CN114398477A - Policy recommendation method based on knowledge graph and related equipment thereof - Google Patents
Policy recommendation method based on knowledge graph and related equipment thereof Download PDFInfo
- Publication number
- CN114398477A CN114398477A CN202210057430.1A CN202210057430A CN114398477A CN 114398477 A CN114398477 A CN 114398477A CN 202210057430 A CN202210057430 A CN 202210057430A CN 114398477 A CN114398477 A CN 114398477A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- policy
- data
- target
- entity
- 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 50
- 230000009193 crawling Effects 0.000 claims abstract description 12
- 239000013598 vector Substances 0.000 claims description 55
- 230000011218 segmentation Effects 0.000 claims description 31
- 230000004927 fusion Effects 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000000547 structure data Methods 0.000 claims description 9
- 238000013075 data extraction Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 239000000463 material Substances 0.000 description 11
- PXHVJJICTQNCMI-UHFFFAOYSA-N Nickel Chemical compound [Ni] PXHVJJICTQNCMI-UHFFFAOYSA-N 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- QPLDLSVMHZLSFG-UHFFFAOYSA-N Copper oxide Chemical class [Cu]=O QPLDLSVMHZLSFG-UHFFFAOYSA-N 0.000 description 3
- 229910017052 cobalt Inorganic materials 0.000 description 3
- 239000010941 cobalt Substances 0.000 description 3
- GUTLYIVDDKVIGB-UHFFFAOYSA-N cobalt atom Chemical compound [Co] GUTLYIVDDKVIGB-UHFFFAOYSA-N 0.000 description 3
- 229910052759 nickel Inorganic materials 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000013145 classification model Methods 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 241000238413 Octopus Species 0.000 description 1
- 240000002834 Paulownia tomentosa Species 0.000 description 1
- 235000010678 Paulownia tomentosa Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- 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
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application belongs to the technical field of big data, is applied to the field of intelligent government affairs, and relates to a policy recommendation method based on a knowledge graph and related equipment thereof, wherein the policy recommendation method comprises the steps of crawling policy information of a target website to obtain policy text data; performing label generation operation on the policy text data to obtain a policy category label, and converting the policy text data into structured data to obtain structural policy data; constructing an industry knowledge graph based on the relationship between the industry entities and the industry entities; acquiring enterprise information of an enterprise to be recommended, reasoning enterprise associated information of the enterprise to be recommended from an industrial knowledge map based on the enterprise information, and taking the enterprise information and the enterprise associated information as target enterprise data of the enterprise to be recommended; and calculating the matching degree of the structure policy data and the target enterprise data, and recommending the corresponding policy text data to the enterprise to be recommended when the matching degree reaches a matching threshold value. The industry knowledge map may be stored in a blockchain. The policy recommendation method and the policy recommendation device improve the policy recommendation accuracy.
Description
Technical Field
The application relates to the technical field of big data, in particular to a policy recommendation method based on a knowledge graph and related equipment thereof.
Background
In order to build a good operator environment, various favorable enterprises and policies can be timely released by government departments at all levels, but the benign development of enterprises is influenced due to the conditions of multiple policies, large total amount, difficulty in searching, difficulty in understanding terms of the policies and the like.
At present, although a policy recommending mode for an enterprise exists according to a knowledge graph, the problem of inaccurate recommendation often exists, and the requirement of the enterprise cannot be met.
Disclosure of Invention
The embodiment of the application aims to provide a policy recommendation method based on a knowledge graph and related equipment thereof, and the policy recommendation accuracy is improved.
In order to solve the above technical problem, an embodiment of the present application provides a policy recommendation method based on a knowledge graph, which adopts the following technical solutions:
a policy recommendation method based on knowledge graph comprises the following steps:
crawling operation is carried out on the policy information of the target website to obtain policy text data;
performing label generation operation on the policy text data to obtain a policy category label, and converting the policy text data into structured data based on the policy category label to obtain structural policy data;
receiving an industry document, extracting an industry entity and an industry entity relationship from the industry document, and constructing an industry knowledge graph based on the industry entity and the industry entity relationship;
acquiring enterprise information of an enterprise to be recommended, reasoning enterprise associated information of the enterprise to be recommended from the industrial knowledge map based on the enterprise information, and taking the enterprise information and the enterprise associated information as target enterprise data of the enterprise to be recommended;
and calculating the matching degree of the structure policy data and the target enterprise data, and recommending corresponding policy text data to the enterprise to be recommended when the matching degree reaches a matching threshold value.
Further, the step of reasoning the enterprise associated information of the enterprise to be recommended from the industry knowledge graph based on the enterprise information comprises:
identifying enterprise entities from the enterprise information, matching the enterprise entities with industrial entities of the industrial knowledge graph, and taking the successfully matched industrial entities as target industrial entities;
determining an industrial entity which has a connection relation with the target industrial entity in the industrial knowledge graph as a target enterprise entity;
and determining an enterprise information relationship based on the target industrial entity and the target enterprise entity, and generating the enterprise association information according to the enterprise entity, the target enterprise entity and the enterprise information relationship.
Further, the step of determining a business information relationship based on the target industry entity and the target business entity comprises:
determining whether the target industrial entity is directly connected with the target business entity;
if the target industrial entity and the target enterprise entity are directly connected through one edge in the industrial knowledge graph, taking the industrial entity relationship corresponding to the edge connecting the target industrial entity and the target enterprise entity as the enterprise information relationship;
and if the target industrial entity and the target enterprise entity are indirectly connected in the industrial knowledge graph through a plurality of edges, taking the industrial entity relationship corresponding to the last edge from the target industrial entity to the target enterprise entity as the enterprise information relationship.
Further, the step of extracting industry entities and industry entity relationships from the industry document includes:
performing word segmentation processing on the industrial document to obtain a plurality of industrial words;
carrying out entity identification operation on the industrial words to obtain a plurality of industrial entities;
converting the industrial entity into an entity vector, acquiring position information of the industrial entity in the industrial document, and generating a position vector based on the position information;
fusing the entity vectors and the position vectors of any two industrial entities in the same sentence of the industrial document to obtain a fusion characteristic;
and inputting the fusion characteristics into a pre-trained convolutional neural network to obtain an output industrial entity relationship.
Further, the step of performing a tag generation operation on the policy text data to obtain a policy category tag includes:
calling a preset word segmentation tool, and replacing a dictionary of the word segmentation tool with a preset policy dictionary to obtain a target word segmentation tool;
performing word segmentation operation on the policy text data through the target word segmentation tool to obtain a plurality of initial policy words;
removing stop words from the initial policy words to obtain target policy words;
inputting the target policy words into a vector model trained in advance to obtain word vectors;
and performing classification prediction based on the word vector, and outputting the corresponding policy category label.
Further, the step of using the enterprise information and the enterprise-related information as target enterprise data includes:
taking the enterprise information and the enterprise correlation information as initial enterprise data;
identifying initial enterprise data belonging to a geographic location as geographic data;
and taking the provincial name to which the geographic data belongs as target geographic data, and replacing the geographic data with the target geographic data to obtain the target enterprise data.
Further, the step of calculating the matching degree of the structure policy data and the target enterprise data comprises:
determining a key policy label from the policy category labels, and performing data extraction operation on the structure policy data based on the key policy label to obtain target structure data;
generating a plurality of enterprise data categories through the target enterprise data, taking the enterprise data categories which are the same as the key policy labels as key enterprise categories, and performing data extraction operation on the target enterprise data through the key enterprise categories to obtain key enterprise data;
converting the target structure data and the key enterprise data into a target structure vector and a key enterprise vector respectively;
and calculating the cosine similarity of the target structure vector and the key enterprise vector to obtain the matching degree.
In order to solve the above technical problem, an embodiment of the present application further provides a policy recommendation device based on a knowledge graph, which adopts the following technical solutions:
a knowledge-graph based policy recommendation apparatus comprising:
the crawling module is used for crawling policy information of the target website to obtain policy text data;
the conversion module is used for carrying out label generation operation on the policy text data to obtain a policy category label, and converting the policy text data into structured data based on the policy category label to obtain structured policy data;
the extraction module is used for receiving an industrial document, extracting an industrial entity and an industrial entity relationship from the industrial document, and constructing an industrial knowledge graph based on the industrial entity and the industrial entity relationship;
the inference module is used for acquiring enterprise information of an enterprise to be recommended, inferring enterprise associated information of the enterprise to be recommended from the industry knowledge map based on the enterprise information, and taking the enterprise information and the enterprise associated information as target enterprise data of the enterprise to be recommended;
and the calculation module is used for calculating the matching degree of the structure policy data and the target enterprise data, and recommending the corresponding policy text data to the enterprise to be recommended when the matching degree reaches a matching threshold value.
In order to solve the above technical problem, an embodiment of the present application further provides a computer device, which adopts the following technical solutions:
a computer device comprising a memory having computer readable instructions stored therein and a processor that when executed performs the steps of the above-described method of knowledge-map based policy recommendation.
In order to solve the above technical problem, an embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solutions:
a computer readable storage medium having computer readable instructions stored thereon which, when executed by a processor, implement the steps of the above-described method for knowledge-graph based policy recommendation.
Compared with the prior art, the embodiment of the application mainly has the following beneficial effects:
according to the method and the device, the policy category label is generated according to the crawled policy text data, and then the policy text data is converted into the structure policy data, so that subsequent matching degree calculation is facilitated. And reasoning enterprise associated information from the constructed industrial knowledge map according to the acquired enterprise information, thereby realizing the completion of the enterprise information. And then, the matching degree is calculated through target enterprise data consisting of the enterprise information and the enterprise associated information and the structural policy data, so that when the matching degree reaches a matching threshold value, a corresponding policy is recommended to the enterprise to be recommended, and the accuracy and the precision of the policy recommended to the enterprise are improved.
Drawings
In order to more clearly illustrate the solution of the present application, the drawings needed for describing the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow diagram of one embodiment of a knowledge-graph based policy recommendation method according to the present application;
FIG. 3 is a schematic diagram of an embodiment of a knowledge-graph based policy recommendation apparatus according to the present application;
FIG. 4 is a schematic block diagram of one embodiment of a computer device according to the present application.
Reference numerals: 200. a computer device; 201. a memory; 202. a processor; 203. a network interface; 300. a knowledge-graph based policy recommendation device; 301. a crawling module; 302. a conversion module; 303. an extraction module; 304. an inference module; 305. and a calculation module.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof, in the description and claims of this application and the description of the above figures are intended to cover non-exclusive inclusions. The terms "first," "second," and the like in the description and claims of this application or in the above-described drawings are used for distinguishing between different objects and not for describing a particular order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
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 accompanying drawings.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have various communication client applications installed thereon, such as a web browser application, a shopping application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (moving Pi picture Experts Group Aud I o Layer I, mpeg compression standard audio Layer 3), MP4 players (moving Pi picture Experts Group Aud I o Layer IV, mpeg compression standard audio Layer 4), laptop and desktop computers, etc.
The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.
It should be noted that the method for recommending policies based on knowledge graph provided in the embodiment of the present application is generally executed by a server/terminal device, and accordingly, a device for recommending policies based on knowledge graph is generally disposed in the server/terminal device.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow diagram of one embodiment of a knowledge-graph based policy recommendation method in accordance with the present application is shown. The policy recommendation method based on the knowledge graph comprises the following steps:
s1: and crawling operation is carried out on the policy information of the target website to obtain policy text data.
In this embodiment, policy information is crawled from various related channels (such as government websites) through the octopus crawler system to obtain full-text policies.
S2: and performing label generation operation on the policy text data to obtain a policy category label, and converting the policy text data into structured data based on the policy category label to obtain structural policy data.
In this embodiment, a tag generation operation is performed on the policy text data to obtain a policy category tag. The policy category label comprises information such as industry category, acceptance department, region, city, support force, declaration time, declaration material, declaration condition, declaration system, policy source, policy category and the like. And converting text data of the policy into structured data according to the generated policy category label.
Specifically, in step S2, the step of performing a tag generation operation on the policy text data to obtain a policy category tag includes:
calling a preset word segmentation tool, and replacing a dictionary of the word segmentation tool with a preset policy dictionary to obtain a target word segmentation tool;
performing word segmentation operation on the policy text data through the target word segmentation tool to obtain a plurality of initial policy words;
removing stop words from the initial policy words to obtain target policy words;
inputting the target policy words into a vector model trained in advance to obtain word vectors;
and performing classification prediction based on the word vector, and outputting the corresponding policy category label.
In this embodiment, the training process: the pre-collected full policy text is divided into a training set and a testing set. The test set only contains full text of policies for testing; the training set comprises a policy full text and a policy category corresponding to the policy full text and is used for training a vector model (word2vec), specifically, a Stanford word segmentation tool is called, word segmentation operation is carried out on the training set through a preset policy dictionary, stop words are removed, then word2vec is trained according to a word segmentation result and a policy category label, and word vectors related to the policy category are learned by the word2 vec;
the application process comprises the following steps: performing word segmentation operation on policy text data through a word segmentation tool, removing stop words to obtain a plurality of target policy words, inputting the target policy words into a vector model (word2vec), obtaining word vectors, performing classification prediction based on the word vectors, and outputting corresponding policy category labels. Specifically, the word vector is input into a pre-trained classification model (NPL model), and an output classification result, that is, a policy class label, is obtained.
In addition, the method for converting the policy text data into the structured data based on the policy category label includes the steps of: segmenting the policy text data based on the policy category label to obtain policy segment data; generating the structured policy data based on a correspondence of the policy category label and the policy fragment data. And performing structured label extraction on the crawled policy document through a word2vec model, wherein the following is a result example of the structured policy data generated based on the policy category label:
s3: receiving an industry document, extracting an industry entity and an industry entity relation from the industry document, and constructing an industry knowledge graph based on the industry entity and the industry entity relation.
In this embodiment, an industry knowledge graph is constructed that contains an industry name, and a related product name. For example, leading edge materials (industry name) include new energy materials (industry name) that include nickel, cobalt, copper oxides (related product name). The industry entities comprise industry names, enterprise names and product names. The method and the system are used for subsequently complementing the relevant information of the enterprise by constructing the industrial knowledge map.
In this embodiment, the electronic device (e.g., the server/terminal device shown in fig. 1) on which the knowledge-graph-based policy recommendation method operates may receive the industry document through a wired connection or a wireless connection. It should be noted that the wireless connection means may include, but is not limited to, a 3G/4G connection, a Wi Fi connection, a bluetooth connection, a Wi MAX connection, a zigbee connection, a uwb (u l tra Wi band) connection, and other wireless connection means now known or developed in the future.
Specifically, in step S3, the step of extracting the industry entities and the industry entity relationships from the industry document includes:
performing word segmentation processing on the industrial document to obtain a plurality of industrial words;
carrying out entity identification operation on the industrial words to obtain a plurality of industrial entities;
converting the industrial entity into an entity vector, acquiring position information of the industrial entity in the industrial document, and generating a position vector based on the position information;
fusing the entity vectors and the position vectors of any two industrial entities in the same sentence of the industrial document to obtain a fusion characteristic;
and inputting the fusion characteristics into a pre-trained convolutional neural network to obtain an output industrial entity relationship.
In this embodiment, obtaining the industrial entity relationship between the industrial entities is achieved by fusing the vectors of the industrial entities in the same sentence in the industrial document. The specific fusion mode is numerical addition of the corresponding dimensionalities of the vectors or vector splicing operation.
S4: acquiring enterprise information of an enterprise to be recommended, reasoning enterprise associated information of the enterprise to be recommended from the industrial knowledge graph based on the enterprise information, and taking the enterprise information and the enterprise associated information as target enterprise data of the enterprise to be recommended.
In this embodiment, enterprise information is obtained through enterprise data source data such as enterprise research, industry and commerce bureau, etc., but the enterprise information obtained from the network is incomplete, and the information of the enterprise needs to be supplemented through an industrial knowledge map. That is, enterprise-related information is inferred from the industry knowledge graph based on the acquired enterprise information. The enterprise information and the enterprise associated information constitute complete information of the enterprise. For example, from the information of the industry and the commerce, Zhejiang M corporation, 22.05.2002, registered in Zhejiang province and commerce administration. The legal representatives are old XX, and the names of the main products of enterprises comprise research, development, production and sale: cobalt, nickel, copper oxides, and the like. Through the established industry knowledge map, the cobalt, nickel and copper oxides belong to the advanced materials, namely new energy materials, and Zhejiang M corporation is inferred to belong to the new energy materials industry. And taking the new energy materials as enterprise associated information. By the method, the basic information of the enterprise, the industry information of the enterprise and the main and operating product information of the enterprise are collected, the information of the enterprise is perfected, and the target enterprise data is obtained.
Specifically, in step S4, the step of inferring the enterprise-related information of the enterprise to be recommended from the industry knowledge graph based on the enterprise information includes:
identifying enterprise entities from the enterprise information, matching the enterprise entities with industrial entities of the industrial knowledge graph, and taking the successfully matched industrial entities as target industrial entities;
determining an industrial entity which has a connection relation with the target industrial entity in the industrial knowledge graph as a target enterprise entity;
and determining an enterprise information relationship based on the target industrial entity and the target enterprise entity, and generating the enterprise association information according to the enterprise entity, the target enterprise entity and the enterprise information relationship.
In this embodiment, the target industry entity is determined by matching the enterprise entity with the industry entity, so that the target enterprise entity in the industry knowledge graph is determined according to the target industry entity, and the target enterprise entity is a part of the content of the enterprise associated information. And connecting the enterprise entity and the target enterprise entity through the enterprise information relationship to generate enterprise correlation information. For example, the enterprise information relationship belongs to, the enterprise entity is Zhejiang M corporation, and the target enterprise entity is new energy material. The generated enterprise association information is: zhejiang M corporation is a company belonging to new energy materials.
Wherein the step of determining a business information relationship based on the target industry entity and the target business entity comprises:
determining whether the target industrial entity is directly connected with the target business entity;
if the target industrial entity and the target enterprise entity are directly connected through one edge in the industrial knowledge graph, taking the industrial entity relationship corresponding to the edge connecting the target industrial entity and the target enterprise entity as the enterprise information relationship;
and if the target industrial entity and the target enterprise entity are indirectly connected in the industrial knowledge graph through a plurality of edges, taking the industrial entity relationship corresponding to the last edge from the target industrial entity to the target enterprise entity as the enterprise information relationship.
In this embodiment, under the condition that the target industrial entity is indirectly connected to the target business entity, multiple edges need to be passed through, and multiple business information relationships may occur, at this time, since the target business entity is a component of the business information relationship, the business entity relationship corresponding to the last edge passed from the target industrial entity to the target business entity, that is, the business entity relationship closest to the target business entity, is used as the business information relationship, so that the accuracy of the obtained business information relationship can be higher.
In addition, in step S4, the step of regarding the business information and the business-related information as target business data includes:
taking the enterprise information and the enterprise correlation information as initial enterprise data;
determining the provincial name to which the geographic data of the initial enterprise data belong as target geographic data;
and replacing the geographic data of the initial enterprise data with the target geographic data to obtain the target enterprise data.
In this embodiment, the enterprise basic information, the industry information to which the enterprise belongs, and the enterprise main-operation product information are collected and an enterprise map is constructed by the method according to the province-zhejiang that the enterprise belongs to. For example: [ Enterprise ] Zhejiang M company limited-the city to which it belongs [ City ] Tongxiang. For example, if the enterprise belongs to the rural area, the policy of reasoning all the Zhejiang provinces based on the city map is also applicable. In the subsequent matching process, from the region dimension: [ Enterprise ] - [ city ] - [ Tung village ] of Zhejiang M Limited company-the city to which it belongs; [ policy ] Zhejiang province high and new technology enterprises cultivate and store-suitable for- [ province ] Zhejiang; [ CHINESE PARTS ] Zhejiang-including cities [ cities ] Tongxiang. The reason is that the Zhejiang province high and new technology enterprises are suitable for cultivation and warehousing-Zhejiang M company Limited.
S5: and calculating the matching degree of the structure policy data and the target enterprise data, and recommending corresponding policy text data to the enterprise to be recommended when the matching degree reaches a matching threshold value.
In this embodiment, the policy category label is matched with the enterprise label, so that a policy applicable to an enterprise is inferred and recommended to the corresponding enterprise. From the industrial dimension: [ Enterprise ] -Zhejiang M company limited-belongs to [ industry ] -leading edge materials-new energy materials; [ policy ] Zhejiang province high and new technology enterprises cultivate and store in-application industry- [ industry ] leading-edge materials-new energy materials. Reasoning out: [ policy ] Zhejiang province high and new technology enterprises cultivate and store-suitable for-enterprises [ enterprises ] Zhejiang M Limited. The matching degree can be used by directly comparing the word overlapping degree of the structure policy data and the target enterprise data.
Specifically, in step S5, the step of calculating the matching degree between the structure policy data and the target enterprise data includes:
determining a key policy label from the policy category labels, and performing data extraction operation on the structure policy data based on the key policy label to obtain target structure data;
generating a plurality of enterprise data categories through the target enterprise data, taking the enterprise data categories which are the same as the key policy labels as key enterprise categories, and performing data extraction operation on the target enterprise data through the key enterprise categories to obtain key enterprise data;
converting the target structure data and the key enterprise data into a target structure vector and a key enterprise vector respectively;
and calculating the cosine similarity of the target structure vector and the key enterprise vector to obtain the matching degree.
In this embodiment, the specific process of determining the key policy tags from the policy category tags is to use the policy category tags selected by the user in the front-end page as the key policy tags. When the matching degree is calculated, the structural policy data and the target enterprise data are screened through the key policy tags, the matching degree is calculated according to the target structural data obtained after screening and the key enterprise data, the accuracy is improved, the calculation of key dimension data is realized, specifically, each sentence in the structural policy data corresponds to one policy category tag, the sentence corresponding to the key policy tag in the structural policy data is determined, and the sentence is extracted to serve as the target structural data. The key policy label comprises an industry category, a region, a policy category and a declaration condition. In the enterprise data category generation process, the pre-trained multi-label classification model pair is selected for classification, and a plurality of output enterprise data categories are obtained.
According to the method and the device, the policy category label is generated according to the crawled policy text data, and then the policy text data is converted into the structure policy data, so that subsequent matching degree calculation is facilitated. And reasoning enterprise associated information from the constructed industrial knowledge map according to the acquired enterprise information, thereby realizing the completion of the enterprise information. And then, the matching degree is calculated through target enterprise data consisting of the enterprise information and the enterprise associated information and the structural policy data, so that when the matching degree reaches a matching threshold value, a corresponding policy is recommended to the enterprise to be recommended, and the accuracy and the precision of the policy recommended to the enterprise are improved.
It is emphasized that to further ensure the privacy and security of the industry knowledge graph, the industry knowledge graph may also be stored in a blockchain node.
The block chain referred by the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. The block chain (B l ockchai n), which is essentially a decentralized database, is a string of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, which is used for verifying the validity (anti-counterfeiting) of the information and generating a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
This application can be applied to in the wisdom government affairs field to promote the construction in wisdom city.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware associated with computer readable instructions, which can be stored in a computer readable storage medium, and when executed, can include processes of the embodiments of the methods described above. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-only Memory (ROM), or a Random Access Memory (RAM).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
With further reference to fig. 3, as an implementation of the method shown in fig. 2, the present application provides an embodiment of a knowledge-graph-based policy recommendation apparatus, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be applied to various electronic devices.
As shown in fig. 3, the knowledge-graph-based policy recommendation apparatus 300 according to the present embodiment includes: crawling module 301, translating module 302, extracting module 303, reasoning module 304, and calculating module 305. Wherein: the crawling module 301 is configured to perform crawling operation on policy information of a target website to obtain policy text data; the conversion module 302 is configured to perform a tag generation operation on the policy text data to obtain a policy category tag, and convert the policy text data into structured data based on the policy category tag to obtain structured policy data; the extraction module 303 is configured to receive an industry document, extract an industry entity and an industry entity relationship from the industry document, and construct an industry knowledge graph based on the industry entity and the industry entity relationship; the inference module 304 is configured to acquire enterprise information of an enterprise to be recommended, infer enterprise associated information of the enterprise to be recommended from the industry knowledge graph based on the enterprise information, and use the enterprise information and the enterprise associated information as target enterprise data of the enterprise to be recommended; the calculating module 305 is configured to calculate a matching degree between the structure policy data and the target enterprise data, and recommend corresponding policy text data to the enterprise to be recommended when the matching degree reaches a matching threshold.
In the embodiment, the policy category label is generated according to the crawled policy text data, and then the policy text data is converted into the structural policy data, so that the subsequent matching degree calculation is facilitated. And reasoning enterprise associated information from the constructed industrial knowledge map according to the acquired enterprise information, thereby realizing the completion of the enterprise information. And then, the matching degree is calculated through target enterprise data consisting of the enterprise information and the enterprise associated information and the structural policy data, so that when the matching degree reaches a matching threshold value, a corresponding policy is recommended to the enterprise to be recommended, and the accuracy and the precision of the policy recommended to the enterprise are improved.
The conversion module 302 comprises a replacement submodule, a word segmentation submodule, a removal submodule, an input submodule and a classification submodule, wherein the replacement submodule is used for calling a preset word segmentation tool and replacing a dictionary of the word segmentation tool with a preset policy dictionary to obtain a target word segmentation tool; the word segmentation sub-module is used for carrying out word segmentation operation on the policy text data through the target word segmentation tool to obtain a plurality of initial policy words; the removing submodule is used for removing stop words from the initial policy words to obtain target policy words; the input submodule is used for inputting the target policy words into a vector model trained in advance to obtain word vectors; the classification submodule is used for performing classification prediction based on the word vector and outputting the corresponding policy category label.
The extraction module 303 comprises an industry word obtaining sub-module, an identification sub-module, a conversion sub-module, a fusion sub-module and a relation determination sub-module, wherein the obtaining sub-module is used for performing word segmentation processing on the industry document to obtain a plurality of industry words; the identification submodule is used for carrying out entity identification operation on the industrial words to obtain a plurality of industrial entities; the conversion sub-module is used for converting the industrial entity into an entity vector, acquiring the position information of the industrial entity in the industrial document, and generating a position vector based on the position information; the fusion sub-module is used for fusing the entity vectors and the position vectors of any two industrial entities in the same sentence of the industrial document to obtain fusion characteristics; and the relation determining submodule is used for inputting the fusion characteristics into a pre-trained convolutional neural network to obtain an output industrial entity relation.
The inference module 304 comprises a matching submodule, a target enterprise entity determining submodule and a generating submodule, wherein the matching submodule is used for identifying an enterprise entity from the enterprise information, matching the enterprise entity with an industrial entity of the industrial knowledge map, and taking the successfully matched industrial entity as a target industrial entity; the target enterprise entity determining submodule is used for determining an industrial entity which has a connection relation with the target industrial entity in the industrial knowledge map and is used as a target enterprise entity; the generation submodule is used for determining an enterprise information relationship based on the target industrial entity and the target enterprise entity and generating the enterprise association information according to the enterprise entity, the target enterprise entity and the enterprise information relationship.
The generation submodule comprises a judgment unit, a first information relation determination unit and a second information relation determination unit, wherein the judgment unit is used for determining whether the target industrial entity is directly connected with the target enterprise entity; the first information relationship determining unit is configured to, when the target industry entity and the target enterprise entity are directly connected through one edge in the industry knowledge graph, use the industry entity relationship corresponding to the edge connecting the target industry entity and the target enterprise entity as the enterprise information relationship; the second information relationship determining unit is configured to, when the target industry entity and the target enterprise entity are indirectly connected through multiple edges in the industry knowledge graph, take the industry entity relationship corresponding to the last edge from the target industry entity to the target enterprise entity as the enterprise information relationship.
The inference module 304 further includes an initial enterprise data determination submodule, a target geographic data determination submodule, and a target enterprise data obtaining submodule, where the initial enterprise data determination submodule is configured to use the enterprise information and the enterprise-related information as initial enterprise data; the target geographic data determining submodule is used for determining the provincial name to which the geographic data of the initial enterprise data belong as target geographic data; the target enterprise data obtaining submodule is used for replacing the geographic data of the initial enterprise data with the target geographic data to obtain the target enterprise data.
The calculation module 305 includes a target structure data determination sub-module, a category generation sub-module, a vector conversion sub-module, and a matching degree sub-module, where the determination sub-module is configured to determine a key policy label from the policy category labels, and perform a data extraction operation on the structure policy data based on the key policy label to obtain target structure data; the category generation submodule is used for generating a plurality of enterprise data categories through the target enterprise data, taking the enterprise data categories which are the same as the key policy labels as key enterprise categories, and performing data extraction operation on the target enterprise data through the key enterprise categories to obtain key enterprise data; the vector conversion sub-module is used for converting the target structure data and the key enterprise data into a target structure vector and a key enterprise vector respectively; and the matching degree operator module is used for calculating the cosine similarity of the target structure vector and the key enterprise vector to obtain the matching degree.
According to the method and the device, the policy category label is generated according to the crawled policy text data, and then the policy text data is converted into the structure policy data, so that subsequent matching degree calculation is facilitated. And reasoning enterprise associated information from the constructed industrial knowledge map according to the acquired enterprise information, thereby realizing the completion of the enterprise information. And then, the matching degree is calculated through target enterprise data consisting of the enterprise information and the enterprise associated information and the structural policy data, so that when the matching degree reaches a matching threshold value, a corresponding policy is recommended to the enterprise to be recommended, and the accuracy and the precision of the policy recommended to the enterprise are improved.
In order to solve the technical problem, an embodiment of the present application further provides a computer device. Referring to fig. 4, fig. 4 is a block diagram of a basic structure of a computer device according to the present embodiment.
The computer device 200 comprises a memory 201, a processor 202, a network interface 203 communicatively connected to each other via a system bus. It is noted that only computer device 200 having components 201 and 203 is shown, but it is understood that not all of the illustrated components are required and that more or fewer components may alternatively be implemented. As will be understood by those skilled in the art, the computer device herein is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an application Specific integrated circuit (ASI C), a programmable gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.
The computer device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The computer equipment can carry out man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch panel or voice control equipment and the like.
The memory 201 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the storage 201 may be an internal storage unit of the computer device 200, such as a hard disk or a memory of the computer device 200. In other embodiments, the memory 201 may also be an external storage device of the computer device 200, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure digital (Secure Di gita l, SD) Card, a flash memory Card (F l ash Card), and the like, which are provided on the computer device 200. Of course, the memory 201 may also include both internal and external storage devices of the computer device 200. In this embodiment, the memory 201 is generally used for storing an operating system and various types of application software installed on the computer device 200, such as computer readable instructions of a knowledge-graph based policy recommendation method. Further, the memory 201 may also be used to temporarily store various types of data that have been output or are to be output.
The processor 202 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 202 is generally operative to control overall operation of the computer device 200. In this embodiment, the processor 202 is configured to execute computer readable instructions or process data stored in the memory 201, such as executing computer readable instructions of the knowledge-graph based policy recommendation method.
The network interface 203 may comprise a wireless network interface or a wired network interface, and the network interface 203 is generally used for establishing communication connection between the computer device 200 and other electronic devices.
In this embodiment, enterprise associated information is inferred from the established industry knowledge graph according to the acquired enterprise information, so that completion of the enterprise information is realized. The matching degree is calculated through target enterprise data consisting of the enterprise information and the enterprise associated information and the structural policy data, so that when the matching degree reaches a matching threshold value, a corresponding policy is recommended to the enterprise to be recommended, and the accuracy and precision of the policy recommended to the enterprise are improved.
The present application further provides another embodiment, which is to provide a computer-readable storage medium storing computer-readable instructions executable by at least one processor to cause the at least one processor to perform the steps of the method for knowledge-graph based policy recommendation as described above.
In this embodiment, enterprise associated information is inferred from the established industry knowledge graph according to the acquired enterprise information, so that completion of the enterprise information is realized. The matching degree is calculated through target enterprise data consisting of the enterprise information and the enterprise associated information and the structural policy data, so that when the matching degree reaches a matching threshold value, a corresponding policy is recommended to the enterprise to be recommended, and the accuracy and precision of the policy recommended to the enterprise are improved.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.
It is to be understood that the above-described embodiments are merely illustrative of some, but not restrictive, of the broad invention, and that the appended drawings illustrate preferred embodiments of the invention and do not limit the scope of the invention. This application is capable of embodiments in many different forms and is provided for the purpose of enabling a thorough understanding of the disclosure of the application. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that the present application may be practiced without modification or with equivalents of some of the features described in the foregoing embodiments. All equivalent structures made by using the contents of the specification and the drawings of the present application are directly or indirectly applied to other related technical fields and are within the protection scope of the present application.
Claims (10)
1. A policy recommendation method based on knowledge graph is characterized by comprising the following steps:
crawling operation is carried out on the policy information of the target website to obtain policy text data;
performing label generation operation on the policy text data to obtain a policy category label, and converting the policy text data into structured data based on the policy category label to obtain structural policy data;
receiving an industry document, extracting an industry entity and an industry entity relationship from the industry document, and constructing an industry knowledge graph based on the industry entity and the industry entity relationship;
acquiring enterprise information of an enterprise to be recommended, reasoning enterprise associated information of the enterprise to be recommended from the industrial knowledge map based on the enterprise information, and taking the enterprise information and the enterprise associated information as target enterprise data of the enterprise to be recommended;
and calculating the matching degree of the structure policy data and the target enterprise data, and recommending the corresponding policy text data to the enterprise to be recommended when the matching degree reaches a matching threshold value.
2. The knowledge-graph-based policy recommendation method according to claim 1, wherein the step of inferring business-related information of the business to be recommended from the industry knowledge graph based on the business information comprises:
identifying enterprise entities from the enterprise information, matching the enterprise entities with industrial entities of the industrial knowledge graph, and taking the successfully matched industrial entities as target industrial entities;
determining an industrial entity which has a connection relation with the target industrial entity in the industrial knowledge graph as a target enterprise entity;
and determining an enterprise information relationship based on the target industrial entity and the target enterprise entity, and generating the enterprise association information according to the enterprise entity, the target enterprise entity and the enterprise information relationship.
3. The knowledge-graph-based policy recommendation method of claim 2, wherein the step of determining business information relationships based on the target industry entity and the target business entity comprises:
determining whether the target industrial entity is directly connected with the target business entity;
if the target industrial entity and the target enterprise entity are directly connected through one edge in the industrial knowledge graph, taking the industrial entity relationship corresponding to the edge connecting the target industrial entity and the target enterprise entity as the enterprise information relationship;
and if the target industrial entity and the target enterprise entity are indirectly connected in the industrial knowledge graph through a plurality of edges, taking the industrial entity relationship corresponding to the last edge from the target industrial entity to the target enterprise entity as the enterprise information relationship.
4. The knowledge-graph-based policy recommendation method of claim 1, wherein the step of extracting industrial entities and industrial entity relationships from the industrial document comprises:
performing word segmentation processing on the industrial document to obtain a plurality of industrial words;
carrying out entity identification operation on the industrial words to obtain a plurality of industrial entities;
converting the industrial entity into an entity vector, acquiring position information of the industrial entity in the industrial document, and generating a position vector based on the position information;
fusing the entity vectors and the position vectors of any two industrial entities in the same sentence of the industrial document to obtain a fusion characteristic;
and inputting the fusion characteristics into a pre-trained convolutional neural network to obtain an output industrial entity relationship.
5. The knowledge-graph-based policy recommendation method according to claim 1, wherein the step of performing a tag generation operation on the policy text data to obtain a policy category tag comprises:
calling a preset word segmentation tool, and replacing a dictionary of the word segmentation tool with a preset policy dictionary to obtain a target word segmentation tool;
performing word segmentation operation on the policy text data through the target word segmentation tool to obtain a plurality of initial policy words;
removing stop words from the initial policy words to obtain target policy words;
inputting the target policy words into a vector model trained in advance to obtain word vectors;
and performing classification prediction based on the word vector, and outputting the corresponding policy category label.
6. The knowledge-graph-based policy recommendation method of claim 1, wherein the step of using the business information and the business-related information as target business data comprises:
taking the enterprise information and the enterprise correlation information as initial enterprise data;
determining the provincial name to which the geographic data of the initial enterprise data belong as target geographic data;
and replacing the geographic data of the initial enterprise data with the target geographic data to obtain the target enterprise data.
7. The knowledge-graph-based policy recommendation method of claim 1, wherein the step of calculating the matching degree of the structure policy data and the target enterprise data comprises:
determining a key policy label from the policy category labels, and performing data extraction operation on the structure policy data based on the key policy label to obtain target structure data;
generating a plurality of enterprise data categories through the target enterprise data, taking the enterprise data categories which are the same as the key policy labels as key enterprise categories, and performing data extraction operation on the target enterprise data through the key enterprise categories to obtain key enterprise data;
converting the target structure data and the key enterprise data into a target structure vector and a key enterprise vector respectively;
and calculating the cosine similarity of the target structure vector and the key enterprise vector to obtain the matching degree.
8. A knowledge-graph-based policy recommendation apparatus, comprising:
the crawling module is used for crawling policy information of the target website to obtain policy text data;
the conversion module is used for carrying out label generation operation on the policy text data to obtain a policy category label, and converting the policy text data into structured data based on the policy category label to obtain structured policy data;
the extraction module is used for receiving an industrial document, extracting an industrial entity and an industrial entity relationship from the industrial document, and constructing an industrial knowledge graph based on the industrial entity and the industrial entity relationship;
the inference module is used for acquiring enterprise information of an enterprise to be recommended, inferring enterprise associated information of the enterprise to be recommended from the industry knowledge map based on the enterprise information, and taking the enterprise information and the enterprise associated information as target enterprise data of the enterprise to be recommended;
and the calculation module is used for calculating the matching degree of the structure policy data and the target enterprise data, and recommending the corresponding policy text data to the enterprise to be recommended when the matching degree reaches a matching threshold value.
9. A computer device comprising a memory having computer readable instructions stored therein and a processor that when executed performs the steps of the method of knowledge-graph based policy recommendation of any one of claims 1-7.
10. A computer readable storage medium having computer readable instructions stored thereon which, when executed by a processor, implement the steps of the knowledge-graph based policy recommendation method of any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210057430.1A CN114398477A (en) | 2022-01-19 | 2022-01-19 | Policy recommendation method based on knowledge graph and related equipment thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210057430.1A CN114398477A (en) | 2022-01-19 | 2022-01-19 | Policy recommendation method based on knowledge graph and related equipment thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114398477A true CN114398477A (en) | 2022-04-26 |
Family
ID=81230680
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210057430.1A Pending CN114398477A (en) | 2022-01-19 | 2022-01-19 | Policy recommendation method based on knowledge graph and related equipment thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114398477A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117435817A (en) * | 2023-12-20 | 2024-01-23 | 泰安北航科技园信息科技有限公司 | BI intelligent center system based on industry big data |
CN117609432A (en) * | 2023-12-21 | 2024-02-27 | 中国疾病预防控制中心慢性非传染性疾病预防控制中心 | Method for realizing intelligent policy retrieval through label extraction strategy |
CN117708350A (en) * | 2024-02-06 | 2024-03-15 | 成都草根有智创新科技有限公司 | Enterprise policy information association method and device and electronic equipment |
CN117743564A (en) * | 2024-01-30 | 2024-03-22 | 广东省华南技术转移中心有限公司 | Automatic extraction and recommendation method and system for technological policy information |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112395410A (en) * | 2021-01-13 | 2021-02-23 | 北京智源人工智能研究院 | Entity extraction-based industry public opinion recommendation method and device and electronic equipment |
CN112579753A (en) * | 2020-12-17 | 2021-03-30 | 京东数字科技控股股份有限公司 | Information acquisition method, device, equipment, medium and product |
CN112765441A (en) * | 2021-04-07 | 2021-05-07 | 北京零号窗网络信息技术有限公司 | Enterprise policy information multiple dynamic intelligent matching recommendation method for digital government affairs |
CN113505242A (en) * | 2021-07-16 | 2021-10-15 | 珍岛信息技术(上海)股份有限公司 | Method and system for automatically embedding knowledge graph |
-
2022
- 2022-01-19 CN CN202210057430.1A patent/CN114398477A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112579753A (en) * | 2020-12-17 | 2021-03-30 | 京东数字科技控股股份有限公司 | Information acquisition method, device, equipment, medium and product |
CN112395410A (en) * | 2021-01-13 | 2021-02-23 | 北京智源人工智能研究院 | Entity extraction-based industry public opinion recommendation method and device and electronic equipment |
CN112765441A (en) * | 2021-04-07 | 2021-05-07 | 北京零号窗网络信息技术有限公司 | Enterprise policy information multiple dynamic intelligent matching recommendation method for digital government affairs |
CN113505242A (en) * | 2021-07-16 | 2021-10-15 | 珍岛信息技术(上海)股份有限公司 | Method and system for automatically embedding knowledge graph |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117435817A (en) * | 2023-12-20 | 2024-01-23 | 泰安北航科技园信息科技有限公司 | BI intelligent center system based on industry big data |
CN117435817B (en) * | 2023-12-20 | 2024-03-15 | 泰安北航科技园信息科技有限公司 | BI intelligent center system based on industry big data |
CN117609432A (en) * | 2023-12-21 | 2024-02-27 | 中国疾病预防控制中心慢性非传染性疾病预防控制中心 | Method for realizing intelligent policy retrieval through label extraction strategy |
CN117743564A (en) * | 2024-01-30 | 2024-03-22 | 广东省华南技术转移中心有限公司 | Automatic extraction and recommendation method and system for technological policy information |
CN117743564B (en) * | 2024-01-30 | 2024-05-10 | 广东省华南技术转移中心有限公司 | Automatic extraction and recommendation method and system for technological policy information |
CN117708350A (en) * | 2024-02-06 | 2024-03-15 | 成都草根有智创新科技有限公司 | Enterprise policy information association method and device and electronic equipment |
CN117708350B (en) * | 2024-02-06 | 2024-05-14 | 成都草根有智创新科技有限公司 | Enterprise policy information association method and device and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114398477A (en) | Policy recommendation method based on knowledge graph and related equipment thereof | |
WO2022174491A1 (en) | Artificial intelligence-based method and apparatus for medical record quality control, computer device, and storage medium | |
CN112101437A (en) | Fine-grained classification model processing method based on image detection and related equipment thereof | |
CN112686022A (en) | Method and device for detecting illegal corpus, computer equipment and storage medium | |
CN112231569A (en) | News recommendation method and device, computer equipment and storage medium | |
CN113220734A (en) | Course recommendation method and device, computer equipment and storage medium | |
CN112650858A (en) | Method and device for acquiring emergency assistance information, computer equipment and medium | |
CN113836131A (en) | Big data cleaning method and device, computer equipment and storage medium | |
CN112632278A (en) | Labeling method, device, equipment and storage medium based on multi-label classification | |
CN112883730B (en) | Similar text matching method and device, electronic equipment and storage medium | |
CN113761577A (en) | Big data desensitization method and device, computer equipment and storage medium | |
CN112084342A (en) | Test question generation method and device, computer equipment and storage medium | |
CN113627797A (en) | Image generation method and device for employee enrollment, computer equipment and storage medium | |
CN114493255A (en) | Enterprise abnormity monitoring method based on knowledge graph and related equipment thereof | |
CN113987125A (en) | Text structured information extraction method based on neural network and related equipment thereof | |
CN112446209A (en) | Method, equipment and device for setting intention label and storage medium | |
CN112686053A (en) | Data enhancement method and device, computer equipment and storage medium | |
CN112084779A (en) | Entity acquisition method, device, equipment and storage medium for semantic recognition | |
CN111639360A (en) | Intelligent data desensitization method and device, computer equipment and storage medium | |
CN112528040B (en) | Detection method for guiding drive corpus based on knowledge graph and related equipment thereof | |
CN111797297B (en) | Page data processing method and device, computer equipment and storage medium | |
CN113743721A (en) | Marketing strategy generation method and device, computer equipment and storage medium | |
CN112417886A (en) | Intention entity information extraction method and device, computer equipment and storage medium | |
CN117133006A (en) | Document verification method and device, computer equipment and storage medium | |
CN115730603A (en) | Information extraction method, device, equipment and storage medium based on artificial intelligence |
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 |