CN113780005A - Semantic model-based Handle stock identification analysis method - Google Patents
Semantic model-based Handle stock identification analysis method Download PDFInfo
- Publication number
- CN113780005A CN113780005A CN202111077324.1A CN202111077324A CN113780005A CN 113780005 A CN113780005 A CN 113780005A CN 202111077324 A CN202111077324 A CN 202111077324A CN 113780005 A CN113780005 A CN 113780005A
- Authority
- CN
- China
- Prior art keywords
- stock
- identification
- enterprise
- handle
- identifications
- 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.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000013507 mapping Methods 0.000 claims abstract description 21
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 238000012360 testing method Methods 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000013480 data collection Methods 0.000 claims description 3
- 238000007726 management method Methods 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 claims description 2
- 238000003860 storage Methods 0.000 claims 1
- 239000000203 mixture Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000005304 joining Methods 0.000 description 2
- 239000000470 constituent Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a semantic model-based Handle stock identification analysis method, which comprises the following steps: the method comprises the steps of preprocessing stock identifications in an enterprise, classifying the stock identifications through a naive Bayes algorithm, mapping the stock identifications to an established semantic knowledge model, and converting the stock identifications represented by the semantic knowledge model into unique Handle identifications according to a defined mapping rule. The invention establishes the mapping relation between the enterprise stock identifier and the Handle identifier so that the analysis of the stock identifier is converted into the analysis of the corresponding Handle identifier, thereby realizing the compatibility of the enterprise stock identifier and the Handle system.
Description
Technical Field
The invention belongs to the technical field of industrial internet identification analysis, relates to a semantic analysis method, and particularly relates to a Handle system-oriented industrial internet stock identification analysis method.
Background
The industrial internet identification carries out unique and unambiguous naming on people, materials and industrial equipment in industrial production by defining a coding format, provides support for sensing the physical world and information retrieval, and assists in developing various related applications. The function of the system is similar to the Internet domain name, each product, personnel, part and equipment are endowed with a unique 'ID card', and the resource differentiation and management are realized.
The existing identification analysis mode of the industrial internet needs that after an enterprise adds an identification analysis system, a unique analysis system identification is given to a product, so that a user can transmit information according to the identification to realize the function of identification analysis. However, products produced by the enterprise before joining the system are not registered in the existing industrial internet identification resolution system, and the products only have identifications of the identification system inside the enterprise, which are called stock identifications. Because the format of the stock mark is different from the existing mark analysis systems of the industrial Internet, the products cannot enjoy the analysis and application services brought by the industrial Internet mark analysis system through the mark in the process of passing. This increases the cost of enterprise joining the industrial internet, and is not favorable to the popularization of industrial internet in the enterprise.
In order to solve this problem, researchers have proposed a method of uniformly managing the inventory tags of resident enterprises (zhengsi source, an industrial internet tag parsing method, CN 201911318743.2). However, when the number of the resident enterprises is large, the inventory identification rule list maintained by the method becomes large and difficult to maintain, and the identification analysis efficiency is lowered. In the aspect of semantic models, although semantic models can be built through stock identifications and then analyzed, and query is carried out through semantic query languages, most of the existing semantic models are built by texts, and are used for processing unstructured data, which have no clear meaning or are hidden in texts and need inference analysis. The processing problem is focused on the relationship between data and data. However, most industrial internet inventory marks are structured and well-defined data. The main problem that we face is that the identification modes among these data are heterogeneous, that is, the same product may have various coding modes, which may be similar or completely different, so that the existing method for constructing semantic model cannot be directly used to implement semantic model construction of inventory identification and establish mapping relationship with Handle system.
Disclosure of Invention
The invention aims to overcome the problems in the prior art, provides a unified management method of enterprise stock identifications facing to a Handle analysis system, is used for solving the problem that the enterprise stock identifications and the Handle system are incompatible in the prior art, and converts the enterprise stock identifications into the Handle identifications. The method is particularly suitable for solving the problem of analysis of the inventory identification in the Handle system.
In order to realize the purpose of the invention, the technical scheme is as follows:
a method for analyzing the stock identity of Handle based on semantic model includes preprocessing the stock identity, classifying the preprocessed stock identity by naive Bayes algorithm, mapping classification result to semantic model, converting the stock identity represented by semantic model to be Handle identity by predefined rule, and converting the analysis of the stock identity to be that of the Handle identity. And the uniqueness of the semantic model represents the inventory identification of each enterprise, so that the analytic result is not ambiguous. The semantic model comprises a concept, an instance and an enterprise; the semantic model is constructed by mapping the classification result according to rules after classifying the stock identification through a naive Bayes algorithm.
The method comprises the following specific steps:
(1) and preprocessing the stock identification in the internal scene of the enterprise. Invalid identifiers are removed to ensure the correctness of the identifiers. The invalid mark comprises a failure mark and an ambiguous mark. The failure identifier refers to an identifier which cannot acquire a query result under the existing analysis system of the enterprise. The ambiguous identification refers to an identification of a plurality of analysis results obtained by analyzing under the existing analysis system of an enterprise. Both identifiers cannot obtain correct analysis results, and modification or elimination processing is required.
(2) And classifying the stock identification through a naive Bayes algorithm. And dividing the stock identifications into different groups according to product names and enterprise affiliations.
(3) And constructing a general semantic knowledge model. The model is as follows: m ═ concept, example, enterprise }.
(4) And (3) mapping the grouping in the step (2) into a semantic knowledge model based on rules.
The mapping rules are as follows:
the product name is mapped to a concept,
the inventory identification itself is mapped as an instance,
the enterprise affiliation is mapped to an enterprise.
(5) And converting the semantic knowledge model into a Handle identifier according to the format of the Handle identifier. The conversion format is as follows:
<Handle>::＝<Stock Identification Manage>/<concept_instance_enterprise>
the Stock Identification manager is a Handle prefix, which is registered in the Handle parsing system, and all Stock identifications share the prefix.
The concept _ instance _ entity is a Handle suffix, which is converted from the knowledge model in step (4). In particular, in the form of three components of a knowledge model connected by two underlines.
Further, the processing procedure of the inventory identification through the naive bayes algorithm in the step (2) comprises the following steps:
1) a preparation phase. In this stage, the characteristic attributes are determined, each characteristic attribute is divided appropriately, and then part of inventory identifiers to be classified are classified manually to form a training sample collection. The characteristic attributes are different portions of the inventory identity that are manually delineated. Such as: code length, code composition, etc. The selection of the characteristic attributes has great influence on the classification accuracy of the classifier formed by the algorithm. The input of this stage is the stock identification to be classified, and the output is the characteristic attribute and the training sample. This stage needs to be done manually.
2) And training a classifier. This stage requires the generation of a classifier. The main work is to calculate the occurrence probability of each category in the sample and the conditional probability estimation of each characteristic attribute partition for each category, and record the result. The input of the method is a characteristic attribute and a training sample, and the output is a classifier.
3) And selecting part of inventory identification to be manually classified as a data collection of the test classifier, and testing the trained classifier.
The success rate after the test is the number of successful data in the test set/the total number of all data in the test set
And if the success rate is lower than 96%, returning to the step 1) to change the characteristic attribute, and continuing to perform downwards.
4) And processing the inventory identification. And classifying the stock identifications to be classified by using a classifier, inputting the stock identifications to be classified into the classifier and the stock identifications to be classified, and outputting the stock identifications and the groups to which the stock identifications belong.
Further, the semantic model in the step (3) is specifically explained as follows:
the model is as follows: m ═ concept, example, enterprise }. The model is a triplet of three concepts. The system consists of three elements of concepts, examples and enterprises. The details are as follows:
concepts may also be referred to as product names. It exists to unify the heterogeneous representations of the same product across different enterprises.
An example, which is the enterprise's existing inventory identity itself.
An enterprise, i.e., a manufacturing enterprise of instances in a model.
The concept and the enterprise are in many-to-many relation among the three elements of the model, one enterprise can produce various products, and one product can be produced by a plurality of enterprises at the same time. An instance is an instantiation of a concept. Each product is hardly produced in one piece, and the main purpose of the example is to distinguish the same product and ensure that each entity in the industrial internet can have a unique tag. Since the stock id of each enterprise is necessarily unique within the enterprise itself, even if some of the ids are not unique due to some error, they are excluded in the preprocessing stage. The encoding of the inventory identification may be employed as an example. The instances are attributed to the enterprise. Each product ultimately belongs to a business. The existence of the enterprise elements in the model can be used as a distinguishing element for embodying uniqueness when the stock identification rules of two or more enterprises are similar in style, so as to ensure that each stock identification represented by the semantic model is unique and unambiguous.
In a word, the method of the invention expresses the inventory identification with the expression mode isomerism in the same mode through a naive Bayes algorithm, realizes the normalization of the identification, maps the normalized identification into a knowledge model through regular mapping, and finally converts the inventory identification into a Handle identification through the knowledge model.
Compared with the prior art, the method has the advantages that:
1. the conversion process of the invention does not depend on a manually made stock identification rule list any more, only needs to manually classify the training set and the test set, and the subsequent steps are automatic and do not need manual participation, thereby reducing a large amount of labor cost.
2. In the prior art, when the stock identity is analyzed, a situation that one identity is matched with a plurality of stock identity rules in the stock identity list may exist, and at this time, the prior art obtains a plurality of analysis results.
The invention has reasonable design, establishes the mapping relation between the enterprise stock marks and the Handle marks to convert the analysis of the stock marks into the analysis of the corresponding Handle marks, and realizes the compatibility of the enterprise stock marks and the Handle system.
Drawings
Fig. 1 shows an overall flow diagram of the conversion of the inventory identity into a Handle identity.
Fig. 2 shows a flow chart of the na iotave bayes algorithm for processing inventory identification.
FIG. 3 shows a framework diagram of a semantic knowledge model.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples, but the present invention is not limited thereto. The invention is intended to cover any alternatives, modifications, equivalents, and alternatives that fall within the scope of the invention.
The embodiment provides a specific example of mapping the enterprise stock identifier adopting the method into the Handle identifier.
A Handle stock identification analysis method based on a semantic model comprises the following steps: the method comprises the steps of preprocessing stock identifications in an enterprise, classifying the stock identifications through a naive Bayes algorithm, mapping the stock identifications to an established semantic knowledge model, and converting the stock identifications represented by the semantic knowledge model into unique Handle identifications according to a defined mapping rule. As shown in fig. 1, an overall flow diagram of the conversion of the inventory identity to the Handle identity is illustrated. The method comprises the following specific steps:
(1) and a data preprocessing stage:
and preprocessing the stock identification in the internal scene of the enterprise. And analyzing the enterprise stock identification by using the existing enterprise analysis system, and removing the invalid identification if the analysis result is null or more than one piece of data of the analysis result is obtained.
(2) And a naive Bayes classification stage:
and classifying the stock identifications through a naive Bayesian algorithm, and dividing the stock identifications into different groups according to product names and enterprise affiliations. As shown in fig. 2, a flow chart of the naive bayes classification stage is illustrated, which specifically follows:
1) a preparation phase. In this stage, the characteristic attributes are determined, each characteristic attribute is divided appropriately, and then part of inventory identifiers to be classified are classified manually to form a training sample collection. The characteristic attributes are different parts of the manually-defined inventory identification, such as: code length, code composition, etc. The selection of the characteristic attributes has great influence on the classification accuracy of the classifier formed by the algorithm. The input of this stage is the stock identification to be classified, and the output is the characteristic attribute and the training sample. This stage needs to be done manually.
First, a feature attribute is selected. The selection is the mark length, mark composition, the affiliated enterprise, the product name and the mark carrier.
Marking length: the length of the mark, i.e. the mark consists of several characters.
The identification is composed of: identified constituent elements, such as: numbers, letters, Chinese characters, etc. and their mixture.
The method comprises the following steps: code that resides in the enterprise.
Product name: the product names are labeled with agreed common product codes to distinguish the products. The heterogeneous names of the same product in different enterprises need to be marked by an agreed common product code.
Marking a carrier: the existence form of the identification, such as: two-dimensional codes, bar codes, RFID chips, etc.
2) And training a classifier. This stage requires the generation of a classifier. The main work is to calculate the occurrence probability of each category in the sample and the conditional probability estimation of each characteristic attribute partition for each category, and record the result. The input of the method is a characteristic attribute and a training sample, and the output is a classifier.
After the characteristic attributes are selected, the training set is manually classified to be used as a training sample set.
Let x be { a ═ a1,a2,...,amAnd are items to be classified, wherein each a is a characteristic attribute of x. The feature attributes may be tentatively listed above.
Let class set C ═ y1,y2,y3...,yn}. Where each y represents a product of a business, it is assumed that all inventory designations are in several categories.
Counting the conditional probability of each feature attribute under each class, i.e.
P(a1|y1),P(a2|y1),...,P(am|y1)；P(a1|y2),P(a2|y2),...，P(am|y2)；,,,；P(a1|yn),P(a2|yn),...,P(am|yn)
Since each feature attribute is condition independent, there are the following push-to-guide:
and obtaining:
this is the work done during the classifier training phase.
3) Selecting part of inventory identification to be manually classified to be used as a data collection of a test classifier, and then utilizing the manually classified test collection to test the classifier, wherein the specific test steps are as follows:
calculating P (y)1|x),P(y2|x)...，P(yn| x) is the conditional probability of each feature attribute of the item x to be classified for each class.
If, P (y)k|x)＝max{P(y1|x),P(y2|x),...,P(yn| x)) }, then x ∈ yk。
And after the test, if the accuracy is lower than 96%, modifying the characteristic attribute, retraining the classifier, and continuing the process of the naive Bayes classification stage until the success rate is greater than or equal to 96%. And when the classification success rate of the test set in the classifier is more than or equal to 96%, starting to use the classifier to perform batch processing on the existing inventory marks.
4) And processing the inventory identification. And classifying the inventory identification to be classified by using a classifier, wherein the classifier and the inventory identification to be classified are input, and the inventory identification and the group to which the inventory identification belongs are output. In this step, it is assumed that the classifier classification result of step 3) has A, B, C and so on. After the inventory identification to be classified is classified by the classifier, the inventory identification to be classified forms a corresponding relation with each group in the classification result. Such as: the mark 12345 corresponds to group a, the mark Z123 corresponds to group B, the mark a-123 corresponds to group C, and so on.
(3) And constructing a semantic knowledge model stage: and constructing a semantic knowledge model M, namely { concept, instance, enterprise }, as shown in FIG. 3. And then mapping the classification result of the naive Bayes classification stage into a semantic model according to a mapping rule.
The mapping rules are as follows:
the product name is mapped to a concept,
the inventory identification itself is mapped as an instance,
the enterprise affiliation is mapped to an enterprise.
An example of the semantic model after mapping in this embodiment is as follows:
{book,978-7-115-35936-0,36738}
wherein, book is concept code, 978-7-115-35936-0 is instance code, and 36738 is enterprise code.
(5) And mapping the semantic knowledge model and the Handle identifier: and converting the semantic knowledge model into the Handle identifier according to the format of the Handle identifier. The conversion format is as follows:
<Handle>::＝<Stock Identification Manage>/<concept_instance_enterprise>
the Stock Identification manager is a Handle prefix, which is registered in the Handle parsing system, and all Stock identifications share the prefix.
The concept _ instance _ entity is a Handle suffix, which is converted from the knowledge model in step (4). In particular, in the form of three components of a knowledge model connected by two underlines.
The converted Handle id in this embodiment is exemplified as follows:
<Handle>::＝<11.123.123.123>/<book_978-7-115-35936-0_36738>
11.123.123.123 is a common prefix for the inventory id in the Handle resolution hierarchy.
book _978-7-115-35936-0_36738 provides a Handle identification suffix. Wherein:
book is the concept code.
978-7-115-35936-0 is an example code.
36738 is an enterprise code.
The present invention is described in more detail by way of example with reference to the accompanying drawings. It is to be noted, however, that the drawings are designed in a simplified form and are not to scale so as to facilitate the description of the embodiments of the invention.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the detailed description is made with reference to the embodiments of the present invention, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which shall be covered by the claims of the present invention.
Claims (3)
1. A method for analyzing Handle stock identification based on semantic model is characterized in that: and after preprocessing the stock identifications, classifying the stock identifications through a naive Bayes algorithm, mapping the classification result to a semantic model, and then converting the stock identifications represented by the semantic model into Handle identifications through a predefined rule, so that the analysis of the stock identifications is converted into the analysis of the Handle identifications.
2. The semantic model-based Handle stock identity parsing method as recited in claim 1, wherein: the method specifically comprises the following steps:
(1) preprocessing stock identification in the internal scene of the enterprise
Removing the invalid mark to ensure the correctness of the mark; the invalid mark comprises a invalid mark and an ambiguous mark; the failure identification refers to identification which cannot obtain the query result under the existing enterprise analysis system, and the polysemous identification refers to identification which obtains a plurality of analysis results after analysis under the existing enterprise analysis system;
(2) classifying the stock identification through a naive Bayes algorithm
Dividing the stock identification into different groups according to product names and enterprise affiliations;
(3) constructing a general semantic knowledge model
The model is as follows: m ═ concept, example, enterprise }; the model is a triple composed of three concepts, and is composed of three elements of concepts, examples and enterprises; the following were used:
the concept, called product name, exists to unify the heterogeneous representations of the same product across different enterprises;
an instance, which is the enterprise's existing inventory identity itself;
an enterprise, i.e., a manufacturing enterprise of instances in a model;
(4) mapping the grouping in the step (2) into a semantic knowledge model based on rules
The mapping rules are as follows:
the product name is mapped to a concept,
the inventory identification itself is mapped as an instance,
the enterprise affiliation is mapped to an enterprise;
(5) converting the semantic knowledge model into a Handle identifier according to the format of the Handle identifier; the conversion format is as follows:
<Handle>::＝<Stock Identification Manage>/<concept_instance_enterprise>
the Stock Identification management is a Handle prefix which is registered in a Handle analysis system, and all Stock identifications share the prefix;
the concept _ instance _ entity is a Handle suffix transformed from the knowledge model in step (4) in the form of three components of the knowledge model connected by two underlines.
3. The semantic model-based Handle stock identity parsing method as recited in claim 2, wherein: in the step (2), the storage identification is processed by a naive Bayes algorithm in the following steps:
1) preparation phase
In the stage, characteristic attributes are required to be determined, each characteristic attribute is divided, and then part of inventory identifiers to be classified are manually classified to form a training sample set; the characteristic attributes are different parts of artificially defined stock marks; the input of the stage is the stock identification to be classified, and the output is the characteristic attribute and the training sample;
2) training classifier
This stage generates a classifier; the work is to calculate the occurrence probability of each category in the sample and the conditional probability estimation of each category by each characteristic attribute partition, and record the result; the input of the method is a characteristic attribute and a training sample, and the output is a classifier;
3) selecting part of inventory identification to be manually classified and then taking the part of inventory identification as a data collection of a test classifier, and testing the trained classifier;
after the test, the success rate is the number of successful data in the test set/the total number of all data in the test set;
if the success rate is lower than 96%, returning to the step 1) to change the characteristic attribute, and continuing to perform downwards;
4) processing stock identification
And classifying the inventory identification to be classified by using a classifier, wherein the classifier and the inventory identification to be classified are input, and the inventory identification and the group to which the inventory identification belongs are output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111077324.1A CN113780005B (en) | 2021-09-14 | 2021-09-14 | Semantic model-based Handle stock identification analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111077324.1A CN113780005B (en) | 2021-09-14 | 2021-09-14 | Semantic model-based Handle stock identification analysis method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113780005A true CN113780005A (en) | 2021-12-10 |
| CN113780005B CN113780005B (en) | 2024-04-16 |
Family
ID=78843789
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111077324.1A Active CN113780005B (en) | 2021-09-14 | 2021-09-14 | Semantic model-based Handle stock identification analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113780005B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120066253A1 (en) * | 2010-09-15 | 2012-03-15 | Cbs Interactive, Inc. | Mapping Product Identification Information To A Product |
| CA2932310A1 (en) * | 2015-06-10 | 2016-12-10 | Accenture Global Services Limited | System and method for automating information abstraction process for documents |
| CN110019418A (en) * | 2018-01-02 | 2019-07-16 | 中国移动通信有限公司研究院 | Object factory method and device, mark system, electronic equipment and storage medium |
| CN110941611A (en) * | 2019-11-06 | 2020-03-31 | 四川长虹电器股份有限公司 | Identification analysis system implementation method based on block chain technology and identification coding technology |
| CN111199259A (en) * | 2018-11-19 | 2020-05-26 | 中国电信股份有限公司 | Identification conversion method, device and computer readable storage medium |
-
2021
- 2021-09-14 CN CN202111077324.1A patent/CN113780005B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120066253A1 (en) * | 2010-09-15 | 2012-03-15 | Cbs Interactive, Inc. | Mapping Product Identification Information To A Product |
| CA2932310A1 (en) * | 2015-06-10 | 2016-12-10 | Accenture Global Services Limited | System and method for automating information abstraction process for documents |
| CN110019418A (en) * | 2018-01-02 | 2019-07-16 | 中国移动通信有限公司研究院 | Object factory method and device, mark system, electronic equipment and storage medium |
| CN111199259A (en) * | 2018-11-19 | 2020-05-26 | 中国电信股份有限公司 | Identification conversion method, device and computer readable storage medium |
| CN110941611A (en) * | 2019-11-06 | 2020-03-31 | 四川长虹电器股份有限公司 | Identification analysis system implementation method based on block chain technology and identification coding technology |
Non-Patent Citations (1)
| Title |
|---|
| 葛尧: "工业网站的识别和分类系统的研究与实现", 中国优秀硕士学位论文全文数据库 (信息科技辑), pages 2 - 3 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113780005B (en) | 2024-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | A graph-based context-aware requirement elicitation approach in smart product-service systems | |
| US10019509B1 (en) | Multi-dimensional modeling in a functional information system | |
| CN107967575B (en) | Artificial intelligence platform system for artificial intelligence insurance consultation service | |
| US9990380B2 (en) | Proximity search and navigation for functional information systems | |
| US8209407B2 (en) | System and method for web service discovery and access | |
| CN104718542B (en) | Utilize illiteracy's data conversion up and down of index String matching | |
| US7730007B2 (en) | IT event data classifier configured to label messages if message identifiers map directly to classification categories or parse for feature extraction if message identifiers do not map directly to classification categories | |
| CN108460136A (en) | Electric power O＆M information knowledge map construction method | |
| CN110457676B (en) | Evaluation information extraction method and device, storage medium and computer equipment | |
| CN103425740B (en) | A kind of material information search method based on Semantic Clustering of internet of things oriented | |
| Nisa et al. | A text mining based approach for web service classification | |
| CN112989208B (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN111666766A (en) | Data processing method, device and equipment | |
| CN113051914A (en) | Enterprise hidden label extraction method and device based on multi-feature dynamic portrait | |
| CN116127090B (en) | Aviation system knowledge graph construction method based on fusion and semi-supervision information extraction | |
| CN116245177A (en) | Geographic environment knowledge graph automatic construction method and system and readable storage medium | |
| CN109857892B (en) | Semi-supervised cross-modal Hash retrieval method based on class label transfer | |
| CN113673889A (en) | Intelligent data asset identification method | |
| CN106775694B (en) | A kind of hierarchy classification method of software configuration code product | |
| CN115210705A (en) | Vector embedding model for relational tables with invalid or equivalent values | |
| US20210097404A1 (en) | Systems and methods for creating product classification taxonomies using universal product classification ontologies | |
| Su et al. | Understanding query interfaces by statistical parsing | |
| CN113780005A (en) | Semantic model-based Handle stock identification analysis method | |
| CN106055702B (en) | Internet-oriented data service unified description method | |
| CN114372148A (en) | Data processing method based on knowledge graph technology and terminal equipment |
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 |