CN116450918A - Online information consultation method and device and electronic equipment - Google Patents
Online information consultation method and device and electronic equipment Download PDFInfo
- Publication number
- CN116450918A CN116450918A CN202310678566.9A CN202310678566A CN116450918A CN 116450918 A CN116450918 A CN 116450918A CN 202310678566 A CN202310678566 A CN 202310678566A CN 116450918 A CN116450918 A CN 116450918A
- Authority
- CN
- China
- Prior art keywords
- feature vector
- consultation
- information
- hash value
- reply
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 239000013598 vector Substances 0.000 claims abstract description 216
- 230000005540 biological transmission Effects 0.000 claims abstract description 13
- 238000013507 mapping Methods 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 10
- 238000013075 data extraction Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 230000003993 interaction Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 210000001503 joint Anatomy 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000003068 static effect Effects 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9538—Presentation of query results
-
- 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
-
- 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)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an online information consultation method, a device and electronic equipment, which can be applied to an online information consultation platform, wherein the method comprises the following steps: acquiring consultation information of a consultation party, carrying out semantic recognition on the consultation information, and extracting a first feature vector; based on a preset hash mode, a first hash value is obtained according to the first feature vector, and is sent to each consultation platform to carry out second hash value retrieval so as to determine a second hash value group of each consultation platform corresponding to the first hash value, wherein the second hash value is generated based on the second feature vector of the questioning information of each consultation platform; acquiring a second feature vector corresponding to a second hash value group of each consultation platform, searching according to the first feature vector in a trusted execution environment, and determining a matched target feature vector from the second feature vector; and obtaining the reply information corresponding to the target feature vector from the corresponding consultation platform in an unintentional transmission mode, and feeding back the reply corresponding to the consultation information to the consultation party.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to an online information consultation method and apparatus, and an electronic device.
Background
More and more scenes are provided with on-line information consultation services, such as e-commerce, medical treatment and other scenes, and users can obtain corresponding solutions only by uploading the problems through a network, so that the method is quite convenient.
The prior consultation mode is that the user uploads clear questions, and then gives the clear questions to the corresponding consultation platform, the consultation platform searches related questions according to the clear questions, obtains a plurality of answers to sort, and finally feeds back one or more answers with the forefront sorting to the user.
But in the above manner, the privacy of the user is not protected.
Disclosure of Invention
The embodiment of the invention provides an online information consultation method, an online information consultation device and electronic equipment, so as to protect privacy of users.
In order to solve the technical problems, the invention is realized as follows:
in a first aspect, the present application provides an online information consultation method, applied to an online information consultation platform, where the method includes: acquiring consultation information of a consultation party, carrying out semantic recognition on the consultation information, and extracting a first feature vector; based on a preset hash mode, a first hash value is obtained according to the first feature vector, and is sent to each consultation platform to carry out second hash value retrieval so as to determine a second hash value group of each consultation platform corresponding to the first hash value, wherein the second hash value is generated based on the second feature vector of the questioning information of each consultation platform; acquiring a second feature vector corresponding to a second hash value group of each consultation platform, searching according to the first feature vector in a trusted execution environment, and determining a matched target feature vector from the second feature vector; before determining the target feature vector, receiving reply information corresponding to the second feature vector uploaded by each consultation platform; after the target feature vector is determined, if the received reply information contains reply information corresponding to the target feature vector, feeding back a reply corresponding to the consultation information to the consultation party; after the target feature vector is determined, if the received reply information does not contain the reply information corresponding to the target feature vector, obtaining the reply information corresponding to the target feature vector from the corresponding consultation platform in an inadvertent transmission mode, and feeding back a reply corresponding to the consultation information to the consultation party.
Further, the preset hash mode is a location-sensitive hash, and before the consulting information of the consulting party is obtained, the method further includes: receiving questioning information of each consultation platform, carrying out semantic recognition on the consultation information, and extracting a second feature vector; hashing the second feature vector based on a preset hashing mode to obtain a second hash value; and issuing a second hash value to each consultation platform so as to match the first hash value with the second hash value on the consultation platform.
Further, the method further comprises: encrypting the second feature vector to obtain encrypted data, establishing a first mapping relation between the encrypted data and the second hash value, and storing the first mapping relation into an encrypted database; the obtaining the second feature vector corresponding to the second hash value group of each consultation platform includes: receiving first identification information of a second hash value uploaded by a consultation platform; extracting encrypted data from the encrypted database according to the first identification information and the first mapping relation; and decrypting according to the encrypted data to obtain a second feature vector.
Further, the decrypting according to the encrypted data to obtain the second feature vector includes: sending a decryption request to a key management component, wherein the key management component and an online information consultation platform are two independent devices; and receiving a decryption key of the key management assembly, and decrypting the encrypted data according to the decryption key to obtain a second feature vector.
Further, the key management component is configured to: receiving a decryption request and sending a data extraction request to a consultant according to the decryption request; receiving data extraction permission fed back by the consultant, and returning a decryption key.
Further, before encrypting the second feature vector, the method further comprises: matching according to second feature vectors of different consultation platforms to determine intersection data; in the trusted execution environment, obtaining reply information corresponding to the question information corresponding to the intersection data, matching the reply information, and if the reply information is consistent with the answer information, de-duplicating the second feature vector.
Further, the method further comprises: the method comprises the steps that a second feature vector is sent to a consultant and stored in a database of the consultant, and a second mapping relation between the second feature vector and a second hash value is established, wherein the consultant is used for obtaining a second feature vector corresponding to a second hash value group according to the second mapping relation between the second feature vector and the second hash value; the obtaining the second feature vector corresponding to the second hash value group of each consultation platform includes: and receiving a second feature vector uploaded by the consultation platform.
Further, after obtaining the reply information corresponding to the target feature vector, a process of feeding back the reply corresponding to the consultation information to the consultation party includes: determining a ranking related index of the reply information, wherein the ranking related index comprises the similarity of the first feature vector and the second feature vector, the use times of the reply information, the praise number of the reply information and the number of times that the reply information solves the consultation information; and ordering the reply information according to the reply information and the ordering related indexes, and feeding back a reply corresponding to the consultation information to the consultation party.
In a second aspect, the present application provides an online information consultation apparatus, the apparatus including: the first feature acquisition module is used for acquiring the consultation information of the consultation party, carrying out semantic recognition on the consultation information and extracting a first feature vector; the first characteristic matching module is used for obtaining a first hash value according to a first characteristic vector based on a preset hash mode, and sending the first hash value to each consultation platform to perform second hash value retrieval so as to determine a second hash value group corresponding to the first hash value of each consultation platform, wherein the second hash value is generated based on a second characteristic vector of questioning information of each consultation platform; the target feature acquisition module is used for acquiring second feature vectors corresponding to the second hash value groups of the consultation platforms, searching the second feature vectors according to the first feature vectors in the trusted execution environment, and determining matched target feature vectors from the second feature vectors; the reply information receiving module is used for receiving reply information corresponding to the second feature vector uploaded by each consultation platform before determining the target feature vector; the first reply feedback module is used for feeding back a reply corresponding to the consultation information to the consultation party when the received reply information contains the reply information corresponding to the target feature vector after the target feature vector is determined; and the second reply feedback module is used for acquiring reply information corresponding to the target feature vector from the corresponding consultation platform in an inadvertent transmission mode and feeding back a reply corresponding to the consultation information to the consultation party when the received reply information does not contain the reply information corresponding to the target feature vector after the target feature vector is determined.
In a third aspect, the present application provides an electronic device, including: a memory and at least one processor; the memory is used for storing computer execution instructions; the at least one processor is configured to execute computer-executable instructions stored in the memory, such that the at least one processor performs the method according to the first aspect.
The application provides an online information consultation method which is applied to an online information consultation platform, and the method comprises the following steps: acquiring consultation information of a consultation party, carrying out semantic recognition on the consultation information, and extracting a first feature vector; based on a preset hash mode, a first hash value is obtained according to the first feature vector, and is sent to each consultation platform to carry out second hash value retrieval so as to determine a second hash value group of each consultation platform corresponding to the first hash value, wherein the second hash value is generated based on the second feature vector of the questioning information of each consultation platform; acquiring a second feature vector corresponding to a second hash value group of each consultation platform, searching according to the first feature vector in a trusted execution environment, and determining a matched target feature vector from the second feature vector; before determining the target feature vector, receiving reply information corresponding to the second feature vector uploaded by each consultation platform; after the target feature vector is determined, if the received reply information contains reply information corresponding to the target feature vector, feeding back a reply corresponding to the consultation information to the consultation party; after the target feature vector is determined, if the received reply information does not contain the reply information corresponding to the target feature vector, obtaining the reply information corresponding to the target feature vector from the corresponding consultation platform in an inadvertent transmission mode, and feeding back a reply corresponding to the consultation information to the consultation party.
In the embodiment of the application, the online information consultation platform can be in butt joint with a plurality of consultation platforms, and can provide an interaction page for the consultant, the consultant inputs consultation information in the interaction page, and after receiving the consultation information, the online information consultation platform interacts with the consultation platforms, so that corresponding replies are obtained and fed back to the consultant. In this embodiment of the present application, the on-line information consulting platform may perform semantic recognition on the consulting information, extract the first feature vector, and then perform hash processing, where the hash processing is hash processing that retains features of the first feature vector, and may still retain a similarity relationship between two feature vectors when the similarity relationship exists between the two feature vectors, for example, may perform hash processing in a position-sensitive hash manner. After the hash is performed, the first hash value does not expose the original data, and the first hash value can be transmitted to the consultation platforms for matching, so that each consultation platform determines a matched second hash value group. The on-line information consultation platform can acquire a second feature vector corresponding to the second hash value set, match the first feature vector with the second feature vector in a trusted execution environment, and further determine a target feature vector corresponding to the first feature vector from the second feature vector. And then, obtaining reply information corresponding to the target feature vector, and sorting, so that one or more replies with the front sorting are screened out according to the sorting and fed back to the consultant. Before determining the target feature vector, the online information consultation platform may receive the reply information corresponding to the second hash value set, where each consultant may not know the reply adopted finally, i.e. may not expose the intent of the consultant. After determining the target feature vector, if reply information is received, a reply can be quickly acquired. If the corresponding reply information is not received, the required reply information can be acquired in an unintentional transmission mode, and the data quantity of useless replies received by the online information consultation platform is reduced. In addition, the replies received by the online information consultation platform can be processed in plaintext in the trusted execution environment, and are in an encrypted state in other environments, namely the data of each consultation platform cannot be exposed, so that the safety is ensured.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:
FIG. 1 is a flow diagram of an online information consultation method according to an embodiment of the present application;
FIG. 2 is a schematic diagram illustrating steps of an online information consultation method according to another embodiment of the present application;
fig. 3 is a schematic structural view of an on-line information consultation apparatus according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment of the application provides an online information consultation method, which can be applied to an online information consultation platform, as shown in fig. 1, the online information consultation platform can be connected with a plurality of consultation platforms in a butt joint mode, in addition, the online information consultation platform can provide an interaction page for a consultant, the consultant inputs consultation information in the interaction page, and after receiving the consultation information, the online information consultation platform interacts with the consultation platform, so that corresponding replies are obtained and fed back to the consultant.
Specifically, the embodiment of the application provides an online information consultation method, which can be applied to an online information consultation platform, as shown in fig. 2, and includes:
step 202, acquiring consultation information of a consultation party, carrying out semantic recognition on the consultation information, and extracting a first feature vector;
step 204, based on a preset hash mode, obtaining a first hash value according to the first feature vector, and sending the first hash value to each consultation platform for second hash value retrieval to determine a second hash value group of each consultation platform corresponding to the first hash value, wherein the second hash value is generated based on a second feature vector of the questioning information of each consultation platform;
step 206, obtaining a second feature vector corresponding to the second hash value group of each consultation platform, searching according to the first feature vector in the trusted execution environment, and determining a matched target feature vector from the second feature vector;
step 208, before determining the target feature vector, receiving reply information corresponding to the second feature vector uploaded by each consultation platform;
step 210, after determining the target feature vector, if the received reply information includes reply information corresponding to the target feature vector, feeding back a reply corresponding to the consultation information to the consultation party;
step 212, after determining the target feature vector, if the received reply information does not include the reply information corresponding to the target feature vector, obtaining the reply information corresponding to the target feature vector from the corresponding consultation platform in an inadvertent transmission mode, and feeding back the reply corresponding to the consultation information to the consultant.
In this embodiment of the present application, the on-line information consulting platform may perform semantic recognition on the consulting information, extract the first feature vector, and then perform hash processing, where the hash processing is hash processing that retains features of the first feature vector, and may still retain a similarity relationship between two feature vectors when the similarity relationship exists between the two feature vectors, for example, may perform hash processing in a position-sensitive hash manner. After the hash is performed, the first hash value does not expose the original data, and the first hash value can be transmitted to the consultation platforms for matching, so that each consultation platform determines a matched second hash value group. The on-line information consultation platform can acquire a second feature vector corresponding to the second hash value set, match the first feature vector with the second feature vector in a trusted execution environment, and further determine a target feature vector corresponding to the first feature vector from the second feature vector. And then, obtaining reply information corresponding to the target feature vector, and sorting, so that one or more replies with the front sorting are screened out according to the sorting and fed back to the consultant. Before determining the target feature vector, the online information consultation platform may receive the reply information corresponding to the second hash value set, where each consultant may not know the reply adopted finally, i.e. may not expose the intent of the consultant. After determining the target feature vector, if reply information is received, a reply can be quickly acquired. If the corresponding reply information is not received, the required reply information can be acquired in an unintentional transmission mode, and the data quantity of useless replies received by the online information consultation platform is reduced. In addition, the replies received by the online information consultation platform can be processed in plaintext in the trusted execution environment, and are in an encrypted state in other environments, namely the data of each consultation platform cannot be exposed, so that the safety is ensured.
The second hash value of each consultation platform can be generated in advance, and can be generated after the online information consultation platform receives the questioning information of each consultation platform, performs feature extraction and vector hash. Specifically, as an optional embodiment, the preset hash manner is a location-sensitive hash, and before obtaining the consulting information of the consulting party, the method further includes: receiving questioning information of each consultation platform, carrying out semantic recognition on the consultation information, and extracting a second feature vector; hashing the second feature vector based on a preset hashing mode to obtain a second hash value; and issuing a second hash value to each consultation platform so as to match the first hash value with the second hash value on the consultation platform. In the embodiment of the application, the online platform (online information consultation platform) only receives the questioning information of each consultation platform and does not obtain the corresponding reply information, so that the safety of the reply data of each consultation platform is ensured. The location sensitive hash may also be referred to as a Locality Sensitive Hash (LSH), among others.
The second feature vector in the embodiment of the application can be stored in a database of the online platform, and an association relation with the second hash value is established, and the online platform can directly extract the second feature vector from the database of the online platform. Specifically, as an optional embodiment, the method further includes: encrypting the second feature vector to obtain encrypted data, establishing a first mapping relation between the encrypted data and the second hash value, and storing the first mapping relation into an encrypted database; the obtaining the second feature vector corresponding to the second hash value group of each consultation platform includes: receiving first identification information of a second hash value uploaded by a consultation platform; extracting encrypted data from the encrypted database according to the first identification information and the first mapping relation; and decrypting according to the encrypted data to obtain a second feature vector. The second feature vector may be stored in an encrypted manner for decryption at the time of use. The key for encrypting the second feature vector may be stored in the key management component, and in particular, as an alternative embodiment, the decrypting according to the encrypted data, to obtain the second feature vector, includes: sending a decryption request to a key management component, wherein the key management component and an online information consultation platform are two independent devices; and receiving a decryption key of the key management assembly, and decrypting the encrypted data according to the decryption key to obtain a second feature vector. The key management component is independent of the online platform, so that a background person of the online platform cannot easily acquire the decryption key, and the safety of data is improved. And when decryption is needed, the key management component can issue a decryption key to the online platform after obtaining the license of the consultant. Specifically, as an alternative embodiment, the key management component is configured to: receiving a decryption request and sending a data extraction request to a consultant according to the decryption request; receiving data extraction permission fed back by the consultant, and returning a decryption key.
The method may further include, before encrypting the second feature vector, if there is a repetition in part of the data of the different consultants, performing deduplication on the repeated data, and in particular, as an optional embodiment, the method further includes: matching according to second feature vectors of different consultation platforms to determine intersection data; in the trusted execution environment, obtaining reply information corresponding to the question information corresponding to the intersection data, matching the reply information, and if the reply information is consistent with the answer information, de-duplicating the second feature vector. In different fields, answers corresponding to the same question may be different, so that the scheme can determine whether the questions are consistent and whether the answers are consistent, and if so, the duplicate removal processing is performed. And, the application can remove the weight based on the similarity of the second feature vector, so that the process of carrying out data alignment in advance by different consultants is avoided, and the application is more convenient.
In addition, the second feature vector can be stored in the database of the online platform according to the scheme, and can also be stored in the database of the consultant, so that the occupation of database resources of the online platform is avoided. Specifically, as an optional embodiment, the method further includes: the method comprises the steps that a second feature vector is sent to a consultant and stored in a database of the consultant, and a second mapping relation between the second feature vector and a second hash value is established, wherein the consultant is used for obtaining a second feature vector corresponding to a second hash value group according to the second mapping relation between the second feature vector and the second hash value; the obtaining the second feature vector corresponding to the second hash value group of each consultation platform includes: and receiving a second feature vector uploaded by the consultation platform. When the second feature vector is stored in the database of the consultant, the online platform can receive the second feature vector corresponding to the second hash value set uploaded by the consultant platform, so that a subsequent matching process is performed.
According to the embodiment of the application, the online platform can sort the reply information according to the index corresponding to the reply, and then feed back the corresponding information to the consultant. Specifically, as an optional embodiment, after obtaining the reply information corresponding to the target feature vector, a process of feeding back the reply corresponding to the advisory information to the advisory party includes: determining a ranking related index of the reply information, wherein the ranking related index comprises the similarity of the first feature vector and the second feature vector, the use times of the reply information, the praise number of the reply information and the number of times that the reply information solves the consultation information; and ordering the reply information according to the reply information and the ordering related indexes, and feeding back a reply corresponding to the consultation information to the consultation party. According to the method and the device for processing the query information, the weight can be set for the ranking related indexes, the feature similarity is the similarity of the corresponding questions, and the correlation with the quality of the response results is small, so that the low weight is preferably set for the similarity of the first feature vector and the second feature vector, the high weight is set for the use times of the response information, the praise number of the response information, the number of times of the response information for solving the query information and the like, and the weight is higher than the weight of the similarity, and therefore the method and the device can be more reasonably recommended for users.
On the basis of the above embodiment, the embodiment of the present application further provides an online information consultation device, as shown in fig. 3, where the device includes:
the first feature obtaining module 302 is configured to obtain consulting information of a consulting party, perform semantic recognition on the consulting information, and extract a first feature vector;
the first feature matching module 304 is configured to obtain a first hash value according to a first feature vector based on a preset hash manner, and send the first hash value to each consultation platform to perform a second hash value search, so as to determine a second hash value set corresponding to the first hash value of each consultation platform, where the second hash value is generated based on a second feature vector of the questioning information of each consultation platform;
the target feature obtaining module 306 is configured to obtain a second feature vector corresponding to the second hash value set of each consulting platform, retrieve the second feature vector according to the first feature vector in the trusted execution environment, and determine a matched target feature vector from the second feature vector;
a reply information receiving module 308, configured to receive reply information corresponding to the second feature vector uploaded by each consultation platform before determining the target feature vector;
the first reply feedback module 310 is configured to, after determining the target feature vector, feedback a reply corresponding to the consulting information to the consulting party if the received reply information includes the reply information corresponding to the target feature vector;
the second reply feedback module 312 is configured to, after determining the target feature vector, obtain, by means of an unintentional transmission, reply information corresponding to the target feature vector from the corresponding advisory platform if the received reply information does not include reply information corresponding to the target feature vector, and feedback a reply corresponding to the advisory information to the advisory party.
In the embodiment of the application, the online information consultation device can be applied to an online information consultation platform, the online information consultation platform can be in butt joint with a plurality of consultation platforms, the online information consultation platform can provide an interaction page for a consultant, the consultant inputs consultation information in the interaction page, and after receiving the consultation information, the online information consultation platform interacts with the consultation platform, so that corresponding replies are obtained and fed back to the consultant. In this embodiment of the present application, the on-line information consulting platform may perform semantic recognition on the consulting information, extract the first feature vector, and then perform hash processing, where the hash processing is hash processing that retains features of the first feature vector, and may still retain a similarity relationship between two feature vectors when the similarity relationship exists between the two feature vectors, for example, may perform hash processing in a position-sensitive hash manner. After the hash is performed, the first hash value does not expose the original data, and the first hash value can be transmitted to the consultation platforms for matching, so that each consultation platform determines a matched second hash value group. The on-line information consultation platform can acquire a second feature vector corresponding to the second hash value set, match the first feature vector with the second feature vector in a trusted execution environment, and further determine a target feature vector corresponding to the first feature vector from the second feature vector. And then, obtaining reply information corresponding to the target feature vector, and sorting, so that one or more replies with the front sorting are screened out according to the sorting and fed back to the consultant. Before determining the target feature vector, the online information consultation platform may receive the reply information corresponding to the second hash value set, where each consultant may not know the reply adopted finally, i.e. may not expose the intent of the consultant. After determining the target feature vector, if reply information is received, a reply can be quickly acquired. If the corresponding reply information is not received, the required reply information can be acquired in an unintentional transmission mode, and the data quantity of useless replies received by the online information consultation platform is reduced. In addition, the replies received by the online information consultation platform can be processed in plaintext in the trusted execution environment, and are in an encrypted state in other environments, namely the data of each consultation platform cannot be exposed, so that the safety is ensured.
On the basis of the above embodiment, the present application further provides an electronic device, including: a memory and at least one processor; the memory is used for storing computer execution instructions; the at least one processor is configured to execute computer-executable instructions stored in the memory, such that the at least one processor performs the method as described in the above embodiments.
The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the processes of the data processing method embodiment, and can achieve the same technical effects, so that repetition is avoided and no further description is given here. Wherein the computer readable storage medium is selected from Read-Only Memory (ROM), random access Memory (Random ACGess Memory, RAM), magnetic disk or optical disk.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. According to the definitions herein, the computer-readable medium does not include a transitory computer-readable medium (transmission medium), such as a modulated data signal and carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The foregoing is merely exemplary of the present invention and is not intended to limit the present invention. Various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the invention are to be included in the scope of the claims of the present invention.
Claims (10)
1. An online information consultation method is characterized by being applied to an online information consultation platform, and comprises the following steps:
acquiring consultation information of a consultation party, carrying out semantic recognition on the consultation information, and extracting a first feature vector;
based on a preset hash mode, a first hash value is obtained according to the first feature vector, and is sent to each consultation platform to carry out second hash value retrieval so as to determine a second hash value group of each consultation platform corresponding to the first hash value, wherein the second hash value is generated based on the second feature vector of the questioning information of each consultation platform;
acquiring a second feature vector corresponding to a second hash value group of each consultation platform, searching according to the first feature vector in a trusted execution environment, and determining a matched target feature vector from the second feature vector;
before determining the target feature vector, receiving reply information corresponding to the second feature vector uploaded by each consultation platform;
after the target feature vector is determined, if the received reply information contains reply information corresponding to the target feature vector, feeding back a reply corresponding to the consultation information to the consultation party;
after the target feature vector is determined, if the received reply information does not contain the reply information corresponding to the target feature vector, obtaining the reply information corresponding to the target feature vector from the corresponding consultation platform in an inadvertent transmission mode, and feeding back a reply corresponding to the consultation information to the consultation party.
2. The method of claim 1, wherein the predetermined hash manner is a location-sensitive hash, and wherein the method further comprises, prior to obtaining the consulting information of the consulting party:
receiving questioning information of each consultation platform, carrying out semantic recognition on the consultation information, and extracting a second feature vector;
hashing the second feature vector based on a preset hashing mode to obtain a second hash value;
and issuing a second hash value to each consultation platform so as to match the first hash value with the second hash value on the consultation platform.
3. The method according to claim 2, wherein the method further comprises:
encrypting the second feature vector to obtain encrypted data, establishing a first mapping relation between the encrypted data and the second hash value, and storing the first mapping relation into an encrypted database;
the obtaining the second feature vector corresponding to the second hash value group of each consultation platform includes:
receiving first identification information of a second hash value uploaded by a consultation platform;
extracting encrypted data from the encrypted database according to the first identification information and the first mapping relation;
and decrypting according to the encrypted data to obtain a second feature vector.
4. A method according to claim 3, wherein decrypting the encrypted data to obtain the second feature vector comprises:
sending a decryption request to a key management component, wherein the key management component and an online information consultation platform are two independent devices;
and receiving a decryption key of the key management assembly, and decrypting the encrypted data according to the decryption key to obtain a second feature vector.
5. The method of claim 4, wherein the key management component is configured to:
receiving a decryption request and sending a data extraction request to a consultant according to the decryption request;
receiving data extraction permission fed back by the consultant, and returning a decryption key.
6. A method according to claim 3, wherein prior to encrypting the second feature vector, the method further comprises:
matching according to second feature vectors of different consultation platforms to determine intersection data;
in the trusted execution environment, obtaining reply information corresponding to the question information corresponding to the intersection data, matching the reply information, and if the reply information is consistent with the answer information, de-duplicating the second feature vector.
7. The method according to claim 2, wherein the method further comprises:
the method comprises the steps that a second feature vector is sent to a consultant and stored in a database of the consultant, and a second mapping relation between the second feature vector and a second hash value is established, wherein the consultant is used for obtaining a second feature vector corresponding to a second hash value group according to the second mapping relation between the second feature vector and the second hash value;
the obtaining the second feature vector corresponding to the second hash value group of each consultation platform includes:
and receiving a second feature vector uploaded by the consultation platform.
8. The method of claim 1, wherein the process of feeding back the response corresponding to the advisory information to the advisory party after obtaining the response information corresponding to the target feature vector, comprises:
determining a ranking related index of the reply information, wherein the ranking related index comprises the similarity of the first feature vector and the second feature vector, the use times of the reply information, the praise number of the reply information and the number of times that the reply information solves the consultation information;
and ordering the reply information according to the reply information and the ordering related indexes, and feeding back a reply corresponding to the consultation information to the consultation party.
9. An on-line information consultation apparatus, the apparatus comprising:
the first feature acquisition module is used for acquiring the consultation information of the consultation party, carrying out semantic recognition on the consultation information and extracting a first feature vector;
the first characteristic matching module is used for obtaining a first hash value according to a first characteristic vector based on a preset hash mode, and sending the first hash value to each consultation platform to perform second hash value retrieval so as to determine a second hash value group corresponding to the first hash value of each consultation platform, wherein the second hash value is generated based on a second characteristic vector of questioning information of each consultation platform;
the target feature acquisition module is used for acquiring second feature vectors corresponding to the second hash value groups of the consultation platforms, searching the second feature vectors according to the first feature vectors in the trusted execution environment, and determining matched target feature vectors from the second feature vectors;
the reply information receiving module is used for receiving reply information corresponding to the second feature vector uploaded by each consultation platform before determining the target feature vector;
the first reply feedback module is used for feeding back a reply corresponding to the consultation information to the consultation party when the received reply information contains the reply information corresponding to the target feature vector after the target feature vector is determined;
and the second reply feedback module is used for acquiring reply information corresponding to the target feature vector from the corresponding consultation platform in an inadvertent transmission mode and feeding back a reply corresponding to the consultation information to the consultation party when the received reply information does not contain the reply information corresponding to the target feature vector after the target feature vector is determined.
10. An electronic device, comprising: a memory and at least one processor;
the memory is used for storing computer execution instructions;
the at least one processor is configured to execute computer-executable instructions stored in the memory, such that the at least one processor performs the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310678566.9A CN116450918B (en) | 2023-06-09 | 2023-06-09 | Online information consultation method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310678566.9A CN116450918B (en) | 2023-06-09 | 2023-06-09 | Online information consultation method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116450918A true CN116450918A (en) | 2023-07-18 |
| CN116450918B CN116450918B (en) | 2023-08-25 |
Family
ID=87134026
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310678566.9A Active CN116450918B (en) | 2023-06-09 | 2023-06-09 | Online information consultation method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116450918B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002230155A (en) * | 2001-02-06 | 2002-08-16 | Teisuke Fukazawa | Consultation system utilizing internet |
| JP2011150404A (en) * | 2010-01-19 | 2011-08-04 | Future Univ-Hakodate | Information retrieval device, and information retrieval method |
| CN106294350A (en) * | 2015-05-13 | 2017-01-04 | 阿里巴巴集团控股有限公司 | A kind of text polymerization and device |
| CN109376354A (en) * | 2018-09-26 | 2019-02-22 | 出门问问信息科技有限公司 | Fraud recognition methods, device, electronic equipment and readable storage medium storing program for executing |
| CN112231452A (en) * | 2020-10-12 | 2021-01-15 | 平安信托有限责任公司 | Question-answering method, device, equipment and storage medium based on natural language processing |
| CN112948562A (en) * | 2021-04-01 | 2021-06-11 | 广东优碧胜科技有限公司 | Question and answer processing method and device, computer equipment and readable storage medium |
| US11106703B1 (en) * | 2021-01-13 | 2021-08-31 | Bigid Inc | Clustering of structured and semi-structured data |
| CN114048490A (en) * | 2021-10-19 | 2022-02-15 | 深圳市有传科技有限公司 | Information processing method and device, equipment and storage medium thereof |
| WO2022217926A1 (en) * | 2021-04-16 | 2022-10-20 | 深圳前海微众银行股份有限公司 | Image finding method, blockchain, cloud server and image finding apparatus |
-
2023
- 2023-06-09 CN CN202310678566.9A patent/CN116450918B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002230155A (en) * | 2001-02-06 | 2002-08-16 | Teisuke Fukazawa | Consultation system utilizing internet |
| JP2011150404A (en) * | 2010-01-19 | 2011-08-04 | Future Univ-Hakodate | Information retrieval device, and information retrieval method |
| CN106294350A (en) * | 2015-05-13 | 2017-01-04 | 阿里巴巴集团控股有限公司 | A kind of text polymerization and device |
| CN109376354A (en) * | 2018-09-26 | 2019-02-22 | 出门问问信息科技有限公司 | Fraud recognition methods, device, electronic equipment and readable storage medium storing program for executing |
| CN112231452A (en) * | 2020-10-12 | 2021-01-15 | 平安信托有限责任公司 | Question-answering method, device, equipment and storage medium based on natural language processing |
| US11106703B1 (en) * | 2021-01-13 | 2021-08-31 | Bigid Inc | Clustering of structured and semi-structured data |
| CN112948562A (en) * | 2021-04-01 | 2021-06-11 | 广东优碧胜科技有限公司 | Question and answer processing method and device, computer equipment and readable storage medium |
| WO2022217926A1 (en) * | 2021-04-16 | 2022-10-20 | 深圳前海微众银行股份有限公司 | Image finding method, blockchain, cloud server and image finding apparatus |
| CN114048490A (en) * | 2021-10-19 | 2022-02-15 | 深圳市有传科技有限公司 | Information processing method and device, equipment and storage medium thereof |
Non-Patent Citations (1)
| Title |
|---|
| 杨恒;王庆;何周灿;: "面向高维图像特征匹配的多次随机子向量量化哈希算法", 计算机辅助设计与图形学学报, no. 03 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116450918B (en) | 2023-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110704418A (en) | Block chain information query method, device and equipment | |
| EP3814929B1 (en) | Blockchain-based content management method, apparatus, and electronic device | |
| CN109992978B (en) | Information transmission method and device and storage medium | |
| CN110569213A (en) | File access method, device and equipment | |
| US10192278B2 (en) | Traceable data audit apparatus, method, and non-transitory computer readable storage medium thereof | |
| JP2017534964A (en) | Password protection question setting method and apparatus | |
| CN108154024B (en) | Data retrieval method and device and electronic equipment | |
| US11494392B2 (en) | Tracking entity activity using computer generation of values for blockchain network entries | |
| CN116450918B (en) | Online information consultation method and device and electronic equipment | |
| CN111159192B (en) | Big data based data warehousing method and device, storage medium and processor | |
| CN116028964B (en) | Information security risk management system | |
| CN115526551B (en) | Agricultural product traceability data processing method based on artificial intelligence and cloud platform | |
| CN110674383B (en) | Public opinion query method, device and equipment | |
| CN106294417A (en) | A kind of data reordering method, device and electronic equipment | |
| CN110019357B (en) | Database query script generation method and device | |
| CN110020040B (en) | Method, device and system for querying data | |
| CN105187508A (en) | User relationship processing method and system | |
| CN110414251B (en) | Data monitoring method and device | |
| CN111241376B (en) | Multistage information matching method and device and cloud service platform | |
| CN111666347B (en) | Data processing method, device and equipment | |
| CN112800127A (en) | Data mining analysis method and device based on transaction bill | |
| CN112508472A (en) | Method and system for viewing order information of same account by multiple persons | |
| CN110647766A (en) | Method and system for ensuring file downloading safety of data warehouse | |
| CN113312650B (en) | Transaction log privacy protection method and device | |
| CN116028444B (en) | File fingerprint generation method, device and system, electronic equipment 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |