CN115982830A - Indoor design node adaptation method and device, computer equipment and storage medium - Google Patents
Indoor design node adaptation method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN115982830A CN115982830A CN202310140730.0A CN202310140730A CN115982830A CN 115982830 A CN115982830 A CN 115982830A CN 202310140730 A CN202310140730 A CN 202310140730A CN 115982830 A CN115982830 A CN 115982830A
- Authority
- CN
- China
- Prior art keywords
- design
- task
- indoor
- text
- code
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of data processing, and provides an adaptation method and device of an indoor design node, computer equipment and a storage medium, wherein the adaptation method comprises the following steps: acquiring an indoor design model from a design model database; acquiring a design requirement text input by a client; identifying the design requirement text based on a preset first neural network model, and identifying the design requirement keywords in the design requirement text; identifying a design node to which a design requirement keyword belongs; identifying the indoor design model based on a preset second neural network model, and identifying each design node of the indoor design model; and adding the design requirement key words into the design templates of the design nodes corresponding to the indoor design model based on the design nodes to which the design requirement key words belong so as to complete the adaptive design of the indoor design nodes. The method is based on the neural network model, and the design requirement text of the client is adaptively added into the design template of the indoor design model without depending on manpower.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an adaptation method and an adaptation device for indoor design nodes, computer equipment and a storage medium.
Background
At present, when an enterprise is moved to replace an office place and a personal residence is moved to replace a living place, decoration design is usually needed; users in the places usually do not have the capacity of indoor design, so a professional design company is required to assist in indoor design; the user puts forward the design requirement to the design company, and the design company carries out indoor design according to the design requirement.
However, at present, only the design requirements are manually recorded by the staff of the design company, then the planning design of each node of the indoor design is manually carried out, and the design requirements are added into the design model to obtain a preliminary indoor design model; the automation degree is low, and the worker is excessively dependent.
Disclosure of Invention
The invention mainly aims to provide an adaptation method, an adaptation device, computer equipment and a storage medium for indoor design nodes, and aims to overcome the defect that the existing generation of an indoor design model is too dependent on manpower.
In order to achieve the purpose, the invention provides an adaptation method of an indoor design node, which comprises the following steps:
acquiring an indoor design model from a design model database; the indoor design model comprises design templates of all design nodes of indoor design;
acquiring a design requirement text input by a client; wherein, the design requirement text comprises the design requirement of the customer on the indoor design;
identifying the design requirement text based on a preset first neural network model, and identifying design requirement keywords in the design requirement text;
identifying a design node to which the design requirement keyword belongs;
identifying the indoor design model based on a preset second neural network model, and identifying each design node of the indoor design model;
and adding the design requirement key words into the design templates of the design nodes corresponding to the indoor design model based on the design nodes to which the design requirement key words belong so as to complete the adaptive design of the indoor design nodes.
Further, the step of identifying the indoor design model based on a preset second neural network model and identifying each design node of the indoor design model includes:
obtaining each of the indoor design models node texts corresponding to the design nodes;
identifying a target feature text from the node text, inputting the target feature text into the second neural network model, and generating a classification list corresponding to the target feature text based on the second neural network model; the second neural network model is a Bert model, and the target feature text is a named entity text; the classification list comprises the classification of the target feature text and the corresponding classification probability;
screening out the target classification with the maximum classification probability as the classification result of the target characteristic text based on the classification list; and taking the target classification as a design node of the indoor design model.
Further, the step of generating a classification list corresponding to the target feature text based on the second neural network model includes:
extracting a hidden vector corresponding to the target feature text based on a hidden layer of the second neural network model;
extracting weights corresponding to the hidden vectors based on a classification layer of the second neural network model; the weights are used to describe the importance levels of the hidden vectors;
based on a classification layer of the second neural network model, calculating scores of the target feature texts belonging to various classifications according to the hidden vectors and the weights;
acquiring coding vectors corresponding to the classes, and correspondingly calculating loss function values of the target feature texts belonging to the classes according to the coding vectors and scores of the target feature texts belonging to the classes;
calculating the classification probability of the target characteristic text belonging to each classification based on the loss function value of the target characteristic text belonging to each classification;
and generating a classification list corresponding to the target characteristic text based on the classification and the classification probability.
Further, after the step of adding the design requirement keyword to the design template of the design node corresponding to the indoor design model based on the design node to which the design requirement keyword belongs to complete the adaptive design of the indoor design node, the method includes:
creating a unique customer identification code for said customer; the customer identification code is used to identify the customer;
acquiring the job number of a designer of a design task in a processing chamber; after receiving the indoor design task of the client, the management user distributes the indoor design task to a designer for processing;
acquiring the job number of the management user;
creating a unique task code for the indoor design task of the client;
generating a customer task code based on the customer identification code and the task code;
generating a design code based on the job number of the management user and the job number of the designer;
and generating a marking code of the indoor design task based on the task code and the design code, wherein the marking code is used for marking the indoor design task.
Further, the step of generating a mark code for the indoor design task based on the task code and the design code includes:
judging whether the task code and the design code have the same character;
if yes, acquiring the same number of the characters, and recording the number as the target number; if not, acquiring a preset number as the target number;
acquiring a standard Base64 coding table, and circularly moving codes in the standard Base64 coding table backwards by preset digits in a unified manner to obtain a new Base64 coding table; wherein the value of the preset digit is equal to the value of the target number;
the task codes and the design codes are connected in series to obtain serial codes;
and coding the concatenated codes by adopting the new Base64 coding table to obtain the mark codes of the indoor design tasks.
Further, after the step of generating a marking code for the indoor design task based on the task code and the design code, for marking the indoor design task, the method further includes:
converting the format of the design requirement text into a specific format;
adding a mark code of the indoor design task at a specified position of the converted design requirement text;
performing hash calculation on the design requirement text to obtain a corresponding standard hash value, storing the standard hash value and the design requirement text in a database, and establishing an index relationship between the standard hash value and the mark code in the database; and when the standard hash value in the database is called, recording the times and time of the calling of the standard hash value.
Further, after the step of establishing the index relationship between the hash value and the marker code in the database, the method includes:
when task verification is needed in the processing process of the indoor design task, acquiring a design requirement text stored in a database, and acquiring a mark code corresponding to the task needing verification, and recording the mark code as a verification mark code;
performing hash calculation on the design requirement text stored in the database to obtain a corresponding hash value;
acquiring a standard hash value corresponding to the verification mark code based on the index relation between the standard hash value and the mark code established in the database according to the verification mark code;
verifying whether the hash value is the same as the standard hash value; if not, verifying that the task is tampered; if the number of times of calling the standard hash value is the same as the number of times of calling the standard hash value, obtaining the time of calling the standard hash value, and verifying whether the number of times of calling the standard hash value is completely consistent with the number of times of task verification and the time of task verification; if the task is not completely consistent, judging that the task is tampered; and if the task is completely consistent, judging that the task is not tampered.
The invention also provides an adaptation device of the indoor design node, which comprises:
the system comprises a first acquisition unit, a second acquisition unit and a control unit, wherein the first acquisition unit is used for acquiring an indoor design model from a design model database; the indoor design model comprises design templates of all design nodes of indoor design;
the second acquisition unit is used for acquiring a design requirement text input by a client; wherein, the design requirement text comprises the design requirement of the customer on the indoor design;
the first identification unit is used for identifying the design requirement text based on a preset first neural network model and identifying a design requirement keyword in the design requirement text;
a second identifying unit configured to identify a design node to which the design requirement keyword belongs;
the third identification unit is used for identifying the indoor design model based on a preset second neural network model and identifying each design node of the indoor design model;
and the adaptation unit is used for adding the design requirement key words into the design templates of the design nodes corresponding to the indoor design model based on the design nodes to which the design requirement key words belong so as to complete the adaptation design of the indoor design nodes.
The present invention also provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.
The invention also provides a computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the method of any of the above.
The invention provides an adaptation method, an adaptation device, computer equipment and a storage medium of an indoor design node, wherein an indoor design model is obtained from a design model database; acquiring a design requirement text input by a client; wherein, the design requirement text comprises the design requirement of the customer on the indoor design; identifying the design requirement text based on a preset first neural network model, and identifying the design requirement keywords in the design requirement text; identifying a design node to which the design requirement keyword belongs; identifying the indoor design model based on a preset second neural network model, and identifying each design node of the indoor design model; and adding the design requirement key words into the design templates of the design nodes corresponding to the indoor design model based on the design nodes to which the design requirement key words belong so as to complete adaptive design of the indoor design nodes. The method is based on the neural network model, the design requirement text of the client is adaptively added to the design template of the corresponding design node of the indoor design model, and the adaptive design of the indoor design node is automatically carried out without depending on manpower.
Drawings
Fig. 1 is a schematic diagram illustrating steps of an adaptation method for an indoor design node according to an embodiment of the present invention;
fig. 2 is a block diagram of an adaptive apparatus for an indoor design node according to an embodiment of the present invention;
fig. 3 is a block diagram schematically illustrating the structure of a computer apparatus according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, an embodiment of the present invention provides an adaptation method for an indoor design node, including the following steps:
s1, acquiring an indoor design model from a design model database; the indoor design model comprises design templates of all design nodes of indoor design;
s2, acquiring a design requirement text input by a customer; wherein, the design requirement text comprises the design requirement of the customer on the indoor design;
s3, identifying the design requirement text based on a preset first neural network model, and identifying the design requirement keywords in the design requirement text;
s4, identifying a design node to which the design requirement keyword belongs;
s5, identifying the indoor design model based on a preset second neural network model, and identifying each design node of the indoor design model;
and S6, adding the design requirement key words into the design templates of the design nodes corresponding to the indoor design model based on the design nodes to which the design requirement key words belong so as to complete the adaptive design of the indoor design nodes.
In the embodiment, the scheme is applied to the adaptation of the indoor design nodes of the indoor design model aiming at the design requirement text input by the customer; the design requirements of the customer are automatically added into the design template of the corresponding design node of the indoor design model, manual input of designers is not needed, manual work is not needed, and the office process is lighter and more convenient.
As described in the step S1, the design model database stores an indoor design model, the indoor design model includes design templates for designing each design node in the room, and the design nodes include design modules for designing the indoor design, such as design modules for the whole space and the whole color tone, design modules for wall surfaces, windows and curtains, design modules for home appliances and furniture, and the like. The design nodes may be different from one design node to another according to the design requirements of the customers.
As described in step S2, the customer may input a specific design requirement text, and the customer inputs the design requirement for the interior design in text form, and the text can be recognized by the computer.
As described in the step S3, the first neural network model is a text recognition model, which can perform keyword recognition, and is used for recognizing the design requirement text and recognizing the design requirement keywords in the design requirement text. The design requirement keywords include, for example, the layout of the wall surface, the style of furniture, and the color tone of the whole.
As described in step S4, after the design requirement keywords are identified, the design nodes to which the design requirement keywords respectively belong need to be identified; specifically, the design requirement keywords are subjected to semantic recognition, and the design nodes to which the keywords belong can be obtained according to the meanings of the keywords. Alternatively, a correspondence between the keyword and the design node may be preset in the database, and the design node to which the design-required keyword belongs may be obtained according to the correspondence.
As described in the step S5, the second neural network model is obtained by deep learning model training, and is used for identifying an indoor design model and identifying each design node of the indoor design model; identifying each design node of the indoor design model is beneficial for subsequently adding the design requirement key words into the design template.
As described in step S6, the design requirement keyword has a design node to which the design requirement keyword belongs, and the indoor design model has a plurality of design nodes, so that the design requirement keyword is only added to the same design node in the indoor design model, and after the design requirement keyword is added to the indoor design model, a preliminary indoor design model is formed, which includes the design requirement of the customer. In the process, the neural network model is adopted to adapt to the indoor design nodes of the indoor design model, manual work is not needed, the office is lighter, and the design efficiency is improved.
In an embodiment, the step S5 of identifying the indoor design model based on a preset second neural network model and identifying each design node of the indoor design model includes:
s51, acquiring node texts corresponding to all design nodes in the indoor design model;
step S52, identifying a target feature text from the node text, inputting the target feature text into the second neural network model, and generating a classification list corresponding to the target feature text based on the second neural network model; the second neural network model is a Bert model, and the target feature text is named entity text; the classification list comprises the classification of the target feature text and the corresponding classification probability;
step S53, screening out the target classification with the maximum classification probability as the classification result of the target feature text based on the classification list; and taking the target classification as a design node of the indoor design model.
In this embodiment, each design node has a simple text to describe it, that is, the node text describes the type of the design node, and the node text includes some feature texts, which may be named entities, typically, nouns, etc. in the text; for example, the node text is a wall surface design specification and a space design requirement; named entities in the space are wall surfaces and spaces; the wall and the space are feature texts in the node texts, that is, target feature texts in this embodiment. After the target feature text is identified, the computer can only identify the text, but cannot determine the classification to which the text belongs, so that the text needs to be classified through the second neural network model. The second neural network model is a Bert model, which is one of natural speech models and can predict a word to be recognized using context information. The Bert model can classify the target feature text, that is, the target feature text can be identified as a machine-readable classification; and according to the classification result, the method can be adapted to the design node to which the design requirement keyword belongs.
In an embodiment, the step S52 of generating the classification list corresponding to the target feature text based on the second neural network model includes:
step S521, extracting a hidden vector corresponding to the target feature text based on a hidden layer of the second neural network model;
step S522, extracting weights corresponding to the hidden vectors from the classification layer of the second neural network model; the weights are used to describe the importance levels of the hidden vectors; in this embodiment, the second neural network model includes a feature extraction layer, a hidden layer, and a classification layer; the feature extraction layer is used for extracting feature vectors of the text, the hidden layer is used for extracting the hidden vectors, the classification layer is used for classifying, and the classification layer further comprises weights corresponding to the hidden layer.
Step S523, based on the classification layer of the second neural network model, calculating a score of the target feature text belonging to each classification according to the hidden vector and the weight; the score is calculated by using a softmax function.
Step S524, obtaining coding vectors corresponding to the classes, and correspondingly calculating loss function values of the target feature texts belonging to the classes according to the coding vectors and scores of the target feature texts belonging to the classes; the above-mentioned coding vector is a one-hot coding vector, and the above-mentioned loss function value adopts log function to make calculation. I.e. the loss function value = s log (score), where s is the encoding vector.
Step 525, calculating the classification probability of the target characteristic text belonging to each classification based on the loss function value of the target characteristic text belonging to each classification; the classification probability characterizes the likelihood that the target feature text belongs to each classification.
Step S526, based on the classification and the classification probability, a classification list corresponding to the target feature text is generated. The classification list comprises various classifications and classification probabilities corresponding to the target feature texts belonging to the various classifications. And selecting the classification with the highest classification probability as a classification result of the target feature text, wherein the classification result is the design node of the indoor design model.
In an embodiment, after the step S6 of adding the design requirement keyword to the design template of the design node corresponding to the indoor design model based on the design node to which the design requirement keyword belongs to complete adaptive design of the indoor design node, the method includes:
step S7, a unique customer identification code is created for the customer; the customer identification code is used for identifying the customer; the creation of the customer identification code may be generated in conjunction with the customer name and a number. For example, the customer identification code, such as KF01, is generated by using a customer short combination number.
S8, acquiring the job number of a designer handling the indoor design task; after receiving the indoor design task of the client, the management user allocates the indoor design task to a designer for processing;
s9, acquiring the job number of the management user; the job numbers of the management user and the designer are unique numbers inside the design company.
Step S10, a unique task code is created for the indoor design task of the client; the task code can be generated by combining a task number and a task attribute, and the task attribute can mark the attribute characteristics of the task.
Step S11, generating a client task code based on the client identification code and the task code; specifically, the client identification code and the task code may be concatenated to obtain the client task code.
Step S12, generating a design code based on the job number of the management user and the job number of the designer; specifically, the job number of the management user and the job number of the designer may be concatenated, or a specific character may be added between the job number of the management user and the job number of the designer, and then concatenated to obtain the unique design code.
And S13, generating a marking code of the indoor design task based on the task code and the design code, and marking the indoor design task.
In this embodiment, after the design requirement of the customer is adaptively added to the indoor design model, an indoor design task needs to be created and a specific designer is assigned to perform processing, and in order to facilitate subsequent task tracking, the indoor design task needs to be marked by a mark code. Meanwhile, in the marking process, in order to mark the indoor design task in association with the client, the designer and the management user, when a marking code for marking the indoor design task is generated, the client identification code, the job number of the designer, the job number of the management user and the task code of the indoor design task can be combined. Combining the information in the mark code to generate, so that the personnel information and task information related to the indoor design task can be conveniently identified from the mark code; the generation of the marking code is convenient for the tracking of tasks and the subsequent inspection.
In an embodiment, the step S13 of generating a tag code for the indoor design task based on the task code and the design code includes:
s131, judging whether the task code and the design code have the same character;
s132, if yes, acquiring the same number of the characters, and recording the number as the target number; if not, acquiring a preset number as the target number; for example, the preset number is 3.
S133, acquiring a standard Base64 coding table, and circularly moving codes in the standard Base64 coding table backward by preset digits in a unified manner to obtain a new Base64 coding table; wherein the value of the preset digit is equal to the value of the target number; it will be appreciated that the last code arranged in the standard Base64 code table is moved to the head of the code table.
S134, the task codes and the design codes are connected in series to obtain serial codes;
and S135, coding the concatenated codes by adopting the new Base64 coding table to obtain the mark codes of the indoor design tasks.
In this embodiment, a unique scheme for generating the above-mentioned mark code is proposed; in this embodiment, the Base64 encoding table is required to be used to generate the above-mentioned mark code, and if the standard Base64 encoding table is used, the mark code is easily tampered, so the standard Base64 encoding table can be rearranged. When the Base64 coding table is rearranged, in order to associate the arrangement mode with the task coding and the design coding, the same number of characters in the task coding and the design coding can be obtained; and based on the value of the same number of characters, moving the standard Base64 coding table, and rearranging. It can be understood that even if the Base64 encoding table is moved to only one position, the encoding table is changed significantly, and the encoding results are completely different, so that the newly rearranged Base64 encoding table has uniqueness, and the concatenated code obtained by concatenating the task code and the design code by using the Base64 encoding table also has uniqueness, cannot be easily tampered, and ensures the security of data.
In another embodiment, after the step S13 of generating a marking code for the indoor design task based on the task code and the design code, the method further includes:
step S14, converting the format of the design requirement text into a specific format;
s15, adding a mark code of the indoor design task at the specified position of the converted design requirement text;
step S16, carrying out Hash calculation on the design requirement text to obtain a corresponding standard Hash value, storing the standard Hash value and the design requirement text in a database, and establishing an index relation between the standard Hash value and the mark code in the database; and when the standard hash value in the database is called, recording the times and time of the calling of the standard hash value. The design requirement text is the text added with the mark codes.
In this embodiment, after the step S16 of establishing the index relationship between the hash value and the mark code in the database, the method includes:
s17, when task verification is needed in the processing process of the indoor design task, acquiring a design requirement text stored in a database, and acquiring a mark code corresponding to the task needing verification, and recording the mark code as a verification mark code;
s18, carrying out hash calculation on the design requirement text stored in the database to obtain a corresponding hash value;
step S19, according to the verification mark code, based on the index relation between the standard hash value and the mark code established in the database, obtaining the standard hash value corresponding to the verification mark code;
step S19a, verifying whether the hash value is the same as the standard hash value; if not, verifying that the task is tampered; if the number of times of calling the standard hash value is the same as the number of times of calling the standard hash value, obtaining the calling time and the calling time of the standard hash value, and verifying whether the number of times of calling the standard hash value is completely consistent with the number of times of task verification and the calling time of the standard hash value is completely consistent with the number of times of task verification; if the task is not completely consistent, judging that the task is tampered; and if the task is completely consistent with the task, judging that the task is not tampered.
In this embodiment, a scheme for determining whether a design task is tampered is also provided. Specifically, the design requirement text corresponding to the design task may be converted into a specific format (storage format, content editing format, picture attribute, and the like), a mark code is added at a designated position, and then hash calculation is performed to obtain a corresponding standard hash value, which is used as a basis for subsequently judging whether the design task is tampered.
When the task is verified whether the task is tampered or not subsequently, only the design requirement text stored in the database needs to be obtained, and the hash calculation is carried out to obtain a corresponding hash value; further acquiring a standard hash value of the text mark code corresponding to the design requirement from a database; verifying whether the hash value is the same as the standard hash value; if not, verifying that the task is tampered; if the number of times of calling the standard hash value is the same as the number of times of calling the standard hash value, obtaining the calling time and the calling time of the standard hash value, and verifying whether the number of times of calling the standard hash value is completely consistent with the number of times of task verification and the calling time of the standard hash value is completely consistent with the number of times of task verification; if the task is not completely consistent, judging that the task is tampered; and if the task is completely consistent with the task, judging that the task is not tampered.
The method for adapting the indoor design node provided by the embodiment of the invention is characterized in that an indoor design model is obtained from a design model database; acquiring a design requirement text input by a client; wherein, the design requirement text comprises the design requirement of the customer on the indoor design; identifying the design requirement text based on a preset first neural network model, and identifying the design requirement keywords in the design requirement text; identifying a design node to which the design requirement keyword belongs; identifying the indoor design model based on a preset second neural network model, and identifying each design node of the indoor design model; and adding the design requirement key words into the design templates of the design nodes corresponding to the indoor design model based on the design nodes to which the design requirement key words belong so as to complete adaptive design of the indoor design nodes. The method is based on the neural network model, the design requirement text of the client is adaptively added to the design template of the corresponding design node of the indoor design model, and the adaptive design of the indoor design node is automatically carried out without depending on manpower.
Referring to fig. 2, an embodiment of the present invention further provides an adaptation apparatus for an indoor design node, including:
the system comprises a first acquisition unit, a second acquisition unit and a control unit, wherein the first acquisition unit is used for acquiring an indoor design model from a design model database; the indoor design model comprises design templates of all design nodes of indoor design;
the second acquisition unit is used for acquiring a design requirement text input by a client; wherein, the design requirement text comprises the design requirement of the customer on the indoor design;
the first identification unit is used for identifying the design requirement text based on a preset first neural network model and identifying a design requirement keyword in the design requirement text;
a second identifying unit configured to identify a design node to which the design requirement keyword belongs;
the third identification unit is used for identifying the indoor design model based on a preset second neural network model and identifying each design node of the indoor design model;
and the adaptation unit is used for adding the design requirement key words into the design templates of the design nodes corresponding to the indoor design model based on the design nodes to which the design requirement key words belong so as to complete the adaptation design of the indoor design nodes.
In an embodiment, the third identifying unit includes:
the acquisition subunit is used for acquiring node texts corresponding to the design nodes in the indoor design model;
the identification subunit is used for identifying a target feature text from the node text, inputting the target feature text into the second neural network model, and generating a classification list corresponding to the target feature text based on the second neural network model; the second neural network model is a Bert model, and the target feature text is named entity text; the classification list comprises the classification of the target feature text and the corresponding classification probability;
the screening subunit is used for screening out the target classification with the maximum classification probability as the classification result of the target feature text based on the classification list; and taking the target classification as a design node of the indoor design model.
In an embodiment, the generating, by the identifying subunit, a classification list corresponding to the target feature text based on the second neural network model specifically includes:
extracting a hidden vector corresponding to the target feature text based on a hidden layer of the second neural network model;
extracting weights corresponding to the hidden vectors based on a classification layer of the second neural network model; the weights are used to describe the importance levels of the hidden vectors;
based on a classification layer of the second neural network model, calculating scores of the target feature texts belonging to various classifications according to the hidden vectors and the weights;
acquiring coding vectors corresponding to the classes, and correspondingly calculating loss function values of the target feature texts belonging to the classes according to the coding vectors and scores of the target feature texts belonging to the classes;
calculating the classification probability of the target characteristic text belonging to each classification based on the loss function value of the target characteristic text belonging to each classification;
and generating a classification list corresponding to the target characteristic text based on the classification and the classification probability.
In an embodiment, the adaptation device of the indoor design node further includes:
the first establishing unit is used for establishing a unique customer identification code for the customer; the customer identification code is used for identifying the customer;
the third acquisition unit is used for acquiring the job number of a designer handling the indoor design task; after receiving the indoor design task of the client, the management user allocates the indoor design task to a designer for processing;
a fourth obtaining unit, configured to obtain the job number of the management user;
the second creating unit is used for creating a unique task code for the indoor design task of the client;
the first generating unit is used for generating a client task code based on the client identification code and the task code;
a second generation unit configured to generate a design code based on the job number of the management user and the job number of the designer;
and a third generating unit, configured to generate a marking code of the indoor design task based on the task code and the design code, and configured to mark the indoor design task.
In an embodiment, the third generating unit includes:
the judging subunit is used for judging whether the task code and the design code have the same character;
the number obtaining subunit is used for obtaining the same number of the characters if the number of the characters exists, and recording the number as the target number; if not, acquiring a preset number as the target number;
the coding table generating subunit is used for acquiring a standard Base64 coding table, and circularly moving codes in the standard Base64 coding table backwards by preset digits in a unified manner to obtain a new Base64 coding table; wherein the value of the preset digit is equal to the value of the target number;
the concatenation subunit is used for concatenating the task code and the design code to obtain a concatenation code;
and the coding subunit is used for coding the concatenated codes by adopting the new Base64 coding table to obtain the mark codes of the indoor design tasks.
In another embodiment, the apparatus for adapting an indoor design node further includes:
a conversion unit for converting the format of the design requirement text into a specific format;
an adding unit, configured to add a mark code of the indoor design task at a specified position of the converted design requirement text;
the first calculation unit is used for carrying out Hash calculation on the design requirement text to obtain a corresponding standard Hash value, storing the standard Hash value and the design requirement text in a database, and establishing an index relation between the standard Hash value and the mark code in the database; and when the standard hash value in the database is called, recording the times and time of the calling of the standard hash value.
In another embodiment, the apparatus for adapting an indoor design node includes:
a fifth obtaining unit, configured to obtain a design requirement text stored in a database and obtain a mark code corresponding to the task to be verified when task verification is required in the process of processing the indoor design task, and record the mark code as a verification mark code;
the second calculation unit is used for carrying out hash calculation on the design requirement text stored in the database to obtain a corresponding hash value;
a sixth obtaining unit, configured to obtain, according to the verification tag code, a standard hash value corresponding to the verification tag code based on an index relationship between the standard hash value and the tag code established in the database;
a verification unit for verifying whether the hash value is the same as the standard hash value; if not, verifying that the task is tampered; if the number of times of calling the standard hash value is the same as the number of times of calling the standard hash value, obtaining the time of calling the standard hash value, and verifying whether the number of times of calling the standard hash value is completely consistent with the number of times of task verification and the time of task verification; if the task is not completely consistent, judging that the task is tampered; and if the task is completely consistent with the task, judging that the task is not tampered.
In this embodiment, please refer to the method described in the above embodiment for specific implementation of each unit and subunit in the above device embodiment, which is not described herein again.
Referring to fig. 3, an embodiment of the present invention further provides a computer device, where the computer device may be a server, and an internal structure of the computer device may be as shown in fig. 3. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer designed processor is used to provide computational and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing data such as design requirement texts. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of adapting an indoor design node.
It will be appreciated by those skilled in the art that the structure shown in fig. 3 is a block diagram of only a portion of the structure associated with the inventive arrangements, and is not intended to limit the scope of the computer apparatus to which the inventive arrangements may be applied.
An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, where the computer program, when executed by a processor, implements an adaptation method for an indoor design node. It is to be understood that the computer-readable storage medium in the present embodiment may be a volatile-readable storage medium or a non-volatile-readable storage medium.
In summary, the indoor design model is obtained from the design model database for the adaptation method, the adaptation device, the computer device and the storage medium for the indoor design node provided in the embodiment of the present invention; acquiring a design requirement text input by a client; wherein, the design requirement text comprises the design requirement of the customer on the indoor design; identifying the design requirement text based on a preset first neural network model, and identifying the design requirement keywords in the design requirement text; identifying a design node to which the design requirement keyword belongs; identifying the indoor design model based on a preset second neural network model, and identifying each design node of the indoor design model; and adding the design requirement key words into the design templates of the design nodes corresponding to the indoor design model based on the design nodes to which the design requirement key words belong so as to complete the adaptive design of the indoor design nodes. The method is based on the neural network model, the design requirement text of the client is adaptively added to the design template of the corresponding design node of the indoor design model, and the adaptive design of the indoor design node is automatically carried out without depending on manpower.
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 instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, databases, or other media provided herein or used in embodiments of the present invention may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRDRAM), enhanced SDRAM (ESDRAM), synchronous Link (Synchlink) DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct bused dynamic RAM (DRDRAM), and bused dynamic RAM (RDRAM).
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrases "comprising a," "...," or "comprising" does not exclude the presence of another identical element in a process, apparatus, article, or method comprising the element.
The above description is only for the preferred embodiment of the present invention and is not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. An adaptation method of an indoor design node is characterized by comprising the following steps:
acquiring an indoor design model from a design model database; the indoor design model comprises design templates of all design nodes of indoor design;
acquiring a design requirement text input by a client; wherein, the design requirement text comprises the design requirement of the customer on the indoor design;
identifying the design requirement text based on a preset first neural network model, and identifying design requirement keywords in the design requirement text;
identifying a design node to which the design requirement keyword belongs;
identifying the indoor design model based on a preset second neural network model, and identifying each design node of the indoor design model;
and adding the design requirement key words into the design templates of the design nodes corresponding to the indoor design model based on the design nodes to which the design requirement key words belong so as to complete the adaptive design of the indoor design nodes.
2. The method for adapting indoor design nodes according to claim 1, wherein the step of identifying the indoor design model based on a preset second neural network model and identifying each design node of the indoor design model comprises:
acquiring node texts corresponding to all design nodes in the indoor design model;
identifying a target feature text from the node text, inputting the target feature text into the second neural network model, and generating a classification list corresponding to the target feature text based on the second neural network model; wherein the second neural network model is a Bert model; the classification list comprises the classification of the target feature text and the corresponding classification probability;
screening out the target classification with the maximum classification probability as the classification result of the target characteristic text based on the classification list; and taking the target classification as a design node of the indoor design model.
3. The method of claim 2, wherein the step of generating the classification list corresponding to the target feature text based on the second neural network model comprises:
extracting a hidden vector corresponding to the target feature text based on a hidden layer of the second neural network model;
extracting weights corresponding to the hidden vectors based on a classification layer of the second neural network model; the weight is used for describing the importance level of the hidden vector;
calculating scores of the target feature texts belonging to the classes according to the hidden vectors and the weights based on a classification layer of the second neural network model;
acquiring coding vectors corresponding to the classes, and correspondingly calculating loss function values of the target feature texts belonging to the classes according to the coding vectors and scores of the target feature texts belonging to the classes;
calculating the classification probability of the target feature text belonging to each classification based on the loss function value of the target feature text belonging to each classification;
and generating a classification list corresponding to the target characteristic text based on the classification and the classification probability.
4. The method for adapting indoor design nodes according to claim 1, wherein after the step of adding the design requirement keyword to the design template of the design node corresponding to the indoor design model based on the design node to which the design requirement keyword belongs to complete the adaptive design of the indoor design node, the method comprises:
creating a unique customer identification code for said customer; the customer identification code is used for identifying the customer;
acquiring the job number of a designer of a design task in a processing chamber; after receiving the indoor design task of the client, the management user allocates the indoor design task to a designer for processing;
acquiring the job number of the management user;
creating a unique task code for the indoor design task of the client;
generating a customer task code based on the customer identification code and the task code;
generating a design code based on the job number of the management user and the job number of the designer;
and generating a marking code of the indoor design task based on the task code and the design code, wherein the marking code is used for marking the indoor design task.
5. The method of claim 4, wherein the step of generating a mark code for the indoor design task based on the task code and the design code comprises:
judging whether the task code and the design code have the same character;
if yes, acquiring the number of the same characters, and recording the number as a target number; if not, acquiring a preset number as the target number;
acquiring a standard Base64 coding table, and circularly moving codes in the standard Base64 coding table backwards by preset digits in a unified manner to obtain a new Base64 coding table; wherein the value of the preset digit is equal to the value of the target number;
the task codes and the design codes are connected in series to obtain serial codes;
and coding the concatenated codes by adopting the new Base64 coding table to obtain the mark codes of the indoor design tasks.
6. The method of claim 4, wherein the step of generating a marking code for the indoor design task based on the task code and the design code for marking the indoor design task further comprises:
converting the format of the design requirement text into a specific format;
adding a mark code of the indoor design task at a specified position of the converted design requirement text;
performing hash calculation on the design requirement text to obtain a corresponding standard hash value, storing the standard hash value and the design requirement text in a database, and establishing an index relationship between the standard hash value and the mark code in the database; and when the standard hash value in the database is called, recording the times and time of the calling of the standard hash value.
7. The method for adapting indoor design nodes according to claim 6, wherein the step of establishing the index relationship between the hash value and the mark code in the database is followed by:
when task verification is needed in the indoor design task processing process, acquiring a design requirement text stored in a database, and acquiring a mark code corresponding to the task needing verification, and marking as a verification mark code;
performing hash calculation on the design requirement text stored in the database to obtain a corresponding hash value;
acquiring a standard hash value corresponding to the verification mark code based on the index relation between the standard hash value and the mark code established in the database according to the verification mark code;
verifying whether the hash value is the same as the standard hash value; if not, verifying that the task is tampered; if the number of times of calling the standard hash value is the same as the number of times of calling the standard hash value, obtaining the calling time and the calling time of the standard hash value, and verifying whether the number of times of calling the standard hash value is completely consistent with the number of times of task verification and the calling time of the standard hash value is completely consistent with the number of times of task verification; if the task is not completely consistent, judging that the task is tampered; and if the task is completely consistent with the task, judging that the task is not tampered.
8. An adaptation device of an indoor design node, comprising:
the system comprises a first acquisition unit, a second acquisition unit and a control unit, wherein the first acquisition unit is used for acquiring an indoor design model from a design model database; the indoor design model comprises design templates of all design nodes of indoor design;
the second acquisition unit is used for acquiring a design requirement text input by a client; wherein, the design requirement text comprises the design requirement of the customer on the indoor design;
the first identification unit is used for identifying the design requirement text based on a preset first neural network model and identifying a design requirement keyword in the design requirement text;
a second identifying unit configured to identify a design node to which the design requirement keyword belongs;
the third identification unit is used for identifying the indoor design model based on a preset second neural network model and identifying each design node of the indoor design model;
and the adaptation unit is used for adding the design requirement key words into the design templates of the design nodes corresponding to the indoor design model based on the design nodes to which the design requirement key words belong so as to complete the adaptation design of the indoor design nodes.
9. A computer arrangement comprising a memory and a processor, the memory having a computer program stored therein, characterized in that the processor, when executing the computer program, is adapted to carry out the steps of the method according to any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310140730.0A CN115982830B (en) | 2023-02-21 | 2023-02-21 | Indoor design node adaptation method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310140730.0A CN115982830B (en) | 2023-02-21 | 2023-02-21 | Indoor design node adaptation method, device, computer equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115982830A true CN115982830A (en) | 2023-04-18 |
CN115982830B CN115982830B (en) | 2023-06-09 |
Family
ID=85976332
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310140730.0A Active CN115982830B (en) | 2023-02-21 | 2023-02-21 | Indoor design node adaptation method, device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115982830B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110838172A (en) * | 2019-11-13 | 2020-02-25 | 洛阳理工学院 | Indoor design system based on three-dimensional virtual imaging |
CN111160017A (en) * | 2019-12-12 | 2020-05-15 | 北京文思海辉金信软件有限公司 | Keyword extraction method, phonetics scoring method and phonetics recommendation method |
CN113128214A (en) * | 2021-03-17 | 2021-07-16 | 重庆邮电大学 | Text abstract generation method based on BERT pre-training model |
US20220051479A1 (en) * | 2020-08-14 | 2022-02-17 | Accenture Global Solutions Limited | Automated apparel design using machine learning |
CN115081087A (en) * | 2022-07-22 | 2022-09-20 | 深圳装速配科技有限公司 | Decoration cloud design method, device, equipment and storage medium based on Internet of things |
-
2023
- 2023-02-21 CN CN202310140730.0A patent/CN115982830B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110838172A (en) * | 2019-11-13 | 2020-02-25 | 洛阳理工学院 | Indoor design system based on three-dimensional virtual imaging |
CN111160017A (en) * | 2019-12-12 | 2020-05-15 | 北京文思海辉金信软件有限公司 | Keyword extraction method, phonetics scoring method and phonetics recommendation method |
US20220051479A1 (en) * | 2020-08-14 | 2022-02-17 | Accenture Global Solutions Limited | Automated apparel design using machine learning |
CN113128214A (en) * | 2021-03-17 | 2021-07-16 | 重庆邮电大学 | Text abstract generation method based on BERT pre-training model |
CN115081087A (en) * | 2022-07-22 | 2022-09-20 | 深圳装速配科技有限公司 | Decoration cloud design method, device, equipment and storage medium based on Internet of things |
Also Published As
Publication number | Publication date |
---|---|
CN115982830B (en) | 2023-06-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111160017B (en) | Keyword extraction method, phonetics scoring method and phonetics recommendation method | |
CN110765265B (en) | Information classification extraction method and device, computer equipment and storage medium | |
CN111694924B (en) | Event extraction method and system | |
CN108304372B (en) | Entity extraction method and device, computer equipment and storage medium | |
EP3499384A1 (en) | Word and sentence embeddings for sentence classification | |
CN112052324A (en) | Intelligent question answering method and device and computer equipment | |
CN113868419B (en) | Text classification method, device, equipment and medium based on artificial intelligence | |
JP7128919B2 (en) | Skill term evaluation method and device, electronic device, computer readable medium | |
CN112766319A (en) | Dialogue intention recognition model training method and device, computer equipment and medium | |
CN112699923A (en) | Document classification prediction method and device, computer equipment and storage medium | |
CN116628173B (en) | Intelligent customer service information generation system and method based on keyword extraction | |
CN111400340B (en) | Natural language processing method, device, computer equipment and storage medium | |
CN110795942B (en) | Keyword determination method and device based on semantic recognition and storage medium | |
CN112347254A (en) | News text classification method and device, computer equipment and storage medium | |
CN115577080A (en) | Question reply matching method, system, server and storage medium | |
CN116127013A (en) | Personal sensitive information knowledge graph query method and device | |
CN115687621A (en) | Short text label labeling method and device | |
CN115203372A (en) | Text intention classification method and device, computer equipment and storage medium | |
CN115982830B (en) | Indoor design node adaptation method, device, computer equipment and storage medium | |
CN114254622B (en) | Intention recognition method and device | |
CN112749530B (en) | Text encoding method, apparatus, device and computer readable storage medium | |
WO2022264435A1 (en) | Device for automatically generating entity, intent, and corpus, and program | |
CN114741512A (en) | Automatic text classification method and system | |
CN113569569A (en) | Case address extraction method, electronic device and computer-readable storage medium | |
CN112528662A (en) | Entity category identification method, device, equipment and storage medium based on meta-learning |
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 |