A (en) | Data quality inspection method and device for recorded data and storage medium | |
| CN110990274A (en) | Data processing method, device and system for generating test case | |
| CN109635287A (en) | Method, apparatus, computer equipment and the storage medium of policy dynamics analysis | |
| CN114372006A (en) | Method and system for automatically generating test case, computer equipment and storage medium | |
| CN113408278A (en) | Intention recognition method, device, equipment and storage medium | |
| CN106991090A (en) | The analysis method and device of public sentiment event entity | |
| CN110232071A (en) | Search method, device and storage medium, the electronic device of drug data | |
| CN113900955A (en) | Automatic testing method, device, equipment and storage medium | |
| CN117033309A (en) | Data conversion method and device, electronic equipment and readable storage medium | |
| CN109670534A (en) | Method, apparatus, computer equipment and the storage medium of policy hotspot prediction | |
| CN104536897A (en) | Automatic testing method and system based on keyword |
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 |