CN116756296B - Consultation information management method and system based on privacy protection - Google Patents
Consultation information management method and system based on privacy protection Download PDFInfo
- Publication number
- CN116756296B CN116756296B CN202311041110.8A CN202311041110A CN116756296B CN 116756296 B CN116756296 B CN 116756296B CN 202311041110 A CN202311041110 A CN 202311041110A CN 116756296 B CN116756296 B CN 116756296B
- Authority
- CN
- China
- Prior art keywords
- semantic
- report
- character
- consultation
- node
- 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.)
- Active
Links
- 238000007726 management method Methods 0.000 title claims abstract description 25
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000012549 training Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
-
- 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
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Bioethics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Human Computer Interaction (AREA)
- Medical Informatics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a consultation information management method and a consultation information management system based on privacy protection, which belong to the technical field of information management, wherein the method comprises the following steps: s1, acquiring consultation sentences input by a user, and generating a real-time semantic report according to the consultation sentences; s2, encrypting the real-time semantic report to generate an encrypted semantic report, and generating a semantic tag value for the encrypted semantic report; s3, matching corresponding consultation answer sentences for the encrypted semantic report according to the semantic tag value; s4, transmitting the encrypted semantic report and the consultation answer statement to the user terminal. The consultation information management method compares the semantic tag value with the answer tag value, so that the most proper and accurate answer sentence can be determined, and a user can conveniently and quickly ask questions for many times.
Description
Technical Field
The invention belongs to the technical field of information management, and particularly relates to a consultation information management method and system based on privacy protection.
Background
With the development and maturity of network, communication and computer technologies, more and more industries start online consultation services, but when users perform online consultation, the frequently encountered problems are that the information content is too much, the answers required by the users cannot be found quickly, and the consultation efficiency and the user experience are seriously affected.
Disclosure of Invention
In order to solve the problems, the invention provides a consultation information management method and system based on privacy protection.
The technical scheme of the invention is as follows: the consultation information management method based on privacy protection comprises the following steps:
s1, acquiring consultation sentences input by a user, and generating a real-time semantic report according to the consultation sentences;
s2, encrypting the real-time semantic report to generate an encrypted semantic report, and generating a semantic tag value for the encrypted semantic report;
s3, matching corresponding consultation answer sentences for the encrypted semantic report according to the semantic tag value;
s4, transmitting the encrypted semantic report and the consultation answer statement to the user terminal.
The beneficial effects of the invention are as follows:
(1) The consultation information management method generates a real-time semantic report by constructing and training an undirected weighted graph, and can reflect character conditions of inquiry sentences in an image;
(2) The consultation information management method encrypts the semantic report and generates a corresponding semantic tag value, so that the privacy safety of a user can be protected to the greatest extent, and the consultation statement is prevented from being revealed in the transmission process; meanwhile, the semantic report is split, so that the algorithm flow can be greatly simplified;
(3) The consultation information management method compares the semantic tag value with the answer tag value, so that the most proper and accurate answer sentence can be determined, and a user can conveniently and quickly ask questions for many times.
Further, S1 comprises the following sub-steps:
s11, acquiring consultation sentences input by a user, extracting characters in the consultation sentences, and generating a character set;
s12, constructing and training a character undirected weighted graph according to the character set;
s13, calculating the character weight of each node in the character undirected weighted graph;
and S14, generating a real-time semantic report according to the character weights of the nodes.
Further, in S12, the expression of the character undirected weighted graph G is: g= (V, E), where V represents a set of character nodes and E represents a set of edges between characters;
in S12, the specific method for training the character undirected weighted graph comprises the following steps: traversing each node of the undirected weighted graph by utilizing a sliding window, so that the similarity between any node and other nodes is less than 0.5, and completing training;
wherein, similarity d between node i and node j ij The calculation formula of (2) is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein A is ij Representing the edge weight of the node i connected with the node j, M represents the weight matrix of the character undirected weighted graph, and l in The edge weight value of the node i connected with the other nodes except the node j is represented, and N represents the number of the nodes of the character undirected weighted graph.
Further, in S13, the character weight σ of the node i i The calculation formula of (2) is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein d in And (5) representing the similarity of the node i and the rest nodes, and N representing the number of nodes of the character undirected weighted graph.
Further, in S14, the specific method for generating the real-time semantic report includes: and acquiring a report template, and filling characters corresponding to the nodes into the report template according to the sequence of the character weights of the nodes from large to small to generate a real-time semantic report.
Further, S2 comprises the following sub-steps:
s21, encrypting the real-time semantic report by using a secret sharing algorithm to generate an encrypted semantic report;
s22, splitting the encrypted semantic report into a plurality of semantic sub-reports, and generating corresponding ciphertext and random numbers for each semantic sub-report;
s23, calculating the label value of each semantic sub-report according to the ciphertext and the random number of the semantic sub-report;
s24, taking the average value of the tag values of all the semantic sub-reports as the semantic tag value of the encrypted semantic report.
Further, in S23, the calculation formula of the tag value ω of the semantic sub-report is:the method comprises the steps of carrying out a first treatment on the surface of the Wherein c represents the random number of the semantic sub-report, T represents the ciphertext of the semantic sub-report, H (·) represents the collision hash function operation, and X k Mapping function value of kth keyword in semantic sub-report, K represents number of keywords of semantic sub-report, and alpha k And the keyword value of the kth keyword in the semantic sub-report is represented.
Further, S3 comprises the following sub-steps:
s31, obtaining topic sentences in the historical answer sentences by using an LDA topic model;
s32, calculating answer label values of the theme sentences;
s33, taking the historical answer sentence corresponding to the answer label value closest to the semantic label value as the consultation answer sentence.
Further, in S32, the calculation formula of the answer tag value λ of the subject sentence is:the method comprises the steps of carrying out a first treatment on the surface of the Wherein x is g One-hot vector, w, representing the g-th word in a subject sentence g The word frequency of the G-th word in the topic sentence is represented, G represents the number of words of the topic sentence, and epsilon represents the minimum value.
Based on the method, the invention also provides a consultation information management system based on privacy protection, which comprises a semantic report generating unit, a semantic label generating unit and a consultation answer sentence generating unit;
the semantic report generating unit is used for acquiring the consultation statement input by the user and generating a real-time semantic report according to the consultation statement;
the semantic label generating unit is used for encrypting the real-time semantic report, generating an encrypted semantic report and generating a semantic label value for the encrypted semantic report;
the consultation answer sentence generating unit is used for matching the corresponding consultation answer sentence for the encrypted semantic report according to the semantic tag value, and transmitting the encrypted semantic report and the consultation answer sentence to the user terminal.
The beneficial effects of the invention are as follows: the consultation information management system can determine the most proper and accurate answer sentence by comparing the semantic tag value with the answer tag value, and is convenient for users to quickly ask questions for many times.
Drawings
FIG. 1 is a flow chart of a method of consulting information management based on privacy protection;
fig. 2 is a block diagram of a consultation information management system based on privacy protection.
Detailed Description
Embodiments of the present invention are further described below with reference to the accompanying drawings.
As shown in fig. 1, the present invention provides a consultation information management method based on privacy protection, which includes the following steps:
s1, acquiring consultation sentences input by a user, and generating a real-time semantic report according to the consultation sentences;
s2, encrypting the real-time semantic report to generate an encrypted semantic report, and generating a semantic tag value for the encrypted semantic report;
s3, matching corresponding consultation answer sentences for the encrypted semantic report according to the semantic tag value;
s4, transmitting the encrypted semantic report and the consultation answer statement to the user terminal.
In an embodiment of the present invention, S1 comprises the following sub-steps:
s11, acquiring consultation sentences input by a user, extracting characters in the consultation sentences, and generating a character set;
s12, constructing and training a character undirected weighted graph according to the character set;
s13, calculating the character weight of each node in the character undirected weighted graph;
and S14, generating a real-time semantic report according to the character weights of the nodes.
Consultation sentences are usually composed of several words, and when extracting characters, each word is regarded as one character by default, so that a character set is obtained. Training the undirected weighted graph by using the similarity of any character and other characters, rapidly determining all adjacent points of each node in the undirected weighted graph, completing training, directly filling the characters into a report template according to the size sequence of the weights of the characters, and generating a real-time semantic report.
In the embodiment of the present invention, in S12, the expression of the character undirected weighted graph G is: g= (V, E), where V represents a set of character nodes and E represents a set of edges between characters;
in S12, the specific method for training the character undirected weighted graph comprises the following steps: traversing each node of the undirected weighted graph by utilizing a sliding window, so that the similarity between any node and other nodes is less than 0.5, and completing training;
wherein, similarity d between node i and node j ij The calculation formula of (2) is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein A is ij Representing the edge weight of the node i connected with the node j, M represents the weight matrix of the character undirected weighted graph, and l in The edge weight value of the node i connected with the other nodes except the node j is represented, and N represents the number of the nodes of the character undirected weighted graph.
The adjacency matrix can reflect the adjacency relation among the vertexes in the undirected weighted graph, and all adjacency points of a certain vertex can be rapidly determined through the adjacency matrix, so that the adjacency matrix is utilized to calculate the similarity to complete training.
In the embodiment of the present invention, in S13, the character weight σ of the node i i The calculation formula of (2) is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein d in And (5) representing the similarity of the node i and the rest nodes, and N representing the number of nodes of the character undirected weighted graph.
In the embodiment of the invention, in S14, the specific method for generating the real-time semantic report is as follows: and acquiring a report template, and filling characters corresponding to the nodes into the report template according to the sequence of the character weights of the nodes from large to small to generate a real-time semantic report.
The reporting template may be drawn in advance by the user or a history report may be used.
In an embodiment of the present invention, S2 comprises the following sub-steps:
s21, encrypting the real-time semantic report by using a secret sharing algorithm to generate an encrypted semantic report;
s22, splitting the encrypted semantic report into a plurality of semantic sub-reports, and generating corresponding ciphertext and random numbers for each semantic sub-report;
s23, calculating the label value of each semantic sub-report according to the ciphertext and the random number of the semantic sub-report;
s24, taking the average value of the tag values of all the semantic sub-reports as the semantic tag value of the encrypted semantic report.
Secret sharing algorithm: the secret is split in a proper way, each split share is managed by different participants, and only a plurality of participants cooperate together to recover the secret message.
The encryption semantic report is split, a plurality of sub-reports can be obtained, repeated calculation of a plurality of characters can be avoided when the label value is calculated, and then the average value of the label values of all the sub-reports is directly used as the semantic label value, so that the algorithm flow is greatly simplified.
In the embodiment of the present invention, in S23, the calculation formula of the tag value ω of the semantic sub-report is:the method comprises the steps of carrying out a first treatment on the surface of the Wherein c represents the random number of the semantic sub-report, T represents the ciphertext of the semantic sub-report, H (·) represents the collision hash function operation, and X k Mapping function value of kth keyword in semantic sub-report, K represents number of keywords of semantic sub-report, and alpha k And the keyword value of the kth keyword in the semantic sub-report is represented.
The keywords can express the central content of the semantic sub-report, and the keywords of the sub-report are extracted by using an unsupervised keyword extraction algorithm.
In an embodiment of the present invention, S3 comprises the following sub-steps:
s31, obtaining topic sentences in the historical answer sentences by using an LDA topic model;
s32, calculating answer label values of the theme sentences;
s33, taking the historical answer sentence corresponding to the answer label value closest to the semantic label value as the consultation answer sentence.
And storing a large number of historical answer sentences in a database, and analyzing and comparing the semantic tag value of the consultation sentence with the historical answer sentences to determine the most suitable answer sentence. The historical answer sentences are generated according to all the historical consultation sentences, and the consultation conditions of the users are more comprehensively covered, so that the matching is more universal.
The LDA topic model is used for presuming topic distribution of historical answer sentences in the database, and each historical answer sentence in the data can be given out topic sentences in a probability form.
In the embodiment of the present invention, in S32, the calculation formula of the answer tag value λ of the subject sentence is:the method comprises the steps of carrying out a first treatment on the surface of the Wherein x is g One-hot vector, w, representing the g-th word in a subject sentence g The word frequency of the G-th word in the topic sentence is represented, G represents the number of words of the topic sentence, and epsilon represents the minimum value.
Based on the method, the invention also provides a consultation information management system based on privacy protection, as shown in fig. 2, comprising a semantic report generating unit, a semantic label generating unit and a consultation answer sentence generating unit;
the semantic report generating unit is used for acquiring the consultation statement input by the user and generating a real-time semantic report according to the consultation statement;
the semantic label generating unit is used for encrypting the real-time semantic report, generating an encrypted semantic report and generating a semantic label value for the encrypted semantic report;
the consultation answer sentence generating unit is used for matching the corresponding consultation answer sentence for the encrypted semantic report according to the semantic tag value, and transmitting the encrypted semantic report and the consultation answer sentence to the user terminal.
Those of ordinary skill in the art will recognize that the embodiments described herein are for the purpose of aiding the reader in understanding the principles of the present invention and should be understood that the scope of the invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific modifications and combinations from the teachings of the present disclosure without departing from the spirit thereof, and such modifications and combinations remain within the scope of the present disclosure.
Claims (6)
1. The consultation information management method based on privacy protection is characterized by comprising the following steps:
s1, acquiring consultation sentences input by a user, and generating a real-time semantic report according to the consultation sentences;
s2, encrypting the real-time semantic report to generate an encrypted semantic report, and generating a semantic tag value for the encrypted semantic report;
s3, matching corresponding consultation answer sentences for the encrypted semantic report according to the semantic tag value;
s4, transmitting the encrypted semantic report and the consultation answer statement to the user terminal;
the step S1 comprises the following substeps:
s11, acquiring consultation sentences input by a user, extracting characters in the consultation sentences, and generating a character set;
s12, constructing and training a character undirected weighted graph according to the character set;
s13, calculating the character weight of each node in the character undirected weighted graph;
s14, generating a real-time semantic report according to the character weight of each node;
in S12, the expression of the character undirected weighted graph G is: g= (V, E), where V represents a set of character nodes and E represents a set of edges between characters;
in the step S12, the specific method for training the character undirected weighted graph is as follows: traversing each node of the undirected weighted graph by utilizing a sliding window, so that the similarity between any node and other nodes is less than 0.5, and completing training;
wherein, similarity d between node i and node j ij The calculation formula of (2) is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein A is ij Representing the edge weight of the node i connected with the node j, M represents the weight matrix of the character undirected weighted graph, and l in The edge weight values of the node i and the nodes except the node j are represented, and N represents the number of the nodes of the character undirected weighted graph;
in S13, the character weight sigma of the node i i The calculation formula of (2) is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein d in The similarity of the node i and the rest nodes is represented, and N represents the number of the nodes of the character undirected weighted graph;
in the step S14, the specific method for generating the real-time semantic report includes: and acquiring a report template, and filling characters corresponding to the nodes into the report template according to the sequence of the character weights of the nodes from large to small to generate a real-time semantic report.
2. The privacy protection-based advisory information management method as claimed in claim 1, wherein the S2 includes the sub-steps of:
s21, encrypting the real-time semantic report by using a secret sharing algorithm to generate an encrypted semantic report;
s22, splitting the encrypted semantic report into a plurality of semantic sub-reports, and generating corresponding ciphertext and random numbers for each semantic sub-report;
s23, calculating the label value of each semantic sub-report according to the ciphertext and the random number of the semantic sub-report;
s24, taking the average value of the tag values of all the semantic sub-reports as the semantic tag value of the encrypted semantic report.
3. The method for managing consulting information based on privacy protection of claim 2, wherein in S23, the calculation formula of the tag value ω of the semantic sub-report is:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein c represents the random number of the semantic sub-report, T represents the ciphertext of the semantic sub-report, H (·) represents the collision hash function operation, and X k Mapping function value of kth keyword in semantic sub-report, K represents number of keywords of semantic sub-report, and alpha k And the keyword value of the kth keyword in the semantic sub-report is represented.
4. The privacy protection-based advisory information management method as claimed in claim 1, wherein the S3 includes the sub-steps of:
s31, obtaining topic sentences in the historical answer sentences by using an LDA topic model;
s32, calculating answer label values of the theme sentences;
s33, taking the historical answer sentence corresponding to the answer label value closest to the semantic label value as the consultation answer sentence.
5. The method for managing consulting information based on privacy protection of claim 4, wherein in S32, the calculation formula of the answer tag value λ of the topic sentence is:the method comprises the steps of carrying out a first treatment on the surface of the Wherein x is g One-hot vector, w, representing the g-th word in a subject sentence g The word frequency of the G-th word in the topic sentence is represented, G represents the number of words of the topic sentence, and epsilon represents the minimum value.
6. The consultation information management system based on privacy protection is characterized by comprising a semantic report generation unit, a semantic label generation unit and a consultation answer sentence generation unit;
the semantic report generating unit is used for acquiring consultation sentences input by a user and generating real-time semantic reports according to the consultation sentences;
the semantic label generating unit is used for encrypting the real-time semantic report, generating an encrypted semantic report and generating a semantic label value for the encrypted semantic report;
the consultation answer sentence generating unit is used for matching the corresponding consultation answer sentence for the encrypted semantic report according to the semantic tag value and transmitting the encrypted semantic report and the consultation answer sentence to the user terminal;
the consultation information management system based on privacy protection is realized based on a consultation information management method, and the method comprises the following steps:
s1, acquiring consultation sentences input by a user, and generating a real-time semantic report according to the consultation sentences;
s2, encrypting the real-time semantic report to generate an encrypted semantic report, and generating a semantic tag value for the encrypted semantic report;
s3, matching corresponding consultation answer sentences for the encrypted semantic report according to the semantic tag value;
s4, transmitting the encrypted semantic report and the consultation answer statement to the user terminal;
the step S1 comprises the following substeps:
s11, acquiring consultation sentences input by a user, extracting characters in the consultation sentences, and generating a character set;
s12, constructing and training a character undirected weighted graph according to the character set;
s13, calculating the character weight of each node in the character undirected weighted graph;
s14, generating a real-time semantic report according to the character weight of each node;
in S12, the expression of the character undirected weighted graph G is: g= (V, E), where V represents a set of character nodes and E represents a set of edges between characters;
in the step S12, the specific method for training the character undirected weighted graph is as follows: traversing each node of the undirected weighted graph by utilizing a sliding window, so that the similarity between any node and other nodes is less than 0.5, and completing training;
wherein, similarity d between node i and node j ij The calculation formula of (2) is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein A is ij Representing the edge weight of the node i connected with the node j, M represents the weight matrix of the character undirected weighted graph, and l in The edge weight values of the node i and the nodes except the node j are represented, and N represents the number of the nodes of the character undirected weighted graph;
in S13, the character weight sigma of the node i i The calculation formula of (2) is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein d in The similarity of the node i and the rest nodes is represented, and N represents the number of the nodes of the character undirected weighted graph;
in the step S14, the specific method for generating the real-time semantic report includes: and acquiring a report template, and filling characters corresponding to the nodes into the report template according to the sequence of the character weights of the nodes from large to small to generate a real-time semantic report.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311041110.8A CN116756296B (en) | 2023-08-18 | 2023-08-18 | Consultation information management method and system based on privacy protection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311041110.8A CN116756296B (en) | 2023-08-18 | 2023-08-18 | Consultation information management method and system based on privacy protection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116756296A CN116756296A (en) | 2023-09-15 |
| CN116756296B true CN116756296B (en) | 2023-11-17 |
Family
ID=87957597
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311041110.8A Active CN116756296B (en) | 2023-08-18 | 2023-08-18 | Consultation information management method and system based on privacy protection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116756296B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107292189A (en) * | 2017-05-15 | 2017-10-24 | 温州大学瓯江学院 | The privacy of user guard method of text-oriented retrieval service |
| CN109471964A (en) * | 2018-10-23 | 2019-03-15 | 哈尔滨工程大学 | A kind of fuzzy multi-key word based on synset can search for encryption method |
| CN110874348A (en) * | 2019-11-13 | 2020-03-10 | 哈尔滨工业大学 | Privacy differential data retrieval method in mixed cloud environment |
| WO2022095368A1 (en) * | 2020-11-04 | 2022-05-12 | 平安科技（深圳）有限公司 | Question-answer corpus generation method and device based on text generation model |
| CN114707474A (en) * | 2022-04-25 | 2022-07-05 | 平安普惠企业管理有限公司 | Report generation method and device, electronic equipment and computer readable storage medium |
| CN115203391A (en) * | 2022-06-24 | 2022-10-18 | 润联软件系统(深圳)有限公司 | Information retrieval method and device, computer equipment and storage medium |
-
2023
- 2023-08-18 CN CN202311041110.8A patent/CN116756296B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107292189A (en) * | 2017-05-15 | 2017-10-24 | 温州大学瓯江学院 | The privacy of user guard method of text-oriented retrieval service |
| CN109471964A (en) * | 2018-10-23 | 2019-03-15 | 哈尔滨工程大学 | A kind of fuzzy multi-key word based on synset can search for encryption method |
| CN110874348A (en) * | 2019-11-13 | 2020-03-10 | 哈尔滨工业大学 | Privacy differential data retrieval method in mixed cloud environment |
| WO2022095368A1 (en) * | 2020-11-04 | 2022-05-12 | 平安科技（深圳）有限公司 | Question-answer corpus generation method and device based on text generation model |
| CN114707474A (en) * | 2022-04-25 | 2022-07-05 | 平安普惠企业管理有限公司 | Report generation method and device, electronic equipment and computer readable storage medium |
| CN115203391A (en) * | 2022-06-24 | 2022-10-18 | 润联软件系统(深圳)有限公司 | Information retrieval method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116756296A (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111428881B (en) | Recognition model training method, device, equipment and readable storage medium | |
| CN109165683B (en) | Sample prediction method, device and storage medium based on federal training | |
| CN111932386B (en) | User account determining method and device, information pushing method and device, and electronic equipment | |
| US11442804B2 (en) | Anomaly detection in data object text using natural language processing (NLP) | |
| CN115062732A (en) | Resource sharing cooperation recommendation method and system based on big data user tag information | |
| CN113378160A (en) | Graph neural network model defense method and device based on generative confrontation network | |
| CN116402630B (en) | Financial risk prediction method and system based on characterization learning | |
| CN114282692A (en) | Model training method and system for longitudinal federal learning | |
| CN109783805A (en) | A kind of network community user recognition methods and device | |
| CN112016850A (en) | Service evaluation method and device | |
| CN116992052B (en) | Long text abstracting method and device for threat information field and electronic equipment | |
| CN113742763A (en) | Confusion encryption method and system based on government affair sensitive data | |
| Lhasiw et al. | A bidirectional LSTM model for classifying Chatbot messages | |
| CN116756296B (en) | Consultation information management method and system based on privacy protection | |
| CN111582284B (en) | Privacy protection method and device for image recognition and electronic equipment | |
| CN111179101A (en) | Internet insurance marketing data processing system based on shared network | |
| CN114297693B (en) | Model pre-training method and device, electronic equipment and storage medium | |
| CN114422230B (en) | Information transmission system based on data encryption | |
| CN112561538B (en) | Risk model creation method, apparatus, computer device and readable storage medium | |
| CN114997423A (en) | Semi-centralized confrontation training method for federal learning | |
| CN114329127A (en) | Characteristic box dividing method, device and storage medium | |
| CN113936677A (en) | Tone conversion method, device, computer equipment and storage medium | |
| CN112883703A (en) | Method and device for identifying associated text, electronic equipment and storage medium | |
| CN116502255B (en) | Feature extraction method and device based on secret sharing | |
| Tang et al. | A feature interaction network for customer churn prediction |
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 |