CN117669582A - Engineering consultation processing method and device based on deep learning and electronic equipment - Google Patents
Engineering consultation processing method and device based on deep learning and electronic equipment Download PDFInfo
- Publication number
- CN117669582A CN117669582A CN202311624814.8A CN202311624814A CN117669582A CN 117669582 A CN117669582 A CN 117669582A CN 202311624814 A CN202311624814 A CN 202311624814A CN 117669582 A CN117669582 A CN 117669582A
- Authority
- CN
- China
- Prior art keywords
- semantic
- report
- preset
- consultation
- encrypted
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013135 deep learning Methods 0.000 title claims abstract description 24
- 238000003672 processing method Methods 0.000 title claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 154
- 230000004044 response Effects 0.000 claims abstract description 116
- 238000000034 method Methods 0.000 claims abstract description 40
- 238000012549 training Methods 0.000 claims description 91
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 230000004927 fusion Effects 0.000 claims description 15
- 238000010276 construction Methods 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000007477 logistic regression Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 abstract description 9
- 230000008569 process Effects 0.000 description 18
- 239000000284 extract Substances 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 230000003190 augmentative effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000009223 counseling Methods 0.000 description 2
- 238000005336 cracking Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012384 transportation and delivery Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000009435 building construction Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Bioethics (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides an engineering consultation processing method and device based on deep learning and electronic equipment, and relates to the technical field of data processing. In the method, a consultation request sent by user equipment is received, wherein the consultation request is used for representing the consultation request aiming at a target project; generating a semantic report according to the consultation request; encrypting the semantic report to obtain an encrypted semantic report; inputting the encrypted semantic report into a preset processing model to obtain a response result; and sending the response result to the user equipment. By implementing the technical scheme provided by the application, the technical effect of improving the processing efficiency of engineering consultation is achieved.
Description
Technical Field
The application relates to the technical field of data processing, in particular to an engineering consultation processing method and device based on deep learning and electronic equipment.
Background
Engineering consultation is an intelligent service following independent, scientific and fair principles, and aims to provide consultation activities for engineering construction project decisions and management of government departments, project owners and other various clients. These counseling activities cover earlier setback phases, survey design phases, construction phases, post-production or post-delivery evaluations, and the like.
Typically, when a user needs engineering consultation services, they communicate downstream with a worker who provides the engineering consultation services. However, due to the large volume of engineering consultation, the staff needs to repeatedly inquire related data, which clearly prolongs the processing period of engineering consultation, and results in lower processing efficiency of engineering consultation.
Therefore, an engineering consultation processing method and device based on deep learning and electronic equipment are urgently needed.
Disclosure of Invention
The application provides an engineering consultation processing method and device based on deep learning and electronic equipment, which have the technical effect of improving the processing efficiency of engineering consultation.
In a first aspect of the present application, there is provided an engineering consultation processing method based on deep learning, the method including: receiving a consultation request sent by user equipment, wherein the consultation request is used for representing a consultation request aiming at a target project; generating a semantic report according to the consultation request; encrypting the semantic report to obtain an encrypted semantic report; inputting the encrypted semantic report into a preset processing model to obtain a response result; and sending the response result to the user equipment.
By adopting the technical scheme, the processing efficiency is greatly improved by automatically receiving the consultation request sent by the user equipment and automatically generating the semantic report. By encrypting the generated semantic report, the security of the user data can be protected, and the data leakage can be prevented. By inputting the encrypted semantic report into a preset processing model, a response result can be obtained quickly, and the processing efficiency is further improved. Finally, the response result is sent to the user equipment, so that the user can acquire feedback information in time, and the consultation result is better known. Therefore, the process can realize automatic processing, data encryption protection, preset processing models and timely feedback of response results, provides more efficient, safe and convenient consultation services for users, and compared with the related art, the process can automatically complete the processing of engineering consultation without manual intervention, and has the technical effect of improving the processing efficiency of the engineering consultation.
Optionally, generating a semantic report according to the consultation request specifically includes: acquiring text data in the consultation request; matching the text data with a preset keyword library by adopting a text fingerprint algorithm; if the keyword is confirmed to be successfully matched, carrying out intention recognition based on the keyword to obtain the intention consultation field; and generating the semantic report according to the intention consultation field.
By adopting the technical scheme, the text data in the consultation request are acquired and processed, so that the follow-up matching and recognition are more accurate. By matching the text data with a preset keyword library through a text fingerprint algorithm, keywords related to the text data can be quickly found, and a reference is provided for subsequent intention recognition. If the keyword is successfully matched, the intention recognition is carried out based on the keyword, so that the intention consultation field is obtained, the intention of the user is conveniently understood according to the text data input by the user, and therefore more accurate consultation service is provided. By generating the semantic report according to the intended consultation field, the consultation request of the user can be conveniently converted into a standardized semantic report, and subsequent processing and analysis are convenient. Therefore, text data can be conveniently and effectively processed, keyword matching and intention recognition can be conveniently and effectively performed, and a semantic report can be generated according to the intention recognition result, so that more accurate and efficient consultation service can be provided.
Optionally, the encrypting semantic report includes a semantic tag value, and encrypting the semantic report to obtain an encrypting semantic report specifically includes: encrypting the semantic report by adopting a secret sharing algorithm to generate an encrypted semantic report; splitting the encrypted semantic report into a plurality of semantic sub-reports, and generating corresponding ciphertext and random numbers for each semantic sub-report; calculating the label value of each semantic sub-report according to the ciphertext and the random number of each semantic sub-report; and taking the average value of the tag values of the semantic sub-reports as the semantic tag value of the encrypted semantic report.
By adopting the technical scheme, the generated semantic report is encrypted, so that the safety of user data can be protected, and the data leakage can be prevented. The secret sharing algorithm is adopted to encrypt the semantic report, so that the safety of the data can be enhanced, and the data is more difficult to crack in the transmission process. By splitting the encrypted semantic report into a plurality of semantic sub-reports, the privacy and the integrity of each semantic sub-report can be better protected, so that each semantic sub-report is difficult to be independently broken. By generating the corresponding ciphertext and random number for each semantic sub-report, the cracking difficulty can be increased, so that an attacker cannot deduce the original semantic information through the ciphertext and the random number. By calculating the label value of each semantic sub-report according to the ciphertext and the random number of each semantic sub-report, the content and meaning of each semantic sub-report can be better protected, so that an attacker cannot deduce the original semantic information through the label value. By taking the label value average value of the plurality of semantic sub-reports as the semantic label value of the encrypted semantic report, the privacy and the integrity of the whole encrypted semantic report can be better protected, so that an attacker cannot deduce the original semantic information through the label value average value.
Optionally, inputting the encrypted semantic report into a preset processing model to obtain a response result, which specifically includes: extracting a first feature word from the encrypted semantic report, wherein the first feature word is a keyword corresponding to a preset dimension, and the preset dimension comprises an engineering category, engineering content, an engineering period, an engineering budget and a construction environment; performing Hamming similarity calculation on the first feature word and any one preset encryption semantic report in the preset processing model to obtain a target encryption semantic report; and obtaining the response result according to the target encryption semantic report.
By adopting the technical scheme, the first feature words are keywords corresponding to the preset dimension and are extracted from the encrypted semantic report. By extracting the feature words, the consultation request of the user can be better understood, and more accurate matching and response can be carried out on the consultation request. And carrying out Hamming similarity calculation on the extracted first feature words and any one preset encryption semantic report in the preset processing model to obtain a target encryption semantic report. By carrying out Hamming similarity calculation, the similarity degree between two texts can be quantized, so that a preset encryption semantic report which is most matched with a user consultation request is found. And obtaining a response result by encrypting the semantic report according to the target. By matching the most similar preset encryption semantic report, the most relevant response result with the user consultation request can be obtained rapidly, so that the consultation efficiency and accuracy are improved.
Optionally, the performing hamming similarity calculation on the first feature word and any one of the preset encryption semantic report in the preset processing model to obtain a target encryption semantic report specifically includes: extracting a second feature word in any one preset encryption semantic report; calculating a hamming distance between the first feature word and the second feature word; comparing the magnitude relation between the Hamming distance and a preset Hamming distance; and if the Hamming distance is smaller than or equal to the preset Hamming distance, confirming that the preset encryption semantic report corresponding to the second feature word is the target encryption semantic report.
By adopting the technical scheme, the second feature words in any one preset encryption semantic report in the preset processing model are extracted, and the feature words are keywords corresponding to preset dimensions. By extracting these second feature words, comparison and matching with the first feature words in the user consultation request can be performed. This is a measure of similarity between two texts by calculating the hamming distance between the first feature word and the second feature word. By calculating the hamming distance, the difference between the two texts can be quantified, and thus the degree of similarity between them can be judged. By comparing the magnitude relation between the Hamming distance and the preset Hamming distance, the preset encryption semantic report which is most matched with the user consultation request can be screened out. And if the Hamming distance is smaller than or equal to the preset Hamming distance, confirming that the preset encryption semantic report corresponding to the second feature word is the target encryption semantic report. This means that the preset encrypted semantic report most similar to the user consultation request is selected as the response result, thereby improving the accuracy and efficiency of consultation.
Optionally, inputting the encrypted semantic report to a preset processing model to obtain a response result, and specifically further includes: the method comprises the steps of obtaining theme semantics in any one historical response result, wherein a plurality of historical response results are prestored in a preset processing model; calculating response tag values corresponding to the semantics of each theme; judging the similarity between the response tag value and the semantic tag value; and if the similarity is greater than or equal to a preset similarity threshold, determining that the historical response result corresponding to the response tag value is the response result.
By adopting the technical scheme, the subject semantics in any one of the historical response results are acquired, and the historical response results are stored in a preset processing model in advance. By utilizing the historical response results, the consultation request of the user can be better understood, and more accurate and comprehensive response can be provided for the consultation request. And calculating response tag values corresponding to the semantics of the topics. The response tag values are calculated according to the theme semantics of the historical response results, and can reflect the importance of different themes in the historical response results. By judging the similarity between the answer label value and the semantic label value. By comparing the similarity of the two tag values, the degree of association between them can be quantified, thereby judging the degree of matching between the user's consultation request and the historical response result. If the confirmed similarity is larger than or equal to the preset similarity threshold, the historical response result corresponding to the response label value is determined to be the response result, so that the accuracy and the efficiency of consultation are improved conveniently.
Optionally, the encrypted semantic report is input into a preset processing model, and before a response result is obtained, the preset processing model is trained; the training of the preset processing model specifically comprises the following steps: acquiring training information, wherein the training information comprises an encrypted semantic report and a response result; inputting the training information into a self-adaptive feature fusion network for training to obtain a first training result; superposing and standardizing the first training result and the training information to obtain a second training result; inputting the second training result into the self-adaptive feature fusion network for processing to obtain a third training result; and superposing and standardizing the third training result and the second training result until the training information similarity matrix is output, wherein the training information similarity matrix meets a preset logistic regression condition.
By adopting the technical scheme, the matching and response capability of the user consultation request can be improved by training the preset processing model. The training information is acquired, and the training information comprises an encrypted semantic report and a response result. The training information is used for training a preset processing model, so that the user can better understand the consultation request of the user and give an accurate response result. And training by inputting training information into the self-adaptive feature fusion network, so as to obtain a first training result. The self-adaptive feature fusion network can automatically learn and extract features according to the input training information, so that the training efficiency and accuracy are improved. And obtaining a second training result by superposing and standardizing the first training result and the training information. The processing can make the training result more stable and reliable, and improve the generalization capability of the model. And inputting the second training result into the adaptive feature fusion network again for processing to obtain a third training result, and superposing and standardizing the third training result and the second training result. The repeated superposition and standardization treatment can further improve the accuracy and stability of the model. Through outputting the training information similarity matrix, the matrix can be used for measuring the similarity between different encryption semantic reports, so that the preset logistic regression condition is met. The similarity matrix can be used for subsequent matching and response processes, and processing efficiency and accuracy are improved.
In a second aspect of the present application, an engineering consultation processing device based on deep learning is provided, where the processing device includes a receiving module and a processing module, where the receiving module is configured to receive a consultation request sent by a user equipment, where the consultation request is used to represent a consultation request for a target engineering; the processing module is used for generating a semantic report according to the consultation request; the processing module is also used for encrypting the semantic report to obtain an encrypted semantic report; the processing module is also used for inputting the encrypted semantic report into a preset processing model to obtain a response result; the processing module is further configured to send the response result to the user equipment.
In a third aspect of the present application, there is provided an electronic device comprising a processor, a memory for storing instructions, a user interface and a network interface, both for communicating to other devices, the processor being adapted to execute the instructions stored in the memory to cause the electronic device to perform the method as described above.
In a fourth aspect of the present application, there is provided a computer readable storage medium storing instructions that, when executed, perform a method as described above.
In summary, one or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
1. the processing efficiency is greatly improved by automatically receiving the consultation request sent by the user equipment and automatically generating the semantic report. By encrypting the generated semantic report, the security of the user data can be protected, and the data leakage can be prevented. By inputting the encrypted semantic report into a preset processing model, a response result can be obtained quickly, and the processing efficiency is further improved. Finally, the response result is sent to the user equipment, so that the user can acquire feedback information in time, and the consultation result is better known. Therefore, the process can realize automatic processing, data encryption protection, preset processing models and timely feedback of response results, provides more efficient, safe and convenient consultation services for users, and can automatically complete the processing of engineering consultation without manual intervention compared with the related technology, thereby having the technical effect of improving the processing efficiency of the engineering consultation;
2. by calculating the hamming distance, the difference between the two texts can be quantified, and thus the degree of similarity between them can be judged. By comparing the magnitude relation between the Hamming distance and the preset Hamming distance, the preset encryption semantic report which is most matched with the user consultation request can be screened out. And if the Hamming distance is smaller than or equal to the preset Hamming distance, confirming that the preset encryption semantic report corresponding to the second feature word is the target encryption semantic report. This means that the preset encryption semantic report most similar to the user consultation request is selected as a response result, so that the accuracy and efficiency of consultation are improved;
3. By utilizing the historical response results, the consultation request of the user can be better understood, and more accurate and comprehensive response can be provided for the consultation request. And calculating response tag values corresponding to the semantics of the topics. The response tag values are calculated according to the theme semantics of the historical response results, and can reflect the importance of different themes in the historical response results. By judging the similarity between the answer label value and the semantic label value. By comparing the similarity of the two tag values, the degree of association between them can be quantified, thereby judging the degree of matching between the user's consultation request and the historical response result. If the confirmed similarity is larger than or equal to the preset similarity threshold, the historical response result corresponding to the response label value is determined to be the response result, so that the accuracy and the efficiency of consultation are improved conveniently.
Drawings
Fig. 1 is a schematic flow chart of an engineering consultation processing method based on deep learning according to an embodiment of the present application.
Fig. 2 is a schematic block diagram of an engineering consultation processing device based on deep learning according to an embodiment of the present application.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Reference numerals illustrate: 21. a receiving module; 22. a processing module; 31. a processor; 32. a communication bus; 33. a user interface; 34. a network interface; 35. a memory.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present application, but not all embodiments.
In the description of embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described herein as "such as" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "or" for example "is intended to present related concepts in a concrete fashion.
In the description of the embodiments of the present application, the term "plurality" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating an indicated technical feature. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.
Engineering planning is a certain application of science and mathematics by which the properties of substances and energy in nature can be passed through various structures, machines, products, systems and processes, which are efficient, reliable and useful to humans with minimal time and effort. The concept of engineering is thus created and it gradually evolves into a separate discipline and skill that is closely related to engineering throughout the life, but implementation of engineering requires relatively specialized knowledge reserves. However, if the professional knowledge of the constructor cannot meet the requirements in the actual construction process, engineering consultation is required.
Engineering consultation is a very important intellectual service, which follows the principle of independence, science and fairness and aims at providing consultation for engineering construction project decision and management of government departments, project owners and other various clients. These counseling activities cover earlier setback phases, survey design phases, construction phases, post-production or post-delivery evaluations, and the like. The core of engineering consultation is to provide high-quality and comprehensive consultation service for clients by using professional knowledge and experience, help them to make more reasonable and scientific decisions, and improve the quality and benefit of projects.
Typically, when a user needs engineering consultation services, they communicate downstream with a worker who provides the engineering consultation services. However, due to the large volume of engineering consultation, the staff needs to repeatedly inquire related data, which clearly prolongs the processing period of engineering consultation, and results in lower processing efficiency of engineering consultation. In addition, due to the lack of effective informationized management means, the quality and efficiency of engineering consultation work are affected to some extent. Therefore, how to improve the processing efficiency and quality of engineering consultation is an important problem facing the current engineering consultation industry.
In order to solve the above technical problems, the present application provides an engineering consultation processing method based on deep learning, and referring to fig. 1, fig. 1 is a flow chart of an engineering consultation processing method based on deep learning provided in an embodiment of the present application. The processing method is applied to the server and comprises the steps of S110 to S150, wherein the steps are as follows:
s110, receiving a consultation request sent by user equipment, wherein the consultation request is used for representing the consultation request aiming at the target engineering.
Specifically, when a user has a problem of engineering consultation, the problem may be input by using an engineering consultation application on the user equipment or accessing an engineering consultation website, wherein the consultation request includes the consultation problem. In this embodiment of the present application, the user equipment is a smart phone, and the server is used to provide background services for the user equipment, where the server may be a server, or may be a server cluster formed by multiple servers, or is a cloud computing service center. The server may communicate with the user equipment via a wired or wireless network. Types of user equipment include, but are not limited to: android (Android) system equipment, mobile operating system (iOS) equipment developed by apple corporation, personal Computers (PCs), global area network (Web) equipment, virtual Reality (VR) equipment, augmented Reality (Augmented Reality, AR) equipment and the like.
S120, generating a semantic report according to the consultation request.
Specifically, after receiving the consultation request, the server uses natural language processing technology to perform semantic analysis on the consultation request. This process may include lexical analysis, syntactic analysis, semantic understanding, etc., to extract key information in the user's consultation request, such as project name, consultation questions, time, etc.
In one possible implementation, text data in the consultation request is obtained; matching the text data with a preset keyword library by adopting a text fingerprint algorithm; if the keyword matching is confirmed to be successful, carrying out intention recognition based on the keyword to obtain the intention consultation field; and generating a semantic report according to the intention consultation field.
Specifically, after receiving the consultation request, the server extracts text data from the consultation request. The text data contains the user's consultation requirements and questions for the target project. Text fingerprinting is a technique for text matching that determines whether two texts are similar by extracting feature information from the texts to generate a unique fingerprint. And the server matches the extracted text data with keywords in a preset keyword library and judges whether the same keywords are contained. If the matching is successful, the text data contains keywords in a preset keyword library, and then the intention recognition can be performed based on the keywords. Intent recognition refers to extracting the user's intent from text, i.e., what aspects of information the user primarily wants to learn. Through intention recognition, the intention consultation field, namely the target engineering field which the user mainly wants to consult, can be obtained. Finally, according to the intended consultation field, the server can generate a corresponding semantic report. This report is typically a semantic understanding of the user's consultation request, which may help the server better understand the user's consultation needs, thereby providing a more accurate and efficient response.
For example, assume that the user sent a consultation request: "how do the progress of the business building construction project on the morning road? "after receiving this consultation request, the server will extract text data from it: "progress of construction projects of business buildings in the morning sun". Then, the server matches the keywords in the preset keyword library, and discovers that keywords such as "the morning sun", "the commercial building", "the construction project" and the like are successfully matched. Then, the server recognizes the intention based on these keywords, and determines that the intention of the user is to know the progress of the construction project of the business building in the morning. Finally, according to the intention, the server can generate a corresponding semantic report, wherein the semantic report comprises information such as engineering names, places, consultation problems, time and the like. This semantic report may help the server better understand the user's consultation needs and provide support for subsequent responses.
S130, encrypting the semantic report to obtain an encrypted semantic report.
Specifically, the report generated by the server according to the consultation request of the user contains the semantic understanding result of the consultation problem of the user. This report is typically in a structured or semi-structured data format, such as XML, JSON, etc. The information is converted into an unreadable format through a specific algorithm and a key, so that confidentiality and integrity of the information are protected. The semantic report after encryption processing is an encrypted semantic report. It is a protected data format that prevents unauthorized access and tampering.
In one possible implementation manner, the encrypted semantic report includes a semantic tag value, and the semantic report is encrypted to obtain the encrypted semantic report, which specifically includes: encrypting the semantic report by adopting a secret sharing algorithm to generate an encrypted semantic report; splitting the encrypted semantic report into a plurality of semantic sub-reports, and generating corresponding ciphertext and random numbers for each semantic sub-report; calculating the label value of each semantic sub-report according to the ciphertext and the random number of each semantic sub-report; and taking the average value of the tag values of the semantic sub-reports as the semantic tag value of the encrypted semantic report.
Specifically, in the encrypted semantic report, the tag value of each semantic sub-report is included in addition to the encrypted content of the report itself. The tag value is a summary or description of the content of each semantic sub-report, which can facilitate subsequent queries and processing. The secret sharing algorithm is an algorithm in which a key is divided into several parts and stored in a plurality of participating terminals, respectively. Only terminals holding the corresponding shares can recombine the original secret with these shares. The secret sharing algorithm is adopted to encrypt the semantic report, so that the cracking difficulty can be increased, and the safety of data is improved. To better manage and process the encrypted semantic report, the report may be split into multiple smaller sub-reports. Each semantic sub-report contains a portion of the original semantic data and corresponding ciphertext. After the encrypted semantic report is split, a corresponding ciphertext and a random number need to be generated for each semantic sub-report. These random numbers can be used as identifiers for each sub-report, facilitating subsequent processing and querying. And according to the ciphertext and the random number of each semantic sub-report, calculating the label value of each sub-report. These tag values are summaries or descriptions of the sub-report content and may serve as identifiers for each sub-report. And finally, taking the average value of the label values of the semantic sub-reports as the semantic label value of the whole encrypted semantic report. The tag value can be used as an integral identifier, so that subsequent processing and inquiring of the encrypted semantic report are facilitated.
For example, assume that there is a semantic report, including "project name: business buildings in the morning sun; location: the morning sun district of Beijing city; consultation questions: how the project progress is ", the process of encrypting the project progress and generating the encrypted semantic report is as follows: firstly, encrypting the semantic report by adopting a secret sharing algorithm to generate an encrypted semantic report. This process may encrypt the original data into a ciphertext string. And secondly, splitting the encrypted semantic report into a plurality of semantic sub-reports. For example, it can be split into three sub-reports: "engineering name": "morning business building", "venue": "Beijing, kogyang district", "consultation problem": "how engineering progress". Next, a corresponding ciphertext and random number are generated for each semantic sub-report. For example, a random number may be generated for each sub-report separately and the corresponding ciphertext calculated. And then calculating the label value of each sub-report according to the ciphertext and the random number of each semantic sub-report. For example, a hash function such as MD5 may be used to perform hash computation on the content of each sub-report, to obtain a corresponding tag value. And taking the average value of the tag values of the semantic sub-reports as the semantic tag value of the whole encrypted semantic report. Further, if the label values of the three sub-reports are 0x123456, 0xabcdef and 0x789abc respectively, the average value of the three label values corresponding to the three sub-reports can be used as the semantic label value of the whole encrypted semantic report, namely (0x123456+0xabcdef+0x789 abc)/3. The finally obtained encrypted semantic report comprises the information such as the ciphertext, the random number, the tag value and the like of each sub report, and can be stored and used. When the encrypted semantic report needs to be queried and processed, related sub-report information can be rapidly positioned and retrieved through the semantic tag value.
S140, inputting the encrypted semantic report into a preset processing model to obtain a response result.
And S150, sending the response result to the user equipment.
Specifically, by automatically receiving the consultation request sent by the user equipment and automatically generating the semantic report, the processing efficiency is greatly improved. By encrypting the generated semantic report, the security of the user data can be protected, and the data leakage can be prevented. By inputting the encrypted semantic report into a preset processing model, a response result can be obtained quickly, and the processing efficiency is further improved. Finally, the response result is sent to the user equipment, so that the user can acquire feedback information in time, and the consultation result is better known. Therefore, the process can realize automatic processing, data encryption protection, preset processing models and timely feedback of response results, provides more efficient, safe and convenient consultation services for users, and compared with the related art, the process can automatically complete the processing of engineering consultation without manual intervention, and has the technical effect of improving the processing efficiency of the engineering consultation.
In one possible implementation manner, the method includes inputting the encrypted semantic report into a preset processing model to obtain a response result, and specifically includes: extracting a first feature word from the encrypted semantic report, wherein the first feature word is a keyword corresponding to a preset dimension, and the preset dimension comprises an engineering category, engineering content, an engineering period, an engineering budget and a construction environment; carrying out Hamming similarity calculation on the first feature word and any one preset encryption semantic report in a preset processing model to obtain a target encryption semantic report; and obtaining a response result according to the target encryption semantic report.
Specifically, the server extracts first feature words from the encrypted semantic report, wherein the feature words are keywords corresponding to preset dimensions. The preset dimensions include engineering category, engineering content, engineering period, engineering budget, and construction environment. These feature words can be regarded as key descriptions of report content, which facilitate subsequent processing and understanding. Then, the server compares the extracted first feature words with preset encryption semantic reports in a preset processing model, and calculates hamming similarity between the extracted first feature words and the preset encryption semantic reports. Hamming similarity is a method of measuring the degree of similarity of two strings, with a larger value indicating that the two strings are more similar. By calculating the similarity, a preset encrypted semantic report most similar to the input encrypted semantic report can be found. Through the calculation in the last step, a most similar preset encryption semantic report can be obtained, and the report is the target encryption semantic report. This target report is an instance of the preset process model that can be used for subsequent processing and analysis. And finally, obtaining a response result according to the target encryption semantic report. This result may be a direct answer to the user's consultation request or a further interpretation or suggestion of the user's request. This result depends on the setting of the preset processing model and the contents of the target encrypted semantic statement.
In one possible implementation manner, the hamming similarity calculation is performed on the first feature word and any one preset encryption semantic report in the preset processing model to obtain a target encryption semantic report, which specifically includes: extracting a second feature word in any one preset encryption semantic report; calculating a hamming distance between the first feature word and the second feature word; comparing the magnitude relation between the Hamming distance and the preset Hamming distance; and if the Hamming distance is smaller than or equal to the preset Hamming distance, confirming that the preset encryption semantic report corresponding to the second feature word is the target encryption semantic report.
Specifically, the server extracts any one preset encryption semantic report from the preset processing model, and extracts a second feature word from the preset encryption semantic report. These second feature words are keywords corresponding to the first feature words, and are used for calculating hamming similarity. Next, the server calculates a hamming distance between the first feature word and the second feature word. The hamming distance is the number of characters that do not match between two strings and is used to measure the similarity of the two strings. By calculating the hamming distance, the similarity between two feature words can be quantitatively evaluated. Finally, the server compares the calculated hamming distance with a preset hamming distance. The preset hamming distance is a preset threshold value for judging whether the two feature words are similar enough. If the calculated Hamming distance is smaller than or equal to the preset Hamming distance, the two feature words are similar enough, and the corresponding preset encryption semantic report can be confirmed to be the target encryption semantic report. If the calculated Hamming distance is smaller than or equal to the preset Hamming distance, the preset encryption semantic report corresponding to the second feature word can be confirmed to be the target encryption semantic report. This target report will be used as input for subsequent processing and a final answer result will be generated.
In a possible implementation manner, the method includes inputting the encrypted semantic report into a preset processing model to obtain a response result, and specifically further includes: the method comprises the steps of obtaining theme semantics in any one historical response result, and presetting a processing model to store a plurality of historical response results in advance; calculating response tag values corresponding to the semantics of each theme; judging the similarity between the response tag value and the semantic tag value; if the confirmed similarity is greater than or equal to the preset similarity threshold, determining that the historical response result corresponding to the response tag value is a response result.
Specifically, the server first obtains the topic semantics in any one of the historical response results. These topic semantics are the main content and meaning of the historical answer results for subsequent similarity calculation and judgment. Wherein, a plurality of historical response results are prestored in a preset processing model, and are used for providing reference and assisting in generating new response results. And calculating a corresponding response tag value by means of semantic meaning of each topic of each historical response result. These tag values may be the result of classification or tagging based on the content and meaning of the historical response results for subsequent similarity comparison and judgment. And the server compares the calculated response tag value with the semantic tag value and judges the similarity between the response tag value and the semantic tag value. The similarity may be calculated by a specific algorithm or model to measure the degree of similarity between the two tag values. If the calculated similarity is greater than or equal to a preset similarity threshold, it can be confirmed that the historical response result corresponding to the response tag value is most similar to the currently input encrypted semantic report. This historical answer result will be used as the final answer result. The manner of calculating the similarity may be cosine similarity or euclidean distance, which will not be described herein.
In one possible implementation manner, the encrypted semantic report is input into a preset processing model, and the preset processing model is trained before a response result is obtained; training a preset processing model, which specifically comprises the following steps: acquiring training information, wherein the training information comprises an encrypted semantic report and a response result; inputting training information into a self-adaptive feature fusion network for training to obtain a first training result; the first training result and the training information are overlapped and standardized to obtain a second training result; inputting the second training result into the self-adaptive feature fusion network for processing to obtain a third training result; and superposing and standardizing the third training result and the second training result until a training information similarity matrix is output, wherein the training information similarity matrix meets the preset logistic regression condition.
Specifically, the server first obtains training information, including encrypted semantic report and response results. The information is used to train the adaptive feature fusion network to obtain a model that can process the encrypted semantic report and generate a response result. And inputting the training information into the self-adaptive feature fusion network, and obtaining a first training result through training. The self-adaptive feature fusion network is a deep learning model, can automatically learn and extract features, and generates corresponding results according to input information. And secondly, the server performs superposition and standardization processing on the first training result and the original training information to obtain a second training result. This step can be seen as a first evaluation and adjustment of the model, helping the model to learn and understand the entered information better. And then, the server inputs the second training result into the self-adaptive feature fusion network again for processing to obtain a third training result. This process can be seen as a second evaluation and adjustment of the model, further optimizing the performance of the model. And finally, the server performs superposition and standardization processing on the third training result and the second training result, and the step can be regarded as third evaluation and adjustment of the model, so that the model is more suitable for and close to actual requirements. After multiple iterations and adjustment, a training information similarity matrix is finally output, and the matrix meets the preset logistic regression condition. Logistic regression is a common classification algorithm that can be used for prediction and classification tasks. The preset logistic regression conditions herein may refer to classification or prediction criteria set according to specific tasks and requirements.
The application also provides an engineering consultation processing device based on deep learning, referring to fig. 2, fig. 2 is a schematic block diagram of the engineering consultation processing device based on deep learning provided in the embodiment of the application. The processing device is a server, and the server comprises a receiving module 21 and a processing module 22, wherein the receiving module 21 is used for receiving a consultation request sent by user equipment, and the consultation request is used for representing a consultation request aiming at a target project; the processing module 22 is used for generating a semantic report according to the consultation request; the processing module 22 is further configured to encrypt the semantic report to obtain an encrypted semantic report; the processing module 22 is further configured to input the encrypted semantic report into a preset processing model, so as to obtain a response result; the processing module 22 is further configured to send the response result to the user equipment.
In one possible implementation manner, according to the consultation request, a semantic report is generated, which specifically includes: the receiving module 21 acquires text data in the consultation request; the processing module 22 matches the text data with a preset keyword library by adopting a text fingerprint algorithm; if the processing module 22 confirms that the keyword matching is successful, performing intention recognition based on the keyword to obtain the intention consultation field; the processing module 22 generates a semantic report according to the intended consultation field.
In one possible implementation, the encrypted semantic report includes a semantic tag value, and the processing module 22 encrypts the semantic report to obtain the encrypted semantic report, specifically includes: the processing module 22 encrypts the semantic report by adopting a secret sharing algorithm to generate an encrypted semantic report; the processing module 22 splits the encrypted semantic report into a plurality of semantic sub-reports and generates corresponding ciphertext and random numbers for each semantic sub-report; the processing module 22 calculates the label value of each semantic sub-report according to the ciphertext and the random number of each semantic sub-report; the processing module 22 takes the average value of the tag values of the semantic sub-reports as the semantic tag value of the encrypted semantic report.
In one possible implementation manner, the processing module 22 inputs the encrypted semantic report into a preset processing model to obtain a response result, and specifically includes: the processing module 22 extracts a first feature word from the encrypted semantic report, wherein the first feature word is a keyword corresponding to a preset dimension, and the preset dimension comprises an engineering category, engineering content, an engineering period, an engineering budget and a construction environment; the processing module 22 performs hamming similarity calculation on the first feature word and any one preset encryption semantic report in the preset processing model to obtain a target encryption semantic report; the processing module 22 obtains a response result according to the target encryption semantic report.
In one possible implementation manner, the processing module 22 performs hamming similarity calculation on the first feature word and any one of the preset encryption semantic reports in the preset processing model to obtain a target encryption semantic report, and specifically includes: the processing module 22 extracts a second feature word in any one preset encryption semantic report; the processing module 22 calculates a hamming distance between the first feature word and the second feature word; the processing module 22 compares the magnitude relation between the hamming distance and the preset hamming distance; if the hamming distance is less than or equal to the preset hamming distance, the processing module 22 determines that the preset encrypted semantic report corresponding to the second feature word is the target encrypted semantic report.
In a possible implementation manner, the processing module 22 inputs the encrypted semantic report into a preset processing model to obtain a response result, and specifically further includes: the receiving module 21 acquires the subject semantics in any one of the historical response results, and a plurality of historical response results are stored in a preset processing model in advance; the processing module 22 calculates response tag values corresponding to the semantics of the respective subjects; the processing module 22 judges the similarity between the answer label value and the semantic label value; if the similarity is greater than or equal to the preset similarity threshold, the processing module 22 determines that the historical response result corresponding to the response tag value is a response result.
In one possible implementation, the processing module 22 inputs the encrypted semantic report into a preset processing model, and trains the preset processing model before obtaining the response result; training a preset processing model, which specifically comprises the following steps: the receiving module 21 acquires training information, wherein the training information comprises an encrypted semantic report and a response result; the processing module 22 inputs the training information into the self-adaptive feature fusion network for training to obtain a first training result; the processing module 22 performs superposition and standardization processing on the first training result and the training information to obtain a second training result; the processing module 22 inputs the second training result into the adaptive feature fusion network to be processed, so as to obtain a third training result; the processing module 22 performs superposition and standardization processing on the third training result and the second training result until a training information similarity matrix is output, where the training information similarity matrix meets a preset logistic regression condition.
It should be noted that: in the device provided in the above embodiment, when implementing the functions thereof, only the division of the above functional modules is used as an example, in practical application, the above functional allocation may be implemented by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to implement all or part of the functions described above. In addition, the embodiments of the apparatus and the method provided in the foregoing embodiments belong to the same concept, and specific implementation processes of the embodiments of the method are detailed in the method embodiments, which are not repeated herein.
The application further provides an electronic device, and referring to fig. 3, fig. 3 is a schematic structural diagram of the electronic device provided in the embodiment of the application. The electronic device may include: at least one processor 31, at least one network interface 34, a user interface 33, a memory 35, at least one communication bus 32.
Wherein the communication bus 32 is used to enable connected communication between these components.
The user interface 33 may include a Display screen (Display) and a Camera (Camera), and the optional user interface 33 may further include a standard wired interface and a standard wireless interface.
The network interface 34 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others.
Wherein the processor 31 may comprise one or more processing cores. The processor 31 connects various parts within the overall server using various interfaces and lines, performs various functions of the server and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 35, and invoking data stored in the memory 35. Alternatively, the processor 31 may be implemented in hardware in at least one of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 31 may integrate one or a combination of several of a central processing unit (Central Processing Unit, CPU), an image processor (Graphics Processing Unit, GPU), and a modem etc. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing the content required to be displayed by the display screen; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 31 and may be implemented by a single chip.
The Memory 35 may include a random access Memory (Random Access Memory, RAM) or a Read-Only Memory (Read-Only Memory). Optionally, the memory 35 includes a non-transitory computer readable medium (non-transitory computer-readable storage medium). Memory 35 may be used to store instructions, programs, code sets, or instruction sets. The memory 35 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-described respective method embodiments, etc.; the storage data area may store data or the like involved in the above respective method embodiments. The memory 35 may alternatively be at least one memory device located remotely from the aforementioned processor 31. As shown in fig. 3, an operating system, a network communication module, a user interface module, and an application program of an engineering consultation processing method based on deep learning may be included in the memory 35 as a computer storage medium.
In the electronic device shown in fig. 3, the user interface 33 is mainly used for providing an input interface for a user, and acquiring data input by the user; and the processor 31 may be configured to invoke the application program of the deep learning-based engineering consultation processing method stored in the memory 35, which when executed by the one or more processors, causes the electronic device to perform the method of one or more of the above-described embodiments.
It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of action combinations, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required in the present application.
The present application also provides a computer-readable storage medium having instructions stored thereon. When executed by one or more processors, cause an electronic device to perform the method as described in one or more of the embodiments above.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
In the several embodiments provided herein, it should be understood that the disclosed apparatus may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, such as a division of units, merely a division of logic functions, and there may be additional divisions in actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some service interface, device or unit indirect coupling or communication connection, electrical or otherwise.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable memory. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a memory, including several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned memory includes: various media capable of storing program codes, such as a U disk, a mobile hard disk, a magnetic disk or an optical disk.
The foregoing is merely exemplary embodiments of the present disclosure and is not intended to limit the scope of the present disclosure. That is, equivalent changes and modifications are contemplated by the teachings of this disclosure, which fall within the scope of the present disclosure. Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a scope and spirit of the disclosure being indicated by the claims.
Claims (10)
1. An engineering consultation processing method based on deep learning, which is characterized by comprising the following steps:
receiving a consultation request sent by user equipment, wherein the consultation request is used for representing a consultation request aiming at a target project;
generating a semantic report according to the consultation request;
encrypting the semantic report to obtain an encrypted semantic report;
inputting the encrypted semantic report into a preset processing model to obtain a response result;
And sending the response result to the user equipment.
2. The deep learning-based engineering consultation processing method of claim 1, wherein generating a semantic report according to the consultation request specifically includes:
acquiring text data in the consultation request;
matching the text data with a preset keyword library by adopting a text fingerprint algorithm;
if the keyword is confirmed to be successfully matched, carrying out intention recognition based on the keyword to obtain the intention consultation field;
and generating the semantic report according to the intention consultation field.
3. The deep learning-based engineering consultation processing method of claim 1, wherein the encrypted semantic report includes a semantic tag value, and the encrypting the semantic report results in an encrypted semantic report, and specifically includes:
encrypting the semantic report by adopting a secret sharing algorithm to generate an encrypted semantic report;
splitting the encrypted semantic report into a plurality of semantic sub-reports, and generating corresponding ciphertext and random numbers for each semantic sub-report;
calculating the label value of each semantic sub-report according to the ciphertext and the random number of each semantic sub-report;
And taking the average value of the tag values of the semantic sub-reports as the semantic tag value of the encrypted semantic report.
4. The deep learning-based engineering consultation processing method according to claim 1 is characterized in that the encrypting semantic report is input into a preset processing model to obtain a response result, and specifically includes:
extracting a first feature word from the encrypted semantic report, wherein the first feature word is a keyword corresponding to a preset dimension, and the preset dimension comprises an engineering category, engineering content, an engineering period, an engineering budget and a construction environment;
performing Hamming similarity calculation on the first feature word and any one preset encryption semantic report in the preset processing model to obtain a target encryption semantic report;
and obtaining the response result according to the target encryption semantic report.
5. The deep learning-based engineering consultation processing method according to claim 4 is characterized by performing hamming similarity calculation on the first feature word and any one of the preset encryption semantic report in the preset processing model to obtain a target encryption semantic report, and specifically includes:
extracting a second feature word in any one preset encryption semantic report;
Calculating a hamming distance between the first feature word and the second feature word;
comparing the magnitude relation between the Hamming distance and a preset Hamming distance;
and if the Hamming distance is smaller than or equal to the preset Hamming distance, confirming that the preset encryption semantic report corresponding to the second feature word is the target encryption semantic report.
6. The deep learning-based engineering consultation processing method according to claim 3, wherein the inputting the encrypted semantic report into a preset processing model to obtain a response result specifically further includes:
the method comprises the steps of obtaining theme semantics in any one historical response result, wherein a plurality of historical response results are prestored in a preset processing model;
calculating response tag values corresponding to the semantics of each theme;
judging the similarity between the response tag value and the semantic tag value;
and if the similarity is greater than or equal to a preset similarity threshold, determining that the historical response result corresponding to the response tag value is the response result.
7. The deep learning-based engineering consultation processing method according to claim 1, wherein the encrypted semantic report is input into a preset processing model, and the preset processing model is trained before a response result is obtained; the training of the preset processing model specifically comprises the following steps:
Acquiring training information, wherein the training information comprises an encrypted semantic report and a response result;
inputting the training information into a self-adaptive feature fusion network for training to obtain a first training result;
superposing and standardizing the first training result and the training information to obtain a second training result;
inputting the second training result into the self-adaptive feature fusion network for processing to obtain a third training result;
and superposing and standardizing the third training result and the second training result until the training information similarity matrix is output, wherein the training information similarity matrix meets a preset logistic regression condition.
8. An engineering consultation processing device based on deep learning is characterized in that the processing device comprises a receiving module (21) and a processing module (22), wherein,
the receiving module (21) is used for receiving a consultation request sent by user equipment, wherein the consultation request is used for representing a consultation request aiming at a target project;
the processing module (22) is used for generating a semantic report according to the consultation request;
the processing module (22) is further used for encrypting the semantic report to obtain an encrypted semantic report;
The processing module (22) is further used for inputting the encrypted semantic report into a preset processing model to obtain a response result;
the processing module (22) is further configured to send the response result to the user equipment.
9. An electronic device, characterized in that the electronic device comprises a processor (31), a memory (35), a user interface (33) and a network interface (34), the memory (35) being adapted to store instructions, the user interface (33) and the network interface (34) being adapted to communicate to other devices, the processor (31) being adapted to execute the instructions stored in the memory (35) to cause the electronic device to perform the method according to any one of claims 1 to 7.
10. A computer readable storage medium storing instructions which, when executed, perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311624814.8A CN117669582A (en) | 2023-11-30 | 2023-11-30 | Engineering consultation processing method and device based on deep learning and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311624814.8A CN117669582A (en) | 2023-11-30 | 2023-11-30 | Engineering consultation processing method and device based on deep learning and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117669582A true CN117669582A (en) | 2024-03-08 |
Family
ID=90063410
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311624814.8A Pending CN117669582A (en) | 2023-11-30 | 2023-11-30 | Engineering consultation processing method and device based on deep learning and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117669582A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118246924A (en) * | 2024-03-28 | 2024-06-25 | 南京宁政工程咨询有限公司 | Whole process engineering consultation method, product, equipment and medium |
-
2023
- 2023-11-30 CN CN202311624814.8A patent/CN117669582A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118246924A (en) * | 2024-03-28 | 2024-06-25 | 南京宁政工程咨询有限公司 | Whole process engineering consultation method, product, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220308942A1 (en) | Systems and methods for censoring text inline | |
| US11196540B2 (en) | End-to-end secure operations from a natural language expression | |
| CN111310436B (en) | Text processing method and device based on artificial intelligence and electronic equipment | |
| WO2020220823A1 (en) | Method and device for constructing decision trees | |
| US9369488B2 (en) | Policy enforcement using natural language processing | |
| CN116157790A (en) | Document processing and response generation system | |
| WO2021042746A1 (en) | Information recommendation method and apparatus, and storage medium and electronic device | |
| US12126642B2 (en) | Network embeddings model for personal identifiable information protection | |
| WO2022095518A1 (en) | Automatic interface test method and apparatus, and computer device and storage medium | |
| CN110855648A (en) | Early warning control method and device for network attack | |
| WO2021139476A1 (en) | Intersection data generation method, and federated model training method based on intersection data | |
| CN117669582A (en) | Engineering consultation processing method and device based on deep learning and electronic equipment | |
| CN114760149B (en) | Data cross-border compliance management and control method and device, computer equipment and storage medium | |
| Cao et al. | Generative steganography based on long readable text generation | |
| CN111460394A (en) | Copyright file verification method and device and computer readable storage medium | |
| CN110738323A (en) | Method and device for establishing machine learning model based on data sharing | |
| WO2022121183A1 (en) | Text model training method, recognition method, apparatus, device and storage medium | |
| US11664998B2 (en) | Intelligent hashing of sensitive information | |
| KR102319006B1 (en) | First copyright holder authentication system using blockchain and its method | |
| CN114996675A (en) | Data query method and device, computer equipment and storage medium | |
| CN114372082A (en) | Data query method and device based on artificial intelligence, electronic equipment and medium | |
| CN116055067B (en) | Weak password detection method, device, electronic equipment and medium | |
| US20200106602A1 (en) | Blockchain system having multiple parity levels and multiple layers for improved data security | |
| US20130117245A1 (en) | Method and system for identification of asset records in a version managed datastore | |
| CN114528908B (en) | Network request data classification model training method, classification method and storage medium |
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 |