CN110363505A - A kind of enterprise's quasi- battalion e window does service platform - Google Patents
A kind of enterprise's quasi- battalion e window does service platform Download PDFInfo
- Publication number
- CN110363505A CN110363505A CN201910648045.2A CN201910648045A CN110363505A CN 110363505 A CN110363505 A CN 110363505A CN 201910648045 A CN201910648045 A CN 201910648045A CN 110363505 A CN110363505 A CN 110363505A
- Authority
- CN
- China
- Prior art keywords
- keyword
- declare
- sentence
- word
- shop
- 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.)
- Withdrawn
Links
- 239000000463 material Substances 0.000 claims abstract description 25
- 230000009471 action Effects 0.000 claims abstract description 21
- 235000012054 meals Nutrition 0.000 claims abstract description 8
- 239000013598 vector Substances 0.000 claims description 49
- 239000000284 extract Substances 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 230000008520 organization Effects 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 238000005303 weighing Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 abstract description 8
- 238000000034 method Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 206010052428 Wound Diseases 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 235000013361 beverage Nutrition 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of enterprise's quasi- battalion e windows to do service platform, and the window does service platform and includes quick hundred shops set meal column module, the convenience-for-people column module of run a shop guide of action module, government affairs and run a shop to declare and inquire and declare progress module.Window of the invention, which does service platform and solves the masses and do not know about, to be managed whether legal, place what equipment, the masses is needed not to know the problems such as specifically hurrying back and forth back and forth with what material and multiple departments, it is truly realized material reduction, link reduction, time reduction that the masses take card, once to the most races in scene.
Description
Technical field
The present invention relates to information consultation technical fields more particularly to a kind of workflow examination and approval, big data analysis, intelligent form to spell
The enterprise's quasi- battalion e window connect does service platform
Background technique
It is the little Wei enterprise application platform based on B/S framework that enterprise's quasi- battalion e window, which does service platform, for the people
Application founds little Wei enterprise and is ignorant of the application knotty problems such as step and approval process, applies for business, approval process to enterprise is founded
It is combed, develops the application platform software of suitable little Wei enterprise application approval work, eliminated application and found little Wei enterprise journey
The problems such as sequence is complicated, and applicant is ignorant of the associated documents for needing to prepare when application process and application establishment enterprise, to reach
Apply for the purpose that convenient, efficiency improves.
The masses can often encounter following puzzlement before wanting to handle:
1) needs are what if, need to be related to which department handles which license, and the masses need to consult related data study, than
If whether management place is legal, any facilities and equipment is needed in done management place, and health, fire control acceptance are met before opening
Standard, and there is anything to require when the amount of money and area reach the requirement upper limit and can just declare fire-fighting after reaching final acceptance of construction condition
Formality.
2) it handling and often needs many materials, the masses do not know often largely specifically to be needed with for which material,
Usually the masses take the material of energy band, and even such material is more also inevitably to be forgotten, as long as there is a material not have
It takes, the masses will the multiple scene because material is hurried back and forth when handling.
3) it handles and often needs to run many departments, encountering problems on the way is also to need hurrying back and forth back and forth more than once, by
The time of reason is very long, and link is also very much, and the time for taking card of such masses will be very long, and draw materials when must also go
Different departments goes to take.
Summary of the invention
In view of this, the application, which provides a kind of enterprise's quasi- battalion e window, does service platform.
The application is achieved by the following technical solution:
A kind of enterprise's quasi- battalion e window does service platform, and the window does service platform and includes: quick hundred shops set meal column module, opens
The convenience-for-people column module of shop guide of action module, government affairs runs a shop to declare and inquire and declares progress module and information on services retrieval mould
Block:
Quick hundred shops set meal column module, for showing the choice box for listing all shop types, user is by clicking choosing
Select selection of the frame realization to shop type；
It runs a shop guide of action module, for obtaining relevant guide of action according to the shop type, and is added, makes
User is checked by clicking the guide of action；
The convenience-for-people column module of government affairs, for providing policy query function, user is mentioned by clicking the convenience-for-people column module of government affairs
The policy list of confession carries out information inquiry；
It runs a shop to declare and inquire and declares progress module, user declares button by click and declares to start, and passes through a little
Inquiry button is hit to browse the progress of declaring；
Information on services retrieval module, for providing the search function of policy or convenience-for-people information, user inputs term, government affairs
Cloud Server is analyzed and is handled to the term, and the search result obtained is returned to user.
Further, the government affairs Cloud Server is analyzed and is handled to the term, is specifically included:
Step 1, data are divided as unit of sentence and is removed not comprising field concept or only comprising the sentence of a concept
Son；
Step 2, current word and word spacing are chosen as feature, data are labeled；
Step 3, training set and test set are splitted data into, is trained using training the set pair analysis model, and use test set
Model is tested, the accuracy of Relation extraction is verified.
Further, in step 1, described that data are divided as unit of sentence and are removed not comprising field concept or only
Before sentence comprising a concept further include:
The data of input are carried out vectorization processing by the text data that government affairs field is handled using neural network model；
Text data is converted to the form of vector, gives sentence S, wherein including set of words W (w1,w2,...,wm), m is
The number of word in sentence S, the text feature collection K (k of the sentence S extracted1,k2,...,kn), n indicates that each sentence extracts
Text feature number, i-th of Text Representation that t-th of word extracts be
The neural network model specifically includes:
First layer is input layer, and text data is divided as unit of sentence, removes the sentence not comprising concept pair, will be every
Data is expressed as: the form of { concept 1, concept 2, notional word spacing, relationship type, sentence }；
The second layer is term vector expression layer, and data are expressed as to the form of vector using SOWE term vector model；
Third layer is pond layer, and obtaining final vector using the operation of maximum pondization indicates；
4th layer is output layer, and the judgement of relationship type is carried out using integrated softmax function.
Further, the data by input carry out vectorization processing, specifically include:
Using current word and word spacing as feature, term vector processing is carried out to text information:
rw=Wword×Vw
Wherein, rwIt is the term vector expression of word w；Wword∈Rl×|m|Indicate text term vector matrix；M indicates word in sentence
Number；L indicates term vector dimension；VwIt is the one-hot expression of word w；
Term vector processing is carried out to each text feature:
Wherein,It is the term vector expression of the ith feature of text；Be the ith feature of text feature distribution to
Amount,
The corresponding vectorization of each word is expressed as the connection of each vector, and the corresponding vectorization of t-th of word indicates are as follows:
Obtained text local feature are as follows:
E={ x1,x2,...,xm}。
Further, described that data are labeled, it specifically includes:
Different weights is subject to different piece data using attention mechanism, and uses the attention weight of word level
Matrix captures information associated with relationship by objective (RBO) in sentence, using following formula:
Wherein, atFor the vector m calculated automatically in attention mechanismtWeight, l be it is in need distribution weight vector
Number, atIt is normalized using softmax, vaIt is weight vectors, WaAnd UaIt is weight matrix, ytIt is hidden layer
The output of t step, n is the corresponding vector of factor of weighing factor, and l is sentence length, and y is last output, the table as sentence
Show.
Further, described that the search result obtained is returned to user, it specifically includes:
Context resolution is carried out to search result, extracts keyword set, and acquisition candidate is retrieved according to keyword set and is pushed away
It delivers letters breath, and generates candidate pushed information set；
Based on the matching relationship between the keyword set and each item candidate pushed information, chooses at least one candidate and push away
Breath of delivering letters generates pushed information set；
Content and the pushed information set based on the Webpage generate new web page.
Further, Context resolution is carried out to search result, extracts keyword set, comprising:
And/or semantic analysis for statistical analysis to the content of Webpage, extracts at least one keyword, based on described
At least one keyword generates keyword set；
Described at least one keyword based on described in, generates keyword set, comprising:
For the single keyword at least one described keyword, it is extended to generate expanded keyword, wherein institute
Stating expanded keyword includes the single keyword and at least one of the following: the synonym of the single keyword, described
The individually conjunctive word of the near synonym of keyword, the single keyword；
Based on the expanded keyword, keyword set is generated.
Further, the user is checked by clicking the guide of action, is specifically included: being checked whole working
Guide and part guide of action is checked according to the shop type；Include associated department in the guide of action, handle content
Item submits list of materials, relevant law foundation；
Further include flow chart information in the guide of action, includes handling the time and handling ground in the flow chart information
Point；
It include government affairs service organization map in provided policy list, user is by clicking the government affairs service organization
The link of map jumps to specified page and carries out information inquiry.
Further, the user declares button by click and declares to start, and specifically includes:
User by click declare button after, it is described run a shop declare and inquire declare progress module generation first step page
Face includes essential information region in the first step page and handles personnel's status display area；
The essential information region is described to handle personnel status display area for showing personal information, operation and management information
Domain is used to show the online situation for currently handling personnel；
When it is described run a shop declare and inquire declare progress module generate the first step page after, user is in the essential information
Data information needed for the input of region, and according to the online situation for currently handling personnel, handling the choosing of personnel's status display area
Select the personnel of handling；
When user selection handle personnel after, it is described run a shop declare and inquire declare progress module generate material submission page
Face, user carry out the upload of material according to default rule；
After the completion of the upload of the material, it is described run a shop declare and inquire declare progress module generate prompting message.
Further, described to browse the progress of declaring by clicking inquiry button, it specifically includes:
When user click inquiry button after, it is described run a shop declare and inquire declare progress module generate declare progress chart,
And progress chart is declared described in generating in essential information region display.
Compared with the prior art, the advantages of the present invention are as follows: the present invention be directed to reduce in order to which the masses handle business license
Process and a suitable masses developed handle a software of business license.The project major function includes: quick
Hundred shops set meal column, guide of action module of running a shop, the convenience-for-people column of government affairs run a shop and declare and inquire the functional modules such as the progress of declaring, and solve
Whether the masses do not know about manages legal, what equipment place needs, the masses do not know specifically with what material and multiple portions
The problems such as door is hurried back and forth back and forth has been truly realized material reduction, link reduction, time reduction that the masses take card, most to scene
It runs primary.
Detailed description of the invention
Fig. 1 is the composed structure schematic diagram that enterprise's standard of the invention seeks that e window does service platform.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with the application.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the application.
It is only to be not intended to be limiting the application merely for for the purpose of describing particular embodiments in term used in this application.
It is also intended in the application and the "an" of singular used in the attached claims, " described " and "the" including majority
Form, unless the context clearly indicates other meaning.It is also understood that term "and/or" used herein refers to and wraps
It may be combined containing one or more associated any or all of project listed.
Below in conjunction with attached drawing and example, the present invention is described in further detail.
Fig. 1 is the composed structure schematic diagram that enterprise's standard of the invention seeks that e window does service platform.It is one that the window, which does service platform,
Kind enterprise's quasi- battalion e window does service platform, and the window does service platform and includes, quick hundred shops set meal column, guide of action module of running a shop,
The convenience-for-people column of government affairs runs a shop to declare and inquire and declares progress functional module.
Quick hundred shops set meal column, convenient and efficient for operating system, when page load is come in, log in page, which can be shown, lists
The choice box of all types run a shop and the simple introduction for handling process.Push-botton operation is clicked according to prompt, facilitates group
It is very clear when crowd is using system.
Guide of action module of running a shop checks working for being added according to the specified guide of action of the type in shop acquisition
Guide can check whole guides and check guide according to shop type difference, and to how to open food and beverage enterprise in guide, which is related to
Department handles which license needs which material submitted, what legal basis is, is provided in guide when handling related license
Flow chart is handled, is not desired to see that text version can also check to handle flow chart and also designate and handles the time and handle place, this
Function can allow the masses to get information about very much the whole flow process step and points for attention run a shop in system, significantly
It has saved the masses and has browsed relevant information bring puzzlement.
The convenience-for-people column of government affairs, the meeting page can show below the convenience-for-people column of government affairs have when homepage loads, little Wei enterprise support policy
Tax map is done in inquiry, the inquiry of " double wounds " policy, and social security office, Beijing, Beijing's establishing and enterprise e window is logical, government affairs service organization
Figure link clicks can jump specified page access, little Wei enterprise support policy inquiry and, " double wounds " policy inquiry mainly is
Allow the masses that can recognize the variation of policy in real time.Do tax map in order to allow the masses recognize each urban district the tax bureau it is specific
Orientation.
Run a shop to declare and inquire and declare progress module, run a shop need to only click need in the type in shop opened declare button into
Enter to declare the first step page, the page can show essential information region (essential information, legal representative, the food warp that needs are filled in
Battalion's information etc.) fill in after the online assistant director of selection one click and enter second step material in next step and submit the page, select you
Upload material can upload after you can be prompted to need to take to the data at scene (masses ask for, EMS there are two types of pickup mode
Mailing) it chooses.Just finish entirely to handle the process masses to this step and only needs to wait for related personnel's examination & approval by can this
Function substantially reduce handle business license whole flow process be truly realized link material reduce, link reduce, the time reduce,
Run primary live (evidence obtaining).Inquiry declare function can see you handle into specific to which step (received, by
Reason, in examination & approval, wait collect evidence) see and to being checked wait the consulting telephones at most dialed in system of collecting evidence as the masses
It can collect evidence.
It further includes information on services retrieval module that enterprise's quasi- battalion e window, which does service platform, for providing policy or convenience-for-people letter
The search function of breath, user input term, and government affairs Cloud Server is analyzed and handled to the term, and is returned to user
Return the search result obtained.
The government affairs Cloud Server is analyzed and is handled to the term, is specifically included:
Step 1, data are divided as unit of sentence and is removed not comprising field concept or only comprising the sentence of a concept
Son；
Step 2, current word and word spacing are chosen as feature, data are labeled；
Step 3, training set and test set are splitted data into, is trained using training the set pair analysis model, and use test set
Model is tested, the accuracy of Relation extraction is verified.
In step 1, described that data are divided as unit of sentence and are removed not comprising field concept or only comprising one
Before the sentence of concept further include:
The data of input are carried out vectorization processing by the text data that government affairs field is handled using neural network model；
Text data is converted to the form of vector, gives sentence S, wherein including set of words W (w1,w2,...,wm), m is
The number of word in sentence S, the text feature collection K (k of the sentence S extracted1,k2,...,kn), n indicates that each sentence extracts
Text feature number, i-th of Text Representation that t-th of word extracts be
The neural network model specifically includes:
First layer is input layer, and text data is divided as unit of sentence, removes the sentence not comprising concept pair, will be every
Data is expressed as: the form of { concept 1, concept 2, notional word spacing, relationship type, sentence }；
The second layer is term vector expression layer, and data are expressed as to the form of vector using SOWE term vector model；
Third layer is pond layer, and obtaining final vector using the operation of maximum pondization indicates；
4th layer is output layer, and the judgement of relationship type is carried out using integrated softmax function.
The data by input carry out vectorization processing, specifically include:
Using current word and word spacing as feature, term vector processing is carried out to text information:
rw=Wword×Vw
Wherein, rwIt is the term vector expression of word w；Wword∈Rl×|m|Indicate text term vector matrix；M indicates word in sentence
Number；L indicates term vector dimension；VwIt is the one-hot expression of word w；
Term vector processing is carried out to each text feature:
Wherein,It is the term vector expression of the ith feature of text；Be the ith feature of text feature distribution to
Amount,
The corresponding vectorization of each word is expressed as the connection of each vector, and the corresponding vectorization of t-th of word indicates are as follows:
Obtained text local feature are as follows:
E={ x1,x2,...,xm}。
It is described that data are labeled, it specifically includes:
Different weights is subject to different piece data using attention mechanism, and uses the attention weight of word level
Matrix captures information associated with relationship by objective (RBO) in sentence, using following formula:
Wherein, atFor the vector m calculated automatically in attention mechanismtWeight, l be it is in need distribution weight vector
Number, atIt is normalized using softmax, vaIt is weight vectors, WaAnd UaIt is weight matrix, ytIt is hidden layer
The output of t step, n is the corresponding vector of factor of weighing factor, and l is sentence length, and y is last output, the table as sentence
Show.
It is described that the search result obtained is returned to user, it specifically includes:
Context resolution is carried out to search result, extracts keyword set, and acquisition candidate is retrieved according to keyword set and is pushed away
It delivers letters breath, and generates candidate pushed information set；
Based on the matching relationship between the keyword set and each item candidate pushed information, chooses at least one candidate and push away
Breath of delivering letters generates pushed information set；
Content and the pushed information set based on the Webpage generate new web page.
Context resolution is carried out to search result, extracts keyword set, comprising:
And/or semantic analysis for statistical analysis to the content of Webpage, extracts at least one keyword, based on described
At least one keyword generates keyword set；
Described at least one keyword based on described in, generates keyword set, comprising:
For the single keyword at least one described keyword, it is extended to generate expanded keyword, wherein institute
Stating expanded keyword includes the single keyword and at least one of the following: the synonym of the single keyword, described
The individually conjunctive word of the near synonym of keyword, the single keyword；
Based on the expanded keyword, keyword set is generated.
The present invention carries out handling business in order to which the masses handle a suitable masses that business license reduces process and develops
A software of license.It solves the masses and does not know about whether operation is legal, what equipment place needs, and the masses do not know specific band
The problems such as what material and multiple departments hurry back and forth back and forth has been truly realized the masses and has taken the link material reduction of license, link
It reduces, time reduction, is at most run once to scene.
Those of ordinary skill in the art will appreciate that all or part of the steps in the above method can be instructed by program
Related hardware is completed, and described program can store in computer readable storage medium, such as read-only memory, disk or CD
Deng.Optionally, one or more integrated circuits also can be used to realize, accordingly in all or part of the steps of above-described embodiment
Ground, each module/unit in above-described embodiment can take the form of hardware realization, can also use the shape of software function module
Formula is realized.The present invention is not limited to the combinations of the hardware and software of any particular form.
It should be noted that the invention may also have other embodiments, without departing substantially from spirit of that invention and its essence
In the case of, those skilled in the art can make various corresponding changes and modifications according to the present invention, but these are corresponding
Change and modification all should fall within the scope of protection of the appended claims of the present invention.
Claims (10)
1. a kind of enterprise's quasi- battalion e window does service platform, the window does service platform and includes: quick hundred shops set meal column module, runs a shop
The convenience-for-people column module of guide of action module, government affairs runs a shop to declare and inquire and declares progress module and information on services retrieval module,
It is characterized by:
Quick hundred shops set meal column module, for showing the choice box for listing all shop types, user is by clicking choice box
Realize the selection to shop type；
It runs a shop guide of action module, for obtaining relevant guide of action according to the shop type, and is added, user
It is checked by clicking the guide of action；
The convenience-for-people column module of government affairs, for providing policy query function, user is by clicking provided by the convenience-for-people column module of government affairs
Policy list carries out information inquiry；
It runs a shop to declare and inquire and declares progress module, user declares button by click and declares to start, and is looked by clicking
Button is ask to browse the progress of declaring；
Information on services retrieval module, for providing the search function of policy or convenience-for-people information, user inputs term, government affairs cloud clothes
Business device is analyzed and is handled to the term, and the search result obtained is returned to user.
2. enterprise's quasi- battalion according to claim 1 e window does service platform, which is characterized in that the government affairs Cloud Server pair
The term is analyzed and is handled, and is specifically included:
Step 1, data are divided as unit of sentence and is removed not comprising field concept or only comprising the sentence of a concept；
Step 2, current word and word spacing are chosen as feature, data are labeled；
Step 3, training set and test set are splitted data into, is trained using training the set pair analysis model, and using test set to mould
Type is tested, and the accuracy of Relation extraction is verified.
3. enterprise's quasi- battalion according to claim 2 e window does service platform, which is characterized in that in step 1, described to count
Accordingly sentence be unit divides and remove not comprising field concept or only include a concept sentence before further include:
The data of input are carried out vectorization processing by the text data that government affairs field is handled using neural network model；
Text data is converted to the form of vector, gives sentence S, wherein including set of words W (w1,w2,...,wm), m is sentence
The number of word in S, the text feature collection K (k of the sentence S extracted1,k2,...,kn), n indicates the text that each sentence extracts
Eigen number, i-th of Text Representation that t-th of word extracts are
The neural network model specifically includes:
First layer is input layer, and text data is divided as unit of sentence, removes the sentence not comprising concept pair, by every number
According to being expressed as: the form of { concept 1, concept 2, notional word spacing, relationship type, sentence }；
The second layer is term vector expression layer, and data are expressed as to the form of vector using SOWE term vector model；
Third layer is pond layer, and obtaining final vector using the operation of maximum pondization indicates；
4th layer is output layer, and the judgement of relationship type is carried out using integrated softmax function.
4. enterprise's quasi- according to claim 3 battalion e window does service platform, which is characterized in that the data by input into
Row vectorization processing, specifically includes:
Using current word and word spacing as feature, term vector processing is carried out to text information:
rw=Wword×Vw
Wherein, rwIt is the term vector expression of word w；Wword∈Rl×|m|Indicate text term vector matrix；M indicates of word in sentence
Number；L indicates term vector dimension；VwIt is the one-hot expression of word w；
Term vector processing is carried out to each text feature:
Wherein,It is the term vector expression of the ith feature of text；It is the feature distribution vector of the ith feature of text,
The corresponding vectorization of each word is expressed as the connection of each vector, and the corresponding vectorization of t-th of word indicates are as follows:
Obtained text local feature are as follows:
E={ x1,x2,...,xm}。
5. enterprise's quasi- according to one of claim 2 to 4 battalion e window do service platform, which is characterized in that it is described to data into
Rower note, specifically includes:
Different weights is subject to different piece data using attention mechanism, and uses the attention weight matrix of word level
Information associated with relationship by objective (RBO) in sentence is captured, using following formula:
Wherein, atFor the vector m calculated automatically in attention mechanismtWeight, l be it is in need distribution weight vector number,
atIt is normalized using softmax, vaIt is weight vectors, WaAnd UaIt is weight matrix, ytIt is that hidden layer t is walked
Output, n is the corresponding vector of factor of weighing factor, and l is sentence length, and y is last output, the expression as sentence.
6. enterprise's quasi- battalion according to claim 1 e window does service platform, which is characterized in that described return to user obtains
Search result, specifically include:
Context resolution is carried out to search result, extracts keyword set, and is retrieved according to keyword set and obtains candidate push letter
Breath, and generate candidate pushed information set；
Based on the matching relationship between the keyword set and each item candidate pushed information, at least one candidate push letter is chosen
Breath generates pushed information set；
Content and the pushed information set based on the Webpage generate new web page.
7. enterprise's quasi- battalion according to claim 6 e window does service platform, which is characterized in that carry out content to search result
Keyword set is extracted in parsing, comprising:
And/or semantic analysis for statistical analysis to the content of Webpage, extracts at least one keyword, based on described at least
One keyword generates keyword set；
Described at least one keyword based on described in, generates keyword set, comprising:
For the single keyword at least one described keyword, it is extended to generate expanded keyword, wherein the expansion
Open up keyword include the single keyword and at least one of the following: the synonym of the single keyword, it is described individually
The conjunctive word of the near synonym of keyword, the single keyword；
Based on the expanded keyword, keyword set is generated.
8. enterprise's quasi- battalion according to claim 1 e window does service platform, which is characterized in that the user passes through click
The guide of action is checked, is specifically included: being checked whole guides of action and is checked that part is handled affairs according to the shop type
Guide；Include associated department in the guide of action, handles content item, submits list of materials, relevant law foundation；
Further include flow chart information in the guide of action, includes handling the time and handling place in the flow chart information；
It include government affairs service organization map in provided policy list, user is by clicking government affairs service organization map
Link jump to specified page carry out information inquiry.
9. enterprise's quasi- battalion according to claim 1 e window does service platform, which is characterized in that the user passes through click
It declares button to declare to start, specifically include:
User by click declare button after, it is described run a shop declare and inquire declare progress module generation the first step page,
It include essential information region and handling personnel's status display area in the first step page；
The essential information region is described to handle personnel's status display area use for showing personal information, operation and management information
The online situation of personnel is currently handled in display；
When it is described run a shop declare and inquire declare progress module generate the first step page after, user is in the essential information region
Data information needed for input, and according to the online situation for currently handling personnel, it is done handling the selection of personnel's status display area
Reason personnel；
When user selection handle personnel after, it is described run a shop declare and inquire declare progress module generate material submission the page,
User carries out the upload of material according to default rule；
After the completion of the upload of the material, it is described run a shop declare and inquire declare progress module generate prompting message.
10. enterprise's quasi- battalion according to claim 1 e window does service platform, which is characterized in that described to be pressed by clicking inquiry
Button browses the progress of declaring, and specifically includes:
After user clicks inquiry button, it is described run a shop to declare and inquire to declare progress module and generate declare progress chart, and
The described of essential information region display generation declares progress chart.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910648045.2A CN110363505A (en) | 2019-07-18 | 2019-07-18 | A kind of enterprise's quasi- battalion e window does service platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910648045.2A CN110363505A (en) | 2019-07-18 | 2019-07-18 | A kind of enterprise's quasi- battalion e window does service platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110363505A true CN110363505A (en) | 2019-10-22 |
Family
ID=68220229
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910648045.2A Withdrawn CN110363505A (en) | 2019-07-18 | 2019-07-18 | A kind of enterprise's quasi- battalion e window does service platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110363505A (en) |
-
2019
- 2019-07-18 CN CN201910648045.2A patent/CN110363505A/en not_active Withdrawn
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Durbarry | Tourism and economic growth: the case of Mauritius | |
| Boettcher III | Context, methods, numbers, and words: Prospect theory in international relations | |
| JP6369053B2 (en) | MATCHING DEVICE, MATCHING METHOD, AND PROGRAM | |
| US20080097937A1 (en) | Distributed method for integrating data mining and text categorization techniques | |
| CN107872436A (en) | A kind of account recognition methods, apparatus and system | |
| CN110675269B (en) | Text auditing method and device | |
| CN105740227A (en) | Genetic simulated annealing method for solving new words in Chinese segmentation | |
| CN107529655A (en) | Space mission method of commerce, system and space flight mass-rent server based on mass-rent | |
| CN108021628A (en) | A kind of management system of science and technology theme | |
| CN109558591A (en) | Chinese event detection method and device | |
| JP2016153998A (en) | Service evaluation device and method | |
| US20220327445A1 (en) | Workshop assistance system and workshop assistance method | |
| CN106202299A (en) | A kind of people with disability authority user based on people with disability's feature recommends method | |
| Lauterbach et al. | Adopt, adapt, enact or use? A framework and methodology for extracting and integrating conceptual mechanisms of IT adoption and use | |
| CN110363505A (en) | A kind of enterprise's quasi- battalion e window does service platform | |
| CN110377809A (en) | The resource acquisition qualification generation method and relevant device of pre-set user | |
| Rahman et al. | " The Whole Is Greater Than the Sum of Its Parts": Optimization in Collaborative Crowdsourcing | |
| Taherkhani et al. | Intelligent decision support system using nested ensemble approach for customer churn in the hotel industry | |
| McCloskey et al. | Natural language processing analysis of online reviews for small business: extracting insight from small corpora | |
| DE102012221927A1 (en) | Procedure for managing e-mail | |
| Mahari et al. | The law and NLP: Bridging disciplinary disconnects | |
| JP2014229047A (en) | Event information extraction device, operating method of the same, and computer program | |
| Salhi et al. | Sentiment Analysis Application on Twitter for E-reputation | |
| Pijoh et al. | The Importance-Performance Analysis Of Service Quality At Aquarius Car Wash | |
| US20240177255A1 (en) | A data providing device, a data providing system, a data providing program, a data providing method, a data analysis device, a data management system, a data management method, and a data recording medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20191022 |
|
| WW01 | Invention patent application withdrawn after publication |