CN114021001A - Enterprise measure matching method, device and medium based on big data - Google Patents
Enterprise measure matching method, device and medium based on big data Download PDFInfo
- Publication number
- CN114021001A CN114021001A CN202111264058.3A CN202111264058A CN114021001A CN 114021001 A CN114021001 A CN 114021001A CN 202111264058 A CN202111264058 A CN 202111264058A CN 114021001 A CN114021001 A CN 114021001A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- measure
- matching
- information
- measures
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000012545 processing Methods 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 12
- 239000000463 material Substances 0.000 claims description 11
- 238000012795 verification Methods 0.000 claims description 8
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 230000009471 action Effects 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims description 2
- 230000006870 function Effects 0.000 description 26
- 230000008569 process Effects 0.000 description 12
- 238000005516 engineering process Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 238000011161 development Methods 0.000 description 8
- 238000007726 management method Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 238000007639 printing Methods 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 238000013441 quality evaluation Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000002372 labelling Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 238000012550 audit Methods 0.000 description 2
- 238000009960 carding Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000005206 flow analysis Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 239000010410 layer Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000013049 sediment Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 239000002344 surface layer Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24553—Query execution of query operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Educational Administration (AREA)
Abstract
The application discloses a big data-based enterprise measure matching method, equipment and a medium, wherein the method comprises the following steps: acquiring enterprise information uploaded by an enterprise in the measure matching system; searching the enterprise information in a pre-constructed enterprise portrait label library to determine an enterprise portrait label; matching the enterprise portrait tags in a pre-constructed measure tag library, and determining matching measures corresponding to the enterprise and matching degrees of the matching measures; and pushing the matching measures to the enterprise according to the matching degree of the matching measures. The enterprise information is retrieved in the enterprise portrait label library constructed in advance, the enterprise portrait label is determined, then the enterprise portrait label is matched in the measure label library constructed in advance, enterprise intelligence matching meeting measure conditions can be achieved, corresponding measures are accurately pushed to the enterprise, the enterprise can know measure support obtained by the enterprise, and information is communicated with the government in real time.
Description
Technical Field
The present application relates to the field of network security technologies, and in particular, to a method, a device, and a medium for enterprise measure matching based on big data.
Background
Along with the development of society, the nation pays more and more attention to enterprise innovation, and for this reason, the government has a lot of subsidies and tax preferential measures to the enterprise, but needs the enterprise to satisfy certain conditions.
At present, in order to clearly know whether the enterprise accords with the government preferential measures, a plurality of enterprise management layers need to spend more time, and because the conditions of different enterprises are different, a plurality of enterprises cannot quickly combine the conditions of the enterprises to know the current government measures, so that the information between the enterprises and the government is asymmetric.
Disclosure of Invention
The embodiment of the application provides an enterprise measure matching method, equipment and medium based on big data, and is used for solving the problem of information asymmetry between an enterprise and a government.
The embodiment of the application adopts the following technical scheme:
in one aspect, an embodiment of the present application provides an enterprise measure matching method based on big data, where the method includes: acquiring enterprise information uploaded by an enterprise in the measure matching system; searching the enterprise information in a pre-constructed enterprise portrait label library to determine the enterprise portrait label; matching the enterprise portrait tags in a pre-constructed measure tag library, and determining matching measures corresponding to the enterprise and matching degrees of the matching measures; and pushing the matching measures to the enterprise according to the matching degree of the matching measures.
In one example, determining the pre-built enterprise portrait tag library specifically includes: acquiring multi-source information related to an enterprise; preprocessing the multi-source information, and determining preprocessed multi-source information; performing knowledge learning on the preprocessed multi-source information to obtain potential knowledge among the preprocessed multi-source information; carrying out knowledge reasoning on the multi-source information after knowledge learning, and determining a knowledge graph corresponding to an enterprise; and carrying out portrait on the enterprise through the knowledge graph, and determining the enterprise portrait tags so as to construct the enterprise portrait tag library.
In one example, the learning knowledge of the preprocessed multi-source information to obtain the latent knowledge among the multi-source information specifically includes: predicting the value of query predicates in the multi-source information through a discriminant knowledge learning algorithm DSL based on a set predicate table, and performing weight learning on the multi-source information through an unconstrained optimization algorithm L-BFGS to obtain potential knowledge among the preprocessed multi-source information; and generating an initial network structure corresponding to the knowledge graph through the potential knowledge among the preprocessed multi-source information.
In one example, the performing knowledge reasoning on the multi-source information after the knowledge learning to determine the knowledge graph corresponding to the enterprise specifically includes: based on the initial network structure, carrying out knowledge reasoning on the relation between the entities of the multi-source information through a deep learning Lazy-MC-SAT algorithm; and updating the initial network structure according to the knowledge reasoning result, and determining the knowledge graph corresponding to the enterprise.
In one example, determining the pre-constructed measure tag library specifically includes: acquiring multi-source measure information; carrying out structuring processing on the multi-source measure information, and determining the structuring measure information; and setting a label code value and a label name for the structural measure information according to a data dictionary mode, and determining a label of the structural measure information to construct the measure label library.
In one example, the obtaining the multi-source measure information specifically includes: automatically capturing measure information of a set website; matching the measure information of the set website with the measure information uploaded by a government department, and if the matching fails, pushing the measure information of the set website and the link of the set website to a relevant government; and associating a preset news platform to automatically update the multi-source measure information.
In one example, after the matching measure is pushed to the enterprise according to the matching degree of the matching measure, the method includes: monitoring a request for the enterprise to declare the matching measure; extracting enterprise material uploaded by the enterprise based on the request; according to the requirements of the matching measures, automatically performing multiple data cross check on the enterprise materials; and if the verification fails, forbidding the enterprise to declare the matching measures.
In one example, after the performing the multiple data cross-checks on the enterprise material automatically according to the requirements of the matching measures, the method further comprises: if the verification is successful, judging whether the enterprise authorizes the auxiliary declaration; if yes, obtaining declaration information to be filled in from the enterprise portrait label library, and automatically filling the declaration information to a corresponding position to assist the enterprise in declaration.
On the other hand, the embodiment of the present application provides an enterprise measure matching device based on big data, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to: acquiring enterprise information uploaded by an enterprise in the measure matching system; searching the enterprise information in a pre-constructed enterprise portrait label library to determine an enterprise portrait label; matching the enterprise portrait tags in a pre-constructed measure tag library, and determining matching measures corresponding to the enterprise and matching degrees of the matching measures; and pushing the matching measures to the enterprise according to the matching degree of the matching measures.
In another aspect, an embodiment of the present application provides a big data-based enterprise measure matching non-volatile computer storage medium, which stores computer-executable instructions, where the computer-executable instructions are configured to: acquiring enterprise information uploaded by an enterprise in the measure matching system; searching the enterprise information in a pre-constructed enterprise portrait label library to determine an enterprise portrait label; matching the enterprise portrait tags in a pre-constructed measure tag library, and determining matching measures corresponding to the enterprise and matching degrees of the matching measures; and pushing the matching measures to the enterprise according to the matching degree of the matching measures.
The embodiment of the application adopts at least one technical scheme which can achieve the following beneficial effects:
the embodiment of the application applies a big data technology, enterprise information is retrieved in a pre-constructed enterprise portrait label library, enterprise portrait labels are determined, then the enterprise portrait labels are matched in the pre-constructed measure label library, enterprise intelligence matching meeting measure conditions can be achieved, corresponding measures are accurately pushed to an enterprise, the enterprise can know measure support obtained by the enterprise, and information is communicated with the government in real time.
Drawings
In order to more clearly explain the technical solutions of the present application, some embodiments of the present application will be described in detail below with reference to the accompanying drawings, in which:
fig. 1 is a schematic flowchart of an enterprise measure matching method based on big data according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of an enterprise measure matching device based on big data according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following embodiments and accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Some embodiments of the present application are described in detail below with reference to the accompanying drawings.
Fig. 1 is a schematic flowchart of a big-data-based enterprise measure matching method according to an embodiment of the present application, where the flowchart may be executed by computing devices in corresponding fields, and some input parameters or intermediate results in the flowchart allow manual intervention and adjustment to help improve accuracy.
The computing device related to the embodiment of the present application may be a terminal device or a server, and the present application is not limited in this respect. For convenience of understanding and description, the following embodiments are described in detail by taking a server as an example.
It should be noted that the server may be a single device, or may be a system composed of multiple devices, that is, a distributed server, which is not specifically limited in this application.
The process in fig. 1 may include the following steps:
s101: and acquiring enterprise information uploaded by the enterprise in the measure matching system.
It should be noted that, at this time, the enterprise does not match the system for the first login measure.
S102: and searching enterprise information in a pre-constructed enterprise portrait label library to determine an enterprise portrait label.
Specifically, when the server constructs an enterprise portrait label library, the server firstly acquires multi-source information related to an enterprise, for example, massive internet data related to enterprise credit evaluation, including enterprise multi-dimensional data such as enterprise management conditions, enterprise development and development, enterprise management risks, judicial risks and public opinion data, are crawled through a big data acquisition technology, and data parameters can be supplemented and improved automatically after the enterprise logs in a system.
Secondly, the server preprocesses the multi-source information, determines the preprocessed multi-source information, and then learns knowledge of the preprocessed multi-source information to obtain potential knowledge among the preprocessed multi-source information. And thirdly, performing knowledge reasoning on the multi-source information after the knowledge learning to determine a knowledge graph corresponding to the enterprise, and finally, performing portrait on the enterprise through the knowledge graph to determine a portrait label of the enterprise to construct a portrait label library of the enterprise.
When the server preprocesses the multi-source information, different business data in the multi-source information are subjected to data quality evaluation adaptive to the data according to a preset quantity quality evaluation model, and then the data are perfected according to evaluation reverse tracking data, so that the multi-source information is screened, and effective multi-source information can be obtained. It should be noted that the server establishes a data quality evaluation model according to the data quality evaluation index system and the requirements of data quality detection in production.
Then, the server fuses the screened multi-source information, gathers the fused multi-source information in a pre-constructed standard data warehouse, and builds a standard data catalog in the standard data warehouse to provide standard data service. It should be noted that the server performs data fusion on the screened multi-source information by using large data processing technologies such as ETL and large data technology components such as Hadoop, Spark, Storm, and Kafka.
Further, when the server learns knowledge of the preprocessed multi-source information, the server predicts the value of an inquiry predicate in the multi-source information through a discriminant knowledge learning algorithm DSL based on a set predicate table, performs weight learning on the multi-source information through an unconstrained optimization algorithm L-BFGS to obtain potential knowledge among the preprocessed multi-source information, and then generates an initial network structure corresponding to a knowledge graph through the potential knowledge among the preprocessed multi-source information.
That is to say, because a large amount of knowledge is hidden under the surface layer data, the value of the query predicate is predicted under the condition of the given evidence predicate by means of the discriminant knowledge learning algorithm DSL, and the L-BFGS algorithm is used for weight learning, so that a network structure with a reasonable structure is generated.
Further, when the server conducts knowledge reasoning on the multi-source information after knowledge learning, firstly, knowledge reasoning is conducted on the relation between entities of the multi-source information through a deep learning Lazy-MC-SAT algorithm on the basis of an initial network structure, then the initial network structure is updated according to the knowledge reasoning result, and a knowledge graph corresponding to an enterprise is determined.
Namely, based on the model learned in the knowledge learning stage and the weight thereof, the Lazy-MC-SAT algorithm is used for reasoning the relationship between the entities and the entity attributes.
Furthermore, when the server figures the enterprise through the knowledge graph, the enterprise is pictured in a graph mode. The server can analyze the enterprise situation through the dimensions of enterprise credit, development stage, scientific research capability and the like, and can visually check all aspects of information of the enterprise.
It should be noted that, when an enterprise logs in a platform for the first time, the enterprise itself is labeled according to the enterprise typing standard. When the enterprise marks the labels, the source enterprise label dictionary ensures the standardized management of the enterprise labels. The enterprise tag may be maintained and modified by the enterprise user at the personal center. The platform provides a verification function for self-maintenance and modification of enterprise users so as to conveniently ensure the accuracy and the rigor of enterprise labels. The enterprise label dictionary information is managed independently, and information such as an enterprise label code value, a label name, remarks and the like can be maintained.
S103: and matching the enterprise portrait tags in a pre-constructed measure tag library, and determining matching measures corresponding to enterprises and matching degrees of the matching measures.
Specifically, when the server constructs the measure tag library, firstly, the multi-source measure information is acquired. And secondly, carrying out structuring processing on the multi-source measure information and determining the structuring measure information. And finally, setting a label code value and a label name for the structural measure information according to the data dictionary mode, and determining the label of the structural measure information to construct a measure label library.
When multi-source measure information is obtained, the server automatically captures the measure information of a set website, matches the measure information of the set website with the measure information uploaded by government departments, if the matching fails, the measure information of the set website and links of the set website are pushed to relevant governments, and in addition, the server is associated with a preset news platform to automatically update the multi-source measure information.
For example, in order to collect the acquired measures as comprehensively as possible, the server automatically captures the measure information supporting the development of small and medium-sized micro-enterprises, which is published by three levels of relevant government websites of province, city and county through an automatic means, matches and compares the measure information with the measures collected and published by the platform, and if the measures are found not collected, the measure matching system can display the uncollected measure information to corresponding departments in an interface display mode and provide links for capturing the measure information. And the issuing function is reminded, and a higher department can check the measures gathered at lower level and higher level so as to supervise and prompt the measures to be gathered and issued as soon as possible.
For example, the measure is divided into structured conditions such as measure basis, subject enjoyment, condition enjoyment, preference content, material for filing, flow for filing, time for filing, and execution period. The intelligent change technology is utilized to perform labeling processing on the measures and establish measure labels, such as measure names, departure mechanisms, text numbers, texts, main measures, industry types, support objects, support conditions and the like.
It should be noted that, when the measures are collected and released, the relevant government departments may also classify the measures and label the measures. If no corresponding label exists in the measure label dictionary, the user can add a new label on the label page, and when the label is added, the server can match the similar label and prompt to avoid the repeated construction of the measure label dictionary.
S104: and pushing the matching measures to the enterprise according to the matching degree of the matching measures.
Specifically, the server sorts the data according to the matching degree, preferentially screens measures suitable for enterprise declaration to perform matching pushing, and prompts the enterprise to adjust and perfect the data or know and understand the guidability of the enterprise development direction for measure back-row pushing with low matching degree.
Further, after the server pushes the matching measures to the enterprise, the monitoring enterprise declares the request of the matching measures, extracts enterprise materials uploaded by the enterprise when the request is monitored, automatically performs cross check on the multiple data of the enterprise materials according to the requirements of the matching measures, and prohibits the enterprise from declaring the matching measures if the check fails, so that the enterprise is prevented from cheating the supplementary behavior by counterfeiting related proving materials, the data can be prevented from running out more ways, the enterprise runs less legs, the enterprise declaration effort and declaration cost are reduced, and the enterprise can concentrate on business development.
If the verification is successful, whether the enterprise authorizes the auxiliary declaration is judged, if so, declaration information to be filled is obtained from the enterprise portrait label library, and the declaration information is automatically filled to the corresponding position so as to assist the enterprise in declaring. For example, after the enterprise selects the measure matched with the pushing, the declaration form and the declaration material are analyzed after the declaration is clicked, the enterprise automatically shares the administration affairs after authorization and then carries out auxiliary filling on the basic information, the operation information and the information which is filled by the enterprise once, and the enterprise checks and simply supplements the private information to confirm the submission. And after the intelligent audit of the measure matching system is passed, pushing the data to relevant departments for on-line audit feedback.
For example, the user enters an application page to submit application information, wherein the application information mainly includes some compliance application files, and is provided for compliance verification by a measure support department in an attachment uploading mode. Different application requirements are submitted according to the difference needs of the measures, different requirement lists are listed aiming at the measure customized application page, and the system provides necessary filling and unnecessary filling verification. When the enterprise applies for the information-related measures, the platform can compare and find whether the application enterprise has the preliminary conditions for applying the information-related measures or not according to the background data information. And if the condition is not met, informing the enterprise that the application condition is not met, and forbidding the enterprise to submit the application. The platform provides an automatic checking function for enterprise application, guides enterprises to submit applications and upload related requirements according to specifications, improves accuracy of information application of special funds, improves application efficiency and reduces repeated operation. The platform supports the association display of measures and featured credit products and the convenient application of related measures. The user can also check related measures in the measure pushing and measure browsing interface and initiate measure application operation.
It should be noted that, although the embodiment of the present application describes steps 101 to S104 in sequence with reference to fig. 1, this does not mean that steps S101 to S104 must be executed in strict sequence. The embodiment of the present application is described by sequentially describing step S101 to step S104 according to the sequence shown in fig. 1, so as to facilitate those skilled in the art to understand the technical solutions of the embodiment of the present application. In other words, in the embodiment of the present application, the sequence between step S101 and step S104 may be appropriately adjusted according to actual needs.
By the method of the figure 1, a big data technology is applied, enterprise information is retrieved in a pre-constructed enterprise portrait label library to determine enterprise portrait labels, then the enterprise portrait labels are matched in the pre-constructed measure label library, enterprises meeting measure conditions can be intelligently matched, corresponding measures can be accurately pushed to the enterprises, the enterprises can know measure support obtained by the enterprises, and the information between the enterprises and governments is communicated in real time.
Next, the explanation of the measure matching system is continued, and the measure matching system includes a measure collecting module, a measure matching module, a measure displaying module, and a measure implementing module.
The measure display module is used for displaying measures collected by the measure matching system, the enterprise portrait module is used for generating enterprise portrait labels, the measure labeling module is used for labeling the measures, and the measure implementation module is used for knowing the condition of enterprise declaration measures.
The measure collection module comprises measure collection display and measure management. The measure collection display comprises issuing of a prompt and automatic updating. The measure management comprises measure information issuing, measure issuing auditing and measure off-shelf management.
The release reminding means reminding release, in order to realize that the released measures are collected as comprehensively as possible, the system automatically captures the measure information supporting the development of small and medium-sized micro-enterprises, which is released by three levels of relevant government websites of province, city and county through an automatic means, matches and compares the measure information with the measures collected and released by the system, and if the measures are found not collected, the system can display the uncollected measure information to corresponding departments in an interface display mode and simultaneously provide links for capturing the measure information. And the issuing function is reminded, and a higher department can check the measures gathered at lower level and higher level so as to supervise and prompt the measures to be gathered and issued as soon as possible.
The automatic updating refers to associating preset measures or news sources and periodically and automatically updating the news consultation and measure information of the platform.
The measure information issuing means that measure files are subjected to structuring and standardized processing, related departments issue financing measure support files through a system, and enterprises can look up and read related measures through the system and enjoy measure intelligent matching and recommendation services. The method comprises the steps of providing a measure collecting and issuing function, providing an operation interface to support the structured input of measure files, and inputting measures according to the names of the measure files, the measure execution departments, the text numbers, the specific measure, the support objects, the support conditions and other decomposition structures to form a structured measure information base.
The measure collecting and issuing function provides two operations of storing and issuing, only the issued measure files can be formally used by all users in the whole system, the undisleased measure files are stored, and only the user can inquire and edit. And the measure is collected and issued, the uploading of the measure file attachment is provided, and the user can download the corresponding measure file.
The step of modifying the measure information is to provide a function of modifying and editing the measure information, provide a function of modifying the measure if the released measure information is found to be wrong or needs to be modified and perfected after the measures are collected and released, and re-release the measure information after the relevant measure information is modified.
The measure issuing and auditing means that the corresponding administrator needs to perform auditing when the measure information is issued and modified, and the auditing opinions are filled in and recorded during auditing, and then corresponding processing is performed after the auditing is passed. The measure issuing and auditing process can be configured in a user-defined mode.
The measure shelf-off management means that the measure shelf-off is divided into automatic shelf-off and manual shelf-off, and the measure information after shelf-off is invisible to other users of the system and still stored in the measure information base. The system judges according to the validity period of the measures and realizes automatic shelf setting of the failure measures. The automatic shelf unloading function of the measures realizes that the measures with the past validity period are automatically subjected to shelf unloading treatment according to the validity period. The system provides measures for manual shelf unloading operation, a user selects the measures needing to be unloaded to perform the manual shelf unloading operation, the shelf unloading operation can configure an approval process, and the shelf unloading operation approval is realized.
In the measure matching module, enterprise information is searched in the enterprise portrait tag library by establishing a measure tag library and an enterprise portrait tag library to determine enterprise portrait tags, and then the enterprise portrait tags are matched in the measure tag library to determine matching measures corresponding to enterprises.
The measure display module comprises measure checking, measure inquiring, news information, measure publicity, measure forum, manual service and intelligent interaction.
The measure viewing means that a user accesses a platform to view all measure lists, and can click and view detailed information of each measure, including measure texts, reading information and the like. And supporting classified display of the measure information. The user can perform action attachment download, online preview, printing, and the like.
The measure query means providing two query tools of 'precise query' and 'fuzzy query', and meeting the requirement that enterprises, financial institutions, government related departments and the like look up published measure contents according to actual needs. The measure query function provides a search exchange interface, and a user can perform accurate query or fuzzy query according to conditions such as measure names, channel-leaving mechanisms, text numbers, texts, main measures and the like.
The news information is related information news which is displayed and can be displayed according to classification, so that the user can conveniently and finely check the news information, and the user can obtain the latest financial information in one-stop mode. The news information provides a query and search function, so that a user can conveniently search the news information, and the user can input keywords to search the news information related to the title and the content.
And the platform sets a measure implementation bulletin column, the window displays the specific subsidy issuing condition of the implementation of the relevant measures by a rolling effect, and the user clicks an accessible measure subsidy detail page. The measure implementation subsidy data comes from autonomous statistics after the measure is imported on the line. The measure supplementary notice can set a notice period, and notice information exceeding the notice period is not displayed in the notice bulletin rolling window but can be displayed in a notice information list.
The measure forum provides the functions of measure appeal, discussion, comment, consultation, interpretation, public opinion processing and the like, and the measure comment sediment data provides reference for each part of the government to modify and perfect measures, so that the government measures are ensured to accurately land.
The manual service is that the system reads and displays the measure files in a convenient, understandable and lively and friendly display mode. The measure interpretation establishes a measure interpretation knowledge base, the measure interpretation knowledge base is in butt joint with a government affair service hot line, a 24h 'measure interpretation' artificial service hot line is opened, and according to the principle of 'who goes out and who interprets', the hot line is transferred to a measure-out government-related department to realize one-to-one interpretation.
The intelligent interaction means that an intelligent robot answers the inquiry of the civil and camp enterprises on line by establishing an intelligent consultation service function by utilizing an artificial intelligence technology, a big data analysis technology and the like, and an answering scheme is automatically generated. The system gradually improves the answer library through the standardized carding of the measure library and the enrichment and perfection of the question library, trains the intelligent customer service line to answer through a voice and character recognition automatic matching scheme through the self-learning of the machine, and reduces the work load of the staff for answering. Meanwhile, a grading feedback function of the user on the answers is provided, and the system automatically optimizes the answering function.
The measure implementation module provides system operation conditions such as measure release quantity, enterprise declaration conditions, application process links, measure matching conditions and the like, statistical analysis is carried out from multiple dimensions such as industry, regions, time and the like, and results are displayed in a graphical mode. The manager can master the service operation condition generally. And functions of exporting, downloading, printing on line and the like of the general report are provided.
The measure implementation module comprises a measure pre-evaluation system, a measure statistical analysis system, enterprise declaration condition statistics, measure matching condition statistics and measure visual display.
The measure evaluation system refers to the steps of tracking the enterprise conditions (such as enterprise states, operation conditions and the like) after enjoying measure support, evaluating after measures of big data, analyzing the measure support effect and the like.
The measure statistical analysis system is used for counting the measure release quantity, the platform provides measure release quantity statistics, the measures are distributed and counted according to types, distributed and counted according to regions, trend statistics of the time of nearly 12 months, statistics according to industries and the like, and the statistics provides graphical and tabular displays. And functions of exporting, downloading, printing on line and the like of the general report are supported.
The enterprise declaration condition statistics refers to providing enterprise declaration condition statistics, and includes distribution statistics according to enterprise types, distribution statistics according to the number of the enterprise types and the measure types, distribution statistics according to the areas where the enterprises are located, statistics according to the trend of the time of the enterprises in about 12 months, statistics according to the enterprise industry and the like, and the statistics provides graphical and tabular presentations. And functions of exporting, downloading, printing on line and the like of the general report are supported. The platform provides statistics of the condition of the measure application process, including carding statistics according to process nodes, benchmarking statistics according to node processing time, comparison statistics according to average time area of process processing, statistics according to process processing efficiency and the like, and the statistics provides graphical and tabular displays. Support functions of exporting, downloading and printing a general report form on line
The measure matching condition statistics refers to providing measure matching condition statistics, including statistics according to enterprise type matching conditions, statistics according to regional comparison measure matching conditions, statistics according to enterprise industry measure matching conditions, statistics according to time measure matching conditions and the like, and statistics provides graphical and tabular displays. Support functions of exporting, downloading and printing a general report form on line
The visual display of the measures refers to accessing the analysis function or data of the measures, constructing the analysis function of the measures and comprehensively analyzing the condition of falling to the ground of the measures of the civil enterprises. The main indexes comprise: measure coverage, measure fund release condition, measure execution effect, unit release measure comparison, measure declaration flow analysis, declaration deadline comparison and the like. Meanwhile, the method predicts the requirement condition of the measure based on the enjoying condition of the existing measure and provides analysis reference data for the measure formulation unit.
Based on the same idea, some embodiments of the present application further provide a device and a non-volatile computer storage medium corresponding to the above method.
Fig. 2 is a schematic structural diagram of an enterprise measure matching device based on big data according to an embodiment of the present application, including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
acquiring enterprise information uploaded by an enterprise in the measure matching system;
searching enterprise information in a pre-constructed enterprise portrait label library to determine an enterprise portrait label;
matching enterprise portrait labels in a pre-constructed measure label library, and determining matching measures corresponding to enterprises and matching degrees of the matching measures;
and pushing the matching measures to the enterprise according to the matching degree of the matching measures.
Some embodiments of the present application provide a big-data based enterprise measure matching non-volatile computer storage medium storing computer-executable instructions configured to:
acquiring enterprise information uploaded by an enterprise in the measure matching system;
searching enterprise information in a pre-constructed enterprise portrait label library to determine an enterprise portrait label;
matching enterprise portrait labels in a pre-constructed measure label library, and determining matching measures corresponding to enterprises and matching degrees of the matching measures;
and pushing the matching measures to the enterprise according to the matching degree of the matching measures.
The embodiments in the present application are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the device and media embodiments, the description is relatively simple as it is substantially similar to the method embodiments, and reference may be made to some descriptions of the method embodiments for relevant points.
The device and the medium provided by the embodiment of the application correspond to the method one to one, so the device and the medium also have the similar beneficial technical effects as the corresponding method, and the beneficial technical effects of the method are explained in detail above, so the beneficial technical effects of the device and the medium are not repeated herein.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the technical principle of the present application shall fall within the protection scope of the present application.
Claims (10)
1. A big data-based enterprise measure matching method is characterized by comprising the following steps:
acquiring enterprise information uploaded by an enterprise in the measure matching system;
searching the enterprise information in a pre-constructed enterprise portrait label library to determine an enterprise portrait label;
matching the enterprise portrait tags in a pre-constructed measure tag library, and determining matching measures corresponding to the enterprise and matching degrees of the matching measures;
and pushing the matching measures to the enterprise according to the matching degree of the matching measures.
2. The method of claim 1, wherein determining the pre-built enterprise portrait tag library specifically comprises:
acquiring multi-source information related to an enterprise;
preprocessing the multi-source information, and determining preprocessed multi-source information;
performing knowledge learning on the preprocessed multi-source information to obtain potential knowledge among the preprocessed multi-source information;
carrying out knowledge reasoning on the multi-source information after knowledge learning, and determining a knowledge graph corresponding to an enterprise;
and carrying out portrait on the enterprise through the knowledge graph, and determining the enterprise portrait tags so as to construct the enterprise portrait tag library.
3. The method of claim 2, wherein the learning knowledge of the pre-processed multi-source information to obtain the latent knowledge between the multi-source information comprises:
predicting the value of query predicates in the multi-source information through a discriminant knowledge learning algorithm DSL based on a set predicate table, and performing weight learning on the multi-source information through an unconstrained optimization algorithm L-BFGS to obtain potential knowledge among the preprocessed multi-source information;
and generating an initial network structure corresponding to the knowledge graph through the potential knowledge among the preprocessed multi-source information.
4. The method according to claim 3, wherein the performing knowledge reasoning on the multi-source information after knowledge learning to determine the knowledge graph corresponding to the enterprise specifically comprises:
based on the initial network structure, carrying out knowledge reasoning on the relation between the entities of the multi-source information through a deep learning Lazy-MC-SAT algorithm;
and updating the initial network structure according to the knowledge reasoning result, and determining the knowledge graph corresponding to the enterprise.
5. The method according to claim 1, wherein determining the pre-constructed measure tag library specifically comprises:
acquiring multi-source measure information;
carrying out structuring processing on the multi-source measure information, and determining the structuring measure information;
and setting a label code value and a label name for the structural measure information according to a data dictionary mode, and determining a label of the structural measure information to construct the measure label library.
6. The method according to claim 5, wherein the obtaining multi-source measure information specifically comprises:
automatically capturing measure information of a set website;
matching the measure information of the set website with the measure information uploaded by a government department, and if the matching fails, pushing the measure information of the set website and the link of the set website to a relevant government;
and associating a preset news platform to automatically update the multi-source measure information.
7. The method of claim 1, wherein after pushing the matching measure to the enterprise according to the matching degree of the matching measure, the method comprises:
monitoring a request for the enterprise to declare the matching measure;
extracting enterprise material uploaded by the enterprise based on the request;
according to the requirements of the matching measures, automatically performing multiple data cross check on the enterprise materials;
and if the verification fails, forbidding the enterprise to declare the matching measures.
8. The method of claim 7, wherein after automatically performing a plurality of data cross-checks on the enterprise material as required by the matching action, the method further comprises:
if the verification is successful, judging whether the enterprise authorizes the auxiliary declaration;
if yes, obtaining declaration information to be filled in from the enterprise portrait label library, and automatically filling the declaration information to a corresponding position to assist the enterprise in declaration.
9. An enterprise measure matching device based on big data, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
acquiring enterprise information uploaded by an enterprise in the measure matching system;
searching the enterprise information in a pre-constructed enterprise portrait label library to determine an enterprise portrait label;
matching the enterprise portrait tags in a pre-constructed measure tag library, and determining matching measures corresponding to the enterprise and matching degrees of the matching measures;
and pushing the matching measures to the enterprise according to the matching degree of the matching measures.
10. A big-data based enterprise-measure-matching non-volatile computer-storage medium storing computer-executable instructions configured to:
acquiring enterprise information uploaded by an enterprise in the measure matching system;
searching the enterprise information in a pre-constructed enterprise portrait label library to determine an enterprise portrait label;
matching the enterprise portrait tags in a pre-constructed measure tag library, and determining matching measures corresponding to the enterprise and matching degrees of the matching measures;
and pushing the matching measures to the enterprise according to the matching degree of the matching measures.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111264058.3A CN114021001A (en) | 2021-10-28 | 2021-10-28 | Enterprise measure matching method, device and medium based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111264058.3A CN114021001A (en) | 2021-10-28 | 2021-10-28 | Enterprise measure matching method, device and medium based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114021001A true CN114021001A (en) | 2022-02-08 |
Family
ID=80058615
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111264058.3A Pending CN114021001A (en) | 2021-10-28 | 2021-10-28 | Enterprise measure matching method, device and medium based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114021001A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116932919A (en) * | 2023-09-15 | 2023-10-24 | 中关村科学城城市大脑股份有限公司 | Information pushing method, device, electronic equipment and computer readable medium |
| CN117035695A (en) * | 2023-10-08 | 2023-11-10 | 之江实验室 | Information early warning method and device, readable storage medium and electronic equipment |
| CN117075948A (en) * | 2023-10-12 | 2023-11-17 | 阿里巴巴(成都)软件技术有限公司 | Method, equipment and medium for detecting software online |
| CN117390232A (en) * | 2023-11-30 | 2024-01-12 | 金网络(北京)数字科技有限公司 | Enterprise portrait construction method, system, equipment and storage medium |
-
2021
- 2021-10-28 CN CN202111264058.3A patent/CN114021001A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116932919A (en) * | 2023-09-15 | 2023-10-24 | 中关村科学城城市大脑股份有限公司 | Information pushing method, device, electronic equipment and computer readable medium |
| CN116932919B (en) * | 2023-09-15 | 2023-11-24 | 中关村科学城城市大脑股份有限公司 | Information pushing method, device, electronic equipment and computer readable medium |
| CN117035695A (en) * | 2023-10-08 | 2023-11-10 | 之江实验室 | Information early warning method and device, readable storage medium and electronic equipment |
| CN117035695B (en) * | 2023-10-08 | 2024-03-05 | 之江实验室 | Information early warning method and device, readable storage medium and electronic equipment |
| CN117075948A (en) * | 2023-10-12 | 2023-11-17 | 阿里巴巴(成都)软件技术有限公司 | Method, equipment and medium for detecting software online |
| CN117075948B (en) * | 2023-10-12 | 2023-12-26 | 阿里巴巴(成都)软件技术有限公司 | Method, equipment and medium for detecting software online |
| CN117390232A (en) * | 2023-11-30 | 2024-01-12 | 金网络(北京)数字科技有限公司 | Enterprise portrait construction method, system, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114021001A (en) | Enterprise measure matching method, device and medium based on big data | |
| Burdick et al. | Extracting, linking and integrating data from public sources: A financial case study | |
| US8032511B1 (en) | System and method for presenting categorized content on a site using programmatic and manual selection of content items | |
| US8407218B2 (en) | Role based search | |
| CN112182246B (en) | Method, system, medium, and application for creating an enterprise representation through big data analysis | |
| CN1754181A (en) | A surveying apparatus and method thereof | |
| JP2011516938A (en) | Systems and methods for measuring and managing distributed online conversations | |
| KR102121901B1 (en) | System for online public fund investment management assessment service | |
| Mossalam et al. | Using artificial neural networks (ANN) in projects monitoring dashboards’ formulation | |
| US20060004701A1 (en) | System and method for adaptive decision making analysis and assessment | |
| Eppler | A generic framework for information quality in knowledge-intensive processes | |
| Lutz et al. | Analyzing industry stakeholders using open-source competitive intelligence–a case study in the automotive supply industry | |
| Rasmussen | Data quality in online environments | |
| US20190079957A1 (en) | Centralized feature management, monitoring and onboarding | |
| CN115982429B (en) | Knowledge management method and system based on flow control | |
| Liu et al. | Robots and protest: does increased protest among Chinese workers result in more automation? | |
| Toivonen | Big data quality challenges in the context of business analytics | |
| Long | [Retracted] Analysis of Insurance Marketing Planning Based on BD‐Guided Decision Tree Classification Algorithm | |
| Tsvetkov et al. | The data dilemma: how availability can threaten the competitive advantage of data-based firms | |
| Abdullah et al. | Decision making using document driven decision support systems | |
| Shabana et al. | A study on Big data advancement and Big data analytics | |
| Vitari et al. | An Analysis Framework For The Evaluation Of Content Management Systems (CMS) | |
| Yu et al. | Knowledge management in E-commerce: A data mining perspective | |
| CN110750701B (en) | Crawler-based network promotion effect evaluation method | |
| Selleras | Predictive model: using text mining for determining factors leading to high-scoring answers in stack overflow |
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 |