CN116824323A - BIM component semantic recognition method, device, equipment and storage medium - Google Patents

BIM component semantic recognition method, device, equipment and storage medium Download PDF

Info

Publication number
CN116824323A
CN116824323A CN202310811021.0A CN202310811021A CN116824323A CN 116824323 A CN116824323 A CN 116824323A CN 202310811021 A CN202310811021 A CN 202310811021A CN 116824323 A CN116824323 A CN 116824323A
Authority
CN
China
Prior art keywords
text
bim
data
similarity
data information
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
Application number
CN202310811021.0A
Other languages
Chinese (zh)
Inventor
林丰杰
乔蕾
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xiangmei Shanghai Information Technology Co ltd
Original Assignee
Xiangmei Shanghai Information Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xiangmei Shanghai Information Technology Co ltd filed Critical Xiangmei Shanghai Information Technology Co ltd
Priority to CN202310811021.0A priority Critical patent/CN116824323A/en
Publication of CN116824323A publication Critical patent/CN116824323A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
    • G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/10—File systems; File servers
    • G06F16/11—File system administration, e.g. details of archiving or snapshots
    • G06F16/113—Details of archiving
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/10—File systems; File servers
    • G06F16/16—File or folder operations, e.g. details of user interfaces specifically adapted to file systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/10—File systems; File servers
    • G06F16/17—Details of further file system functions
    • G06F16/172—Caching, prefetching or hoarding of files
    • 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
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/761—Proximity, similarity or dissimilarity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/70—Labelling scene content, e.g. deriving syntactic or semantic representations

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Medical Informatics (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Image Analysis (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses a BIM component semantic recognition method, a device, equipment and a storage medium, wherein the semantic recognition method specifically comprises the following steps: acquiring data information of a BIM component; extracting and encoding the characteristics of the data information; constructing a vector space model; calculating the similarity of the semantics; the invention conveniently obtains corresponding text features and image features by carrying out feature extraction and encoding on the data information, and determines a similarity vector and a fusion feature vector of a first semantic of the text data of each component in the BIM model so as to express the similarity vector and the fusion feature vector of the first semantic in the same vector space through a vector space model, thereby realizing breaking the gap between different text features and image features, converting the different text features and image features into vector representations and enabling the vectors to contain as much text and image data information as possible.

Description

BIM component semantic recognition method, device, equipment and storage medium
Technical Field
The invention relates to the technical field of semantic recognition, in particular to a BIM component semantic recognition method, device, equipment and storage medium.
Background
The BIM building information model is a digital expression of physical and functional characteristics of a building body, can provide comprehensive, accurate and real-time information for the management process of the whole life cycle of the project, changes the traditional thinking mode and operation mode of the building industry, improves the working quality and efficiency of project design, construction and operation and maintenance, and promotes the improvement of the productivity level of the industry;
the current BIM model component identification is usually carried out by identifying the component phenomenon of the BIM model according to a single quilt mode, so that the identification result is easy to appear singleness, meanwhile, the identification precision is low, meanwhile, the data information in each field has great difference due to the wide coverage field of the BIM model component, and therefore, the calculation and judgment means of similarity and relevance are lacked, so that great difference exists between the text data and image data which are identified later and the BIM model component information, and further, the identification result is easy to deviate.
Disclosure of Invention
(one) solving the technical problems
Aiming at the defects of the prior art, the invention provides a BIM component semantic recognition method, a device, equipment and a storage medium, which solve the problems that the component phenomenon of a BIM model is recognized according to a single mode, so that the recognition result is easy to have singleness, the recognition precision is low, and meanwhile, the data information in each field has great difference due to the wide coverage field of the BIM model component, so that a calculation and judgment means for similarity and relevance is lacking, great difference exists between text data and image data which are recognized later and the BIM model component information, and further the recognition result is easy to deviate.
(II) technical scheme
In order to achieve the above purpose, the present invention provides the following technical solutions: a BIM component semantic recognition method specifically comprises the following steps:
s1, acquiring data information of a BIM component;
s2, extracting and encoding the characteristics of the data information;
s3, constructing a vector space model;
s4, calculating the similarity of the semantics;
s5, identifying data information of the BIM component.
In the S1, acquiring data information of a BIM component is mainly used for acquiring a text to be identified based on the BIM component, and specifically includes text data and image data;
in S1, after obtaining text data and image data, establishing separate storage folders for the text data and the image data in a computer system for classified storage, and processing the respective text and image data in the separate folders of the text data and the image data;
the main processing includes checking the duplicate of the text and image data and detecting the low quality, the check is mainly to remove the repeated data information in the text data and image data, so that the acquired text data and image data have uniqueness, the low quality detection is mainly to detect and remove the low quality data information in the text data and image data;
the low-quality data information comprises text data with content errors, text data with content with obvious ambiguity, image data with lower definition and processed image data.
In the S2, feature extraction and encoding of the data information mainly means feature extraction and encoding of the obtained text data and image data information, so as to obtain corresponding text features and image features;
and determining a similarity vector of the text data and the first semantics of the text data of each component in the BIM model, and fusing the text features and the image features to obtain a fused feature vector.
In the S3, the similarity vector and the fusion feature vector of the first semantic are expressed in the same vector space mainly through a vector space model, so that the gaps between different text features and image features are broken, and the different text features and image features are converted into vector representations, so that the vectors contain as much text and image data information as possible;
and the processing of different text features and image features is simplified into vector operation in a vector space through a vector space model, and the similarity relation between the text features and the image features and the BIM model component is expressed by using the spatial similarity.
As a preferred technical scheme of the BIM component semantic recognition method, in the S4, similarity of the calculated semantics is mainly calculated by calculating similarity between vectors in a vector space model to measure similarity between text features and image features and BIM model components, and in the specific similarity calculation process, similarity is calculated mainly by measuring cosine distance;
through a vector space model, different text feature and image feature data information are converted into structural data which can be processed by a computer, so that the similarity problem between the different text feature and image feature data information and BIM model components is converted into the similarity problem between two vectors, and the correlation degree between the different text feature and image feature data information and the BIM model components is measured through the similarity between the two vectors, so that the obtained text feature and image feature data information and the label data of the BIM model components to be identified can be judged conveniently, and accurate identification can be realized.
In the S5, the identifying of the data information of the BIM component mainly refers to identifying and judging the tag data of the BIM model component to be identified according to the similarity vector and the fusion feature vector of the first semantic and the correlation information calculated in the step S4, so as to determine the data information of the BIM component.
As a preferred technical scheme of the BIM component semantic recognition method, in S5, the method further comprises calculating the association similarity in the process of recognizing the data information of the BIM component, specifically, comparing and calculating different text characteristic and image characteristic data information with the data information contained in the BIM component, and judging the association similarity by calculating the occurrence probability of the text characteristic and the image characteristic data information in the data information contained in the BIM component, wherein the larger the probability is, the higher the association similarity is, the smaller the probability is, the association similarity is low, and the precise recognition is realized by measuring the correlation between the text characteristic and the image characteristic data information and the data information contained in the BIM component through the probability.
The BIM component semantic recognition device mainly comprises a data acquisition module, a feature extraction and encoding module, a vector space model module, a semantic similarity calculation module and a data information recognition module;
the data acquisition module is mainly used for acquiring texts to be identified based on BIM components, the feature extraction and encoding module is used for carrying out feature extraction and encoding on acquired text data and image data information so as to obtain corresponding text features and image features, the vector space model module is mainly used for representing similarity vectors of first semantics and fusion feature vectors in the same vector space, the semantic similarity calculation module is mainly used for measuring similarity between the text features and the image features and the BIM components by calculating similarity between vectors in a vector space model, and the data information identification module is mainly used for carrying out identification judgment on tag data of the BIM components to be identified so as to determine data information of the BIM components.
A BIM building element semantic recognition device comprising a processor, a memory and a communication unit, the memory storing machine readable instructions executable by the processor, the processor and the memory communicating via the communication unit when the computer device is in operation, the machine readable instructions being executable by the processor to perform the step of speech recognition.
A storage medium having stored thereon a computer program which, when executed by a processor, performs the method steps of semantic recognition.
(III) beneficial effects
Compared with the prior art, the invention provides a BIM component semantic recognition method, device, equipment and storage medium, which have the following beneficial effects:
1. the data information is subjected to feature extraction and encoding to conveniently obtain corresponding text features and image features, and the similarity vector and the fusion feature vector of the first semantic of the text data of each component in the BIM model are determined so as to be represented in the same vector space through the vector space model, so that the gap between different text features and image features is broken, the different text features and image features are converted into vector representations, and the vectors contain as much text and image data information as possible;
and the processing of different text features and image features is simplified into vector operation in a vector space through a vector space model, so that similarity relations between text feature information and image feature information and BIM model component information can be conveniently and intuitively and accurately expressed, and recognition work can be conveniently and accurately carried out.
2. The similarity between the text features and the image features and the BIM model components is measured by calculating the similarity between the vectors in the vector space model so as to better calculate the similarity of semantics, and different text features and image feature data information are converted into structural data which can be processed by a computer through the vector space model, so that the similarity problem between different text features and image feature data information and the BIM model components is converted, and the correlation between different text features and image feature data information and the BIM model components is measured by the similarity between the two vectors so as to facilitate more accurate identification.
3. By comparing and calculating different text feature and image feature data information with the data information contained in the BIM component, the correlation similarity is conveniently judged in a probability size judgment mode, so that the correlation between the text feature and image feature data information and the data information contained in the BIM component is measured through probability, and accurate identification is realized.
4. By establishing an independent storage folder for classifying and storing the data information of the acquired BIM component, the quick search of the subsequent information is facilitated, and simultaneously, the repeated data information in the text data and the image data is conveniently removed by processing the text data and the image data, so that the acquired text data and image data have uniqueness, and the quality of the data is ensured and the accuracy of the subsequent identification is improved by removing the low-quality data information for detection.
Drawings
FIG. 1 is a flow chart of the semantic recognition method of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Examples
Referring to fig. 1, the present invention provides the following technical solutions: a BIM component semantic recognition method specifically comprises the following steps:
s1, acquiring data information of a BIM component;
s2, extracting and encoding the characteristics of the data information;
s3, constructing a vector space model;
s4, calculating the similarity of the semantics;
s5, identifying data information of the BIM component.
According to the technical scheme, in S1, acquiring the data information of the BIM component mainly refers to acquiring a text to be identified based on the BIM component, and specifically comprises text data and image data;
in S1, after obtaining text data and image data, establishing separate storage folders for the text data and the image data in a computer system for classified storage, and processing the respective text and image data in the separate folders of the text data and the image data;
the main processing includes checking the duplicate of the text and image data and detecting the low quality, the check is mainly to remove the repeated data information in the text data and image data, so that the acquired text data and image data have uniqueness, the low quality detection is mainly to detect and remove the low quality data information in the text data and image data;
the low-quality data information specifically includes text data with content errors, text data with content with obvious ambiguity, image data with lower definition, and processed image data.
According to the technical scheme, in S2, feature extraction and coding of the data information mainly means feature extraction and coding of the acquired text data and image data information, so that corresponding text features and image features are obtained;
and determining a similarity vector of the text data and the first semantics of the text data of each component in the BIM model, and fusing the text features and the image features to obtain a fused feature vector.
According to the technical scheme, in S3, the similarity vector and the fusion feature vector of the first semantic meaning are mainly expressed in the same vector space through a vector space model, so that the gap between different text features and image features is broken, and the different text features and image features are converted into vector representations, so that the vectors contain as much text and image data information as possible;
and the processing of different text features and image features is simplified into vector operation in a vector space through a vector space model, and the similarity relation between the text features and the image features and the BIM model component is expressed by using the spatial similarity.
According to the above technical solution, in S4, calculating the similarity of the semantics mainly measures the similarity between the text feature and the image feature and the BIM model component by calculating the similarity between vectors in the vector space model, and in the process of specifically performing similarity calculation, the similarity is calculated mainly by measuring the cosine distance;
through a vector space model, different text feature and image feature data information are converted into structural data which can be processed by a computer, so that the similarity problem between the different text feature and image feature data information and BIM model components is converted into the similarity problem between two vectors, and the correlation degree between the different text feature and image feature data information and the BIM model components is measured through the similarity between the two vectors, so that the obtained text feature and image feature data information and the label data of the BIM model components to be identified can be judged conveniently, and accurate identification can be realized.
According to the above technical solution, in S5, identifying the data information of the BIM member mainly means identifying and judging the tag data of the BIM model member to be identified according to the similarity vector and the fusion feature vector of the first semantic and the correlation information calculated in step S4, so as to determine the data information of the BIM member.
According to the technical scheme, in S5, the process of identifying the data information of the BIM member further includes calculating the association similarity, specifically, comparing and calculating different text feature and image feature data information with the data information contained in the BIM member, and calculating the probability of occurrence of the text feature and image feature data information in the data information contained in the BIM member to judge the association similarity, wherein the probability is higher, the probability is lower, and the association similarity is lower, so that accurate identification is realized by measuring the correlation between the text feature and image feature data information and the data information contained in the BIM member.
The BIM component semantic recognition device mainly comprises a data acquisition module, a feature extraction and encoding module, a vector space model module, a semantic similarity calculation module and a data information recognition module;
the data acquisition module is mainly used for acquiring texts to be identified based on BIM components, the feature extraction and encoding module is used for carrying out feature extraction and encoding on acquired text data and image data information so as to obtain corresponding text features and image features, the vector space model module is mainly used for expressing similarity vectors of first semantics and fusion feature vectors in the same vector space, the semantic similarity calculation module is mainly used for measuring similarity between the text features and the image features and the BIM components by calculating similarity between vectors in the vector space model, and the data information identification module is mainly used for carrying out identification judgment on tag data of the BIM components to be identified and determining data information of the BIM components.
A BIM building element semantic recognition device comprising a processor, a memory and a communication unit, the memory storing machine readable instructions executable by the processor, the processor and the memory communicating via the communication unit when the computer device is in operation, the machine readable instructions being executable by the processor to perform the step of speech recognition.
A storage medium having stored thereon a computer program which, when executed by a processor, performs the method steps of semantic recognition.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. A BIM component semantic recognition method is characterized in that: the semantic recognition method specifically comprises the following steps:
s1, acquiring data information of a BIM component;
s2, extracting and encoding the characteristics of the data information;
s3, constructing a vector space model;
s4, calculating the similarity of the semantics;
s5, identifying data information of the BIM component.
2. The BIM component semantic recognition method of claim 1, wherein: in the step S1, the data information of the BIM component is mainly used for acquiring a text to be identified based on the BIM component, and specifically comprises text data and image data;
in S1, after obtaining text data and image data, establishing separate storage folders for the text data and the image data in a computer system for classified storage, and processing the respective text and image data in the separate folders of the text data and the image data;
the main processing includes checking the duplicate of the text and image data and detecting the low quality, the check is mainly to remove the repeated data information in the text data and image data, so that the acquired text data and image data have uniqueness, the low quality detection is mainly to detect and remove the low quality data information in the text data and image data;
the low-quality data information comprises text data with content errors, text data with content with obvious ambiguity, image data with lower definition and processed image data.
3. The BIM component semantic recognition method of claim 1, wherein: in the step S2, feature extraction and coding are mainly performed on the obtained text data and image data information, so that corresponding text features and image features are obtained;
and determining a similarity vector of the text data and the first semantics of the text data of each component in the BIM model, and fusing the text features and the image features to obtain a fused feature vector.
4. The BIM component semantic recognition method of claim 1, wherein: in the step S3, the similarity vector and the fusion feature vector of the first semantic are mainly expressed in the same vector space through a vector space model, the gap between different text features and image features is broken, and the different text features and image features are converted into vector representations, so that the vectors contain as much text and image data information as possible;
and the processing of different text features and image features is simplified into vector operation in a vector space through a vector space model, and the similarity relation between the text features and the image features and the BIM model component is expressed by using the spatial similarity.
5. The BIM component semantic recognition method of claim 1, wherein: in the step S4, the similarity of the semantics is calculated mainly by calculating the similarity between vectors in the vector space model to measure the similarity between the text feature and the image feature and the BIM model component, and in the process of specifically calculating the similarity, the similarity is calculated mainly by measuring the cosine distance;
through a vector space model, different text feature and image feature data information are converted into structural data which can be processed by a computer, so that the similarity problem between the different text feature and image feature data information and BIM model components is converted into the similarity problem between two vectors, and the correlation degree between the different text feature and image feature data information and the BIM model components is measured through the similarity between the two vectors, so that the obtained text feature and image feature data information and the label data of the BIM model components to be identified can be judged conveniently, and accurate identification can be realized.
6. The BIM component semantic recognition method of claim 1, wherein: in the step S5, the identification of the data information of the BIM component mainly refers to identification and judgment of the tag data of the BIM model component to be identified according to the similarity vector and the fusion feature vector of the first semantic and the correlation information calculated in the step S4, so as to determine the data information of the BIM component.
7. The BIM component semantic recognition method of claim 6, wherein: in S5, the process of identifying the data information of the BIM member further includes calculating the association similarity, specifically, comparing and calculating different text feature and image feature data information with the data information contained in the BIM member, and calculating the probability of occurrence of the text feature and image feature data information in the data information contained in the BIM member to judge the association similarity, wherein the larger the probability is, the higher the association similarity is, the smaller the probability is, the association similarity is low, and the probability is used for measuring the correlation between the text feature and image feature data information and the data information contained in the BIM member to realize accurate identification.
8. BIM component semantic recognition device, its characterized in that: the identification device mainly comprises a data acquisition module, a feature extraction and coding module, a vector space model module, a semantic similarity calculation module and a data information identification module;
the data acquisition module is mainly used for acquiring texts to be identified based on BIM components, the feature extraction and encoding module is used for carrying out feature extraction and encoding on acquired text data and image data information so as to obtain corresponding text features and image features, the vector space model module is mainly used for representing similarity vectors of first semantics and fusion feature vectors in the same vector space, the semantic similarity calculation module is mainly used for measuring similarity between the text features and the image features and the BIM components by calculating similarity between vectors in a vector space model, and the data information identification module is mainly used for carrying out identification judgment on tag data of the BIM components to be identified so as to determine data information of the BIM components.
9. A BIM component semantic recognition device characterized by: the device includes a processor, a memory storing machine-readable instructions executable by the processor, and a communication unit, the communication unit being operable to communicate between the processor and the memory when the computer device is in operation, the machine-readable instructions being operable by the processor to perform the steps of speech recognition.
10. A storage medium for semantic recognition of BIM building elements, characterized by: the storage medium has stored thereon a computer program which, when executed by a processor, performs the method steps of semantic recognition.
CN202310811021.0A 2023-07-04 2023-07-04 BIM component semantic recognition method, device, equipment and storage medium Pending CN116824323A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310811021.0A CN116824323A (en) 2023-07-04 2023-07-04 BIM component semantic recognition method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310811021.0A CN116824323A (en) 2023-07-04 2023-07-04 BIM component semantic recognition method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN116824323A true CN116824323A (en) 2023-09-29

Family

ID=88141058

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310811021.0A Pending CN116824323A (en) 2023-07-04 2023-07-04 BIM component semantic recognition method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN116824323A (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111191457A (en) * 2019-12-16 2020-05-22 浙江大搜车软件技术有限公司 Natural language semantic recognition method and device, computer equipment and storage medium
CN116070164A (en) * 2021-10-25 2023-05-05 广东博智林机器人有限公司 BIM model component identification method, BIM model component identification device, computer equipment and storage medium
CN116361316A (en) * 2023-03-14 2023-06-30 星河智联汽车科技有限公司 Semantic engine adaptation method, device, equipment and storage medium

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111191457A (en) * 2019-12-16 2020-05-22 浙江大搜车软件技术有限公司 Natural language semantic recognition method and device, computer equipment and storage medium
CN116070164A (en) * 2021-10-25 2023-05-05 广东博智林机器人有限公司 BIM model component identification method, BIM model component identification device, computer equipment and storage medium
CN116361316A (en) * 2023-03-14 2023-06-30 星河智联汽车科技有限公司 Semantic engine adaptation method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
CN112581463A (en) Image defect detection method and device, electronic equipment, storage medium and product
CN113032672A (en) Method and device for extracting multi-modal POI (Point of interest) features
CN113742387A (en) Data processing method, device and computer readable storage medium
CN111582169A (en) Image recognition data error correction method, device, computer equipment and storage medium
CN109684374B (en) Method and device for extracting key value pairs of time series data
CN113657274B (en) Table generation method and device, electronic equipment and storage medium
WO2017101225A1 (en) Trademark graph element identification method, apparatus and system, and computer storage medium
CN112598000A (en) Question identification method and device, electronic equipment and computer storage medium
CN114037672A (en) Image defect detection method and device and computer readable medium
CN102508901A (en) Content-based massive image search method and content-based massive image search system
CN111368824A (en) Instrument identification method, mobile device and storage medium
CN109543498B (en) Lane line detection method based on multitask network
CN116824323A (en) BIM component semantic recognition method, device, equipment and storage medium
CN116309963B (en) Batch labeling method and device for images, electronic equipment and storage medium
CN116051558B (en) Defect image labeling method, device, equipment and medium
US20220392192A1 (en) Target re-recognition method, device and electronic device
CN115273177A (en) Method, device and equipment for recognizing face types of heterogeneous faces and storage medium
CN115456996A (en) Discrete defect detection method for nuclear fuel pellet and related assembly
CN115098679A (en) Method, device, equipment and medium for detecting abnormality of text classification labeling sample
CN111046878B (en) Data processing method and device, computer storage medium and computer
CN113344058B (en) Early warning method and device based on information fusion of cloud computing and cloud server
CN113361330A (en) Automatic electronic document identification system and method
CN111104934A (en) Engine label detection method, electronic device and computer readable storage medium
CN109739981A (en) A kind of pdf document kind judging method and text extraction method
CN113420781B (en) Brand identification method, apparatus, device, storage medium, and program product

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