CN111428037B - Method for analyzing matching performance of behavior policy - Google Patents
Method for analyzing matching performance of behavior policy Download PDFInfo
- Publication number
- CN111428037B CN111428037B CN202010211001.6A CN202010211001A CN111428037B CN 111428037 B CN111428037 B CN 111428037B CN 202010211001 A CN202010211001 A CN 202010211001A CN 111428037 B CN111428037 B CN 111428037B
- Authority
- CN
- China
- Prior art keywords
- policy
- text
- words
- keywords
- sentences
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/10—Tax strategies
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The application discloses a method for analyzing matching performance of a behavior policy, which comprises the following steps: acquiring a policy text from a pre-configured website; classifying the policy text to obtain the category of the policy text; acquiring an extraction mode corresponding to the category, wherein the extraction mode is used for indicating a mode of extracting keywords and/or sentences from the policy, the keywords and/or sentences are used for describing behaviors conforming to the policy text, and the extraction mode corresponding to the category is configured in advance; and extracting keywords and/or sentences from the policy text by using the extraction mode, and storing the keywords and/or sentences. The method and the device solve the problem that the related technology can not automatically prompt the content related to how to execute in the policy, provide an auxiliary means for manually analyzing the policy to a certain extent, and provide possibility for improving the comprehensiveness of policy analysis.
Description
Technical Field
The application relates to the field of data processing, in particular to a method for analyzing matching of a behavior policy.
Background
Policies are the standardized provision by the authorities of fighting objectives, principles of action followed, clear tasks performed, modes of work performed, general steps taken and specific measures that should be met within a certain historical period of time. The policy plays an important role in the national economic development process, the whole process of enterprise operation and development, or in the work, study and life of everyone.
After a policy is promulgated, the relevant personnel involved in the policy need to be aware of the policy. Generally, the policy includes various contents, such as the reason for making the policy, how the policy is executed, and other precautions of the policy. The relevant person sometimes only needs to know about the policy enforcement relevant content. Currently, policy texts need to be downloaded manually and then analyzed manually. In the prior art, the content of how to execute the policy cannot be automatically prompted, so that the manual analysis is completely relied on.
Disclosure of Invention
The application provides a method for analyzing the matching performance of a behavior policy, which aims to solve the problem that the related technology can not automatically prompt the content related to how to execute in the policy.
According to one aspect of the application, a method for analyzing matching performance of a behavior policy is provided, which comprises the following steps: acquiring a policy text from a pre-configured website; classifying the policy text to obtain the category of the policy text; acquiring an extraction mode corresponding to the category, wherein the extraction mode is used for indicating a mode for extracting keywords and/or sentences from the policy, the keywords and/or the sentences are used for describing behaviors conforming to the policy text, and the extraction mode corresponding to the category is configured in advance; and extracting keywords and/or sentences from the policy text by using the extraction mode, and storing the keywords and/or sentences.
Further, after obtaining the policy text from the preconfigured website, the method further comprises: and saving the corresponding relation between the policy text and the keywords and/or sentences.
Further, the method further comprises: receiving an acquisition request from a user, wherein the acquisition request is used for acquiring the policy text; in response to the acquisition request, returning the policy text and the keywords and/or sentences to the user.
Further, the website is an official website for issuing a policy, wherein the policy is a policy corresponding to the policy text.
According to another aspect of the present application, there is also provided a memory for storing software for performing the above method.
According to another aspect of the present application, there is also provided a processor for executing software, wherein the software is configured to perform the above method.
The application adopts the following steps: acquiring a policy text from a pre-configured website; classifying the policy text to obtain the category of the policy text; acquiring an extraction mode corresponding to the category, wherein the extraction mode is used for indicating a mode for extracting keywords and/or sentences from the policy, the keywords and/or the sentences are used for describing behaviors conforming to the policy text, and the extraction mode corresponding to the category is configured in advance; and extracting keywords and/or sentences from the policy text by using the extraction mode, and storing the keywords and/or sentences. The method and the device solve the problem that the related technology can not automatically prompt the content related to how to execute in the policy, provide an auxiliary means for manually analyzing the policy to a certain extent, and provide possibility for improving the comprehensiveness of policy analysis.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application. In the drawings:
fig. 1 is a flowchart of a method for analyzing matching of a behavior policy according to an embodiment of the present application.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances in order to facilitate the description of the embodiments of the application herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. 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). The 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 identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application 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.
In the present embodiment, a method for analyzing the matching of a behavior policy is provided, and although the method is used in policy data, the method may be used in other information, and in the following embodiments, policies may be replaced with information. For example, the information is a solution to a problem, and the following steps can be used to find out an action from the solution, which is the key to solve the problem, and then the background information such as the cause of the problem can be masked. Fig. 1 is a flowchart of a method for analyzing matching of a behavior policy according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
step S102, obtaining a policy text from a pre-configured website;
step S104, classifying the policy text to obtain the category of the policy text;
step S106, acquiring an extraction mode corresponding to the category, wherein the extraction mode is used for indicating a mode of extracting keywords and/or sentences from the policy, the keywords and/or sentences are used for describing behaviors conforming to the policy text, and the extraction mode corresponding to the category is configured in advance;
here, it is preferable that all dates are extracted, and the words of the dates are also extracted, and the words of the dates are stored as key sentences in step S108.
Step S108, extracting keywords and/or sentences from the policy text by using the extraction mode, and storing the keywords and/or sentences.
For example, in step S102, information may be captured from an official website according to a predetermined period, and the captured information may be manually determined whether the captured information is a policy, and if the captured information is a policy, the captured information is saved as a policy text. The policy is classified by the computer, for example, into a tax return class if a policy that is a tax return time is grasped. For the tax declaration category, the keyword is tax declaration time, and the search for the sentence including the tax declaration time is the extraction mode of the tax declaration category. The tax return time is used for expressing that tax return behaviors should be carried out at the time node, and the tax return behaviors are in accordance with the policy. The policy text is searched for that the tax declaring time is up to 12 months in the year, and the words are saved. This is in other words a measure of behavior included in the policy. The action may be sent to the user at the same time the user retrieves the policy. The method solves the problem that the related technology can not automatically prompt the content related to how to execute in the policy, provides an auxiliary means for manually analyzing the policy to a certain extent, and provides possibility for improving the comprehensiveness of policy analysis.
In step S104, there are many classification methods, for example, classification may be performed according to the names of policies, the names of policies are segmented, then the segmented words are matched with the words corresponding to the categories, and if matching is possible, the categories of the policy texts may be determined. Wherein, the words corresponding to the categories are pre-configured. For example, the pre-configured keywords of the tax declaration category are "tax" and "tax", and the pre-configured keywords of the high-new declaration category are "high-new". If the name of a policy includes the word "tax", the classification of the policy text is tax declaration.
The above steps can be implemented using a B/S architecture, and the content that the above steps need to be executed in the background is executed by a server, wherein the steps S102 to S108 can be executed by the server. The content to be presented may be implemented by a browser, for example, if a policy name in the previous paragraph is not matched to a category, the unmatched policy name may be displayed to an administrator in a webpage, and the administrator may manually classify the policy name.
As another alternative, if the policy name does not match the type, the matching may be done in the text of the policy, and if the policy text matches the tax, the tax declaration may be classified.
As another alternative, if the text of a policy includes keywords for multiple categories, it is possible to match multiple categories. This is not a problem, and in this case, in step S106, the extraction method corresponding to each category may be acquired. Or as another alternative, the word frequency in the policy body can be counted, and the category with high word frequency of the keywords can be selected as the type of the policy. For example, if "tax" appears three times and "high New" appears five times in the policy body, the policy type is a high New declaration type.
As another alternative, in the event that the policy header does not match successfully, the matching of the text may be performed using machine learning. With the continuous operation of websites, policies and policy categories accumulate more and more data, and when the accumulated data exceeds a threshold value, machine learning can be used for training. Training is performed using a plurality of sets of training data, each set of training data including a policy text and a category to which the policy text belongs. After training is complete, the model can be used for machine recognition. The input of the model is the text of the policy, and the output content is the category of the policy.
Preferably, after obtaining the policy text from the preconfigured website, the method may further include: the correspondence between the policy text and the keywords and/or sentences is saved.
Preferably, the method may further include: receiving an acquisition request from a user, wherein the acquisition request is used for acquiring a policy text; in response to the acquisition request, policy text is returned to the user along with keywords and/or sentences.
After receiving an acquisition request of a user, if a policy text corresponding to the request is not found, a policy query step may be performed first, after the query step is performed to find the policy, the steps from step S102 to step S108 are performed, and after keywords and/or sentences are obtained, the user returns to the user.
Step S202, receiving an inquiry message (i.e., an acquisition request), where the inquiry message is used to query a corresponding policy (or query corresponding information);
step S204, performing word segmentation processing on the text in the inquiry message to obtain a plurality of words;
as one preferred embodiment that may be added: the word segmentation may be performed by using a machine learning manner, for example, a model may be trained, the model is trained by using multiple sets of training data, each set of training data includes a piece of text and a word list obtained after the text is manually segmented, it should be noted that the manual segmentation result only includes key nouns, and the key nouns are words which are manually extracted and can embody the text center idea and appear in the text. The input of the model obtained by training with the training data is a piece of text, and the input result is a keyword. The word segmentation method can be used for word segmentation only related to other parts of the embodiment.
Step S206, determining at least one keyword from a plurality of words, wherein the keyword is used as a keyword for retrieval;
when selecting a keyword, the keyword may be matched with a pre-configured nonsense word list from a plurality of keywords, where the nonsense word list stores words such as dummy, auxiliary words, pronouns and the like that are not helpful for understanding the meaning of the text in advance, the nonsense word list is used to filter words, and the words in the nonsense word list are not used in the search in step S108. All the remaining words after matching can be used as keywords.
As an embodiment that can be added, after a plurality of words are matched by the nonsense word list, N words remain, firstly, N words are all used as keywords for searching, if the searched result is less than a predetermined number, one keyword is removed, then N-1 keywords are used for searching, if the searched result is still less than the predetermined data, the keywords are continuously removed for searching until the number of the searched results is greater than or equal to the predetermined number and less than a second predetermined number, wherein the second predetermined number is less than the predetermined number, namely, the number of the searched results is within a predefined range.
Step S208 is to search the keywords in a plurality of websites configured in advance to obtain search results corresponding to the keywords, and the content in the search results is used as the policy text in step S102. The plurality of websites are websites approved by certification, for example, official websites and the like. These websites typically only have policies.
Preferably, the website is an official website for issuing a policy, wherein the policy is a policy corresponding to the policy text.
In this embodiment, an apparatus is further provided, where modules in the apparatus correspond to the steps of the method described above, which have already been described in the above embodiments and are not described herein again.
There is also provided in this embodiment an apparatus comprising: the first acquisition module is used for acquiring a policy text from a pre-configured website; the classification module is used for classifying the policy text to obtain the category to which the policy text belongs; the second acquisition module is used for acquiring extraction modes corresponding to the categories, wherein the extraction modes are used for indicating a mode of extracting keywords and/or sentences from the policies, the keywords and/or the sentences are used for describing behaviors meeting the policy texts, and the extraction modes corresponding to the categories are pre-configured; and the storage module is used for extracting the keywords and/or sentences from the policy text by using the extraction mode and storing the keywords and/or sentences.
In this embodiment, a memory is provided for storing software for performing the above-described method.
In this embodiment, a processor is provided for executing software for performing the above-described method.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
An embodiment of the present invention provides a storage medium, on which a program or software is stored, the program implementing the above method when executed by a processor. The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (1)
1. A method for analyzing matching of a behavior policy, comprising:
step S102, obtaining a policy text from a pre-configured website;
step S104, classifying the policy text to obtain the category of the policy text; counting word frequency in the policy text, and selecting a category with high word frequency of keywords as the type of the policy; or, in case the policy title is not successfully matched, the matching of the text is performed using machine learning; the method comprises the steps that a plurality of groups of training data are used for training, and each group of training data comprises a policy text and a category to which the policy text belongs; after training is finished, the trained model can be used for machine recognition, the input of the model is a policy text, and the output content is the category of the policy;
step S106, obtaining an extraction mode corresponding to the category, wherein the extraction mode is used for indicating a mode of extracting keywords and/or sentences from the policy text, the keywords and/or the sentences are used for describing behaviors conforming to the policy text, and the extraction mode corresponding to the category is configured in advance;
step S108, extracting keywords and/or sentences from the policy text by using the extraction mode, and storing the keywords and/or sentences;
receiving an acquisition request from a user, wherein the acquisition request is used for acquiring a policy text,
returning policy text and keywords and/or sentences to the user in response to the acquisition request;
after receiving the obtaining request of the user, if a policy text corresponding to the request is not found, executing a policy query step, after the policy is found in the policy query step, executing the steps from step S102 to step S108, obtaining keywords and/or sentences, and returning to the user; wherein the policy querying step comprises:
step S204, performing word segmentation processing on the text in the acquisition request to obtain a plurality of words; the method comprises the steps that a word segmentation mode is carried out in a machine learning mode, a model is trained, the model is obtained by training a plurality of groups of training data, each group of training data comprises a section of text and a word list obtained after the text is segmented manually, the manual word segmentation result only comprises key nouns, the key nouns are words which are manually extracted and can embody the central thought of the text and appear in the text, the model obtained by training through the training data is input into the section of text, and the input result is a plurality of words obtained by word segmentation;
step S206, determining at least one keyword from a plurality of words, wherein the keyword is used as a keyword for retrieval; when the keywords are selected, matching a preset nonsense word list with the keywords, wherein the nonsense word list stores virtual words, auxiliary words and pronouns which do not help the understanding of the text meaning in advance, and is used for filtering words; all the rest matched words are used as key words; the method comprises the following steps that N words are left after a plurality of words are matched by a nonsense word list, the N words are used as key words for retrieval, if the retrieved result is smaller than a preset number, one key word is removed, then N-1 key words are used for retrieval, if the retrieved result is still smaller than preset data, the key words are continuously removed for retrieval until the number of the retrieved results is larger than or equal to the preset number and smaller than a second preset number, wherein the second preset number is smaller than the preset number;
step S208 is to search the keyword used for the search in a plurality of websites which are authenticated and approved in advance to obtain a search result corresponding to the keyword, and to use the content in the search result as the policy text acquired from the website which is configured in advance in step S102.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010211001.6A CN111428037B (en) | 2020-03-24 | 2020-03-24 | Method for analyzing matching performance of behavior policy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010211001.6A CN111428037B (en) | 2020-03-24 | 2020-03-24 | Method for analyzing matching performance of behavior policy |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111428037A CN111428037A (en) | 2020-07-17 |
| CN111428037B true CN111428037B (en) | 2022-09-20 |
Family
ID=71549042
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010211001.6A Active CN111428037B (en) | 2020-03-24 | 2020-03-24 | Method for analyzing matching performance of behavior policy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111428037B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113065050A (en) * | 2021-03-26 | 2021-07-02 | 深圳供电局有限公司 | Electricity price policy document collection method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103902652A (en) * | 2014-02-27 | 2014-07-02 | 深圳市智搜信息技术有限公司 | Automatic question-answering system |
| CN104360993A (en) * | 2014-11-19 | 2015-02-18 | 广州极盛信息科技开发有限公司 | Method for extracting needed content from text |
| CN107562732A (en) * | 2017-10-26 | 2018-01-09 | 北京康夫子科技有限公司 | The processing method and system of electronic health record |
| CN107577763A (en) * | 2017-09-04 | 2018-01-12 | 北京京东尚科信息技术有限公司 | Search method and device |
| WO2018032937A1 (en) * | 2016-08-19 | 2018-02-22 | 中兴通讯股份有限公司 | Method and apparatus for classifying text information |
| CN110457696A (en) * | 2019-07-31 | 2019-11-15 | 福州数据技术研究院有限公司 | A kind of talent towards file data and policy intelligent Matching system and method |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9798802B2 (en) * | 2012-03-23 | 2017-10-24 | Avast Software B.V. | Systems and methods for extraction of policy information |
| CN103870973B (en) * | 2012-12-13 | 2017-12-19 | 阿里巴巴集团控股有限公司 | Information push, searching method and the device of keyword extraction based on electronic information |
| CN105930452A (en) * | 2016-04-21 | 2016-09-07 | 北京紫平方信息技术股份有限公司 | Smart answering method capable of identifying natural language |
| CN114896374A (en) * | 2016-04-28 | 2022-08-12 | 荣耀终端有限公司 | Man-machine interaction method and device |
| CN108197109B (en) * | 2017-12-29 | 2021-04-23 | 北京百分点科技集团股份有限公司 | Multi-language analysis method and device based on natural language processing |
| CN108491438A (en) * | 2018-02-12 | 2018-09-04 | 陆夏根 | A kind of technology policy retrieval analysis method |
| CN110532451B (en) * | 2019-06-26 | 2023-08-29 | 平安科技（深圳）有限公司 | Method and device for searching policy text, storage medium and electronic device |
-
2020
- 2020-03-24 CN CN202010211001.6A patent/CN111428037B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103902652A (en) * | 2014-02-27 | 2014-07-02 | 深圳市智搜信息技术有限公司 | Automatic question-answering system |
| CN104360993A (en) * | 2014-11-19 | 2015-02-18 | 广州极盛信息科技开发有限公司 | Method for extracting needed content from text |
| WO2018032937A1 (en) * | 2016-08-19 | 2018-02-22 | 中兴通讯股份有限公司 | Method and apparatus for classifying text information |
| CN107577763A (en) * | 2017-09-04 | 2018-01-12 | 北京京东尚科信息技术有限公司 | Search method and device |
| CN107562732A (en) * | 2017-10-26 | 2018-01-09 | 北京康夫子科技有限公司 | The processing method and system of electronic health record |
| CN110457696A (en) * | 2019-07-31 | 2019-11-15 | 福州数据技术研究院有限公司 | A kind of talent towards file data and policy intelligent Matching system and method |
Non-Patent Citations (3)
| Title |
|---|
| Trained SVMs based rules extraction method for text classification;Miao Zhang et al.;《2008 IEEE International Symposium on IT in Medicine and Education》;20090109;第16-19页 * |
| 科技成果转化政策文本中的领域关键词汇提取研究;张越等;《中国科技资源导刊》;20180528(第03期);第68-75页 * |
| 观点挖掘中评价对象抽取方法的研究;刘倩;《中国优秀博硕士学位论文全文数据库(博士)信息科技辑》;20170215;第I138-228页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111428037A (en) | 2020-07-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2017076263A1 (en) | Method and device for integrating knowledge bases, knowledge base management system and storage medium | |
| CN110275965B (en) | False news detection method, electronic device and computer readable storage medium | |
| CN106815207B (en) | Information processing method and device for legal referee document | |
| CN108694178B (en) | Method and device for recommending judicial knowledge | |
| US10067965B2 (en) | Hierarchic model and natural language analyzer | |
| CN110458324B (en) | Method and device for calculating risk probability and computer equipment | |
| WO2015149690A1 (en) | Media content recommendation method and apparatus | |
| CN111767716A (en) | Method and device for determining enterprise multilevel industry information and computer equipment | |
| CN106878242B (en) | Method and device for determining user identity category | |
| WO2015084757A1 (en) | Systems and methods for processing data stored in a database | |
| CN114004694A (en) | Public opinion information-based enterprise risk early warning method, equipment and medium | |
| CN111428037B (en) | Method for analyzing matching performance of behavior policy | |
| CN116663505B (en) | Comment area management method and system based on Internet | |
| CN110874366A (en) | Data processing and query method and device | |
| CN112487181B (en) | Keyword determination method and related equipment | |
| CN112016317A (en) | Sensitive word recognition method and device based on artificial intelligence and computer equipment | |
| CN110532773B (en) | Malicious access behavior identification method, data processing method, device and equipment | |
| US11922326B2 (en) | Data management suggestions from knowledge graph actions | |
| CN110019659B (en) | Method and device for searching referee document | |
| CN109062551A (en) | Development Framework based on big data exploitation command set | |
| CN109739817B (en) | Method and system for storing data file in big data storage system | |
| CN113590805A (en) | Method and device for searching textile commodity names based on knowledge graph | |
| CN109948034B (en) | Method and device for extracting page information based on filtering session | |
| CN110019771B (en) | Text processing method and device | |
| CN110909533B (en) | Resource theme judging method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |