A network information technology consultation exchange platform application method and system

Abstract

The application discloses a network information technology consultation exchange platform application method and system, and relates to the field of network information technology, which realizes personalized consultation exchange of new and old users by constructing a platform connected with multiple technology databases. New users are provided with initial simulation consultation when registering, and a similar technology database is constructed through in-depth data mining, and the matching degree is calculated to push related content. Old users construct demand models according to historical records to push customized information. All exchange record data are protected to prevent leakage. The system analyzes IP and geographical position in real time, implements risk area management and double identity verification to ensure data security. The method improves the accuracy of information pushing and user experience, strengthens data protection, and improves the safety and service quality of the platform.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of network information technology, and particularly relates to a network information technology consultation exchange platform application method and system. BACKGROUND

[0002] In today's era of rapid development of information technology, network information technology consultation exchange platforms have become an important carrier for promoting technological progress and innovation. In recent years, with the continuous maturity of technologies such as big data, cloud computing, and artificial intelligence, traditional technology consultation exchange modes have gradually transformed into online platforms. These platforms integrate various technical resources to provide convenient consultation exchange services for users, greatly improving the efficiency of technology dissemination and knowledge sharing. However, the existing network information technology consultation exchange platforms still have certain deficiencies in user experience, data mining depth, personalized recommendation, and data protection.

[0003] Firstly, the existing platforms often lack in-depth mining of user interests and personalized recommendations during user registration and consultation. Although new users can choose topics of interest when registering, the platform fails to effectively utilize this information in subsequent consultation processes, resulting in a deviation between the pushed technical data and expert recommendations and the actual needs of users. Secondly, the data mining models of existing platforms are relatively simple, making it difficult to accurately calculate the comprehensive similarity between user interest vectors and technical feature vectors, thereby affecting the accurate grasp of user needs. In addition, for old users, the existing platforms are insufficient in calculating the degree of matching of professional nature and interests, failing to fully utilize the historical behavior data of users to optimize the recommendation results. Finally, in terms of data protection, the existing platforms have imperfect protection measures for user exchange consultation records, posing a risk of data leakage. The network information technology consultation exchange platform application method and system of the present application have conducted in-depth research and innovation in these aspects in order to provide better services and safer user experiences. SUMMARY

[0004] In view of the above existing problems, the present application aims to provide a network information technology consultation exchange platform application method and system, which aims to solve the problems of inaccurate user interest recognition, inaccurate personalized service push, imperfect data security protection measures, and poor user exchange experience in the prior art. By constructing a personalized consultation exchange platform based on multiple technical databases, the present application realizes in-depth mining and accurate matching of user interests, dynamically constructs a user demand model to provide personalized content recommendations, and designs a comprehensive data protection mechanism to ensure user privacy and data security, thereby improving the efficiency and satisfaction of users in the process of information acquisition and exchange, and ensuring the stable operation and information security of the platform.

[0005] To solve the above technical problems, a network information technology consultation exchange platform application method is proposed, comprising,

[0006] The network information technology consultation exchange platform is connected with a multi-technology database, users select a login or registration button, users selecting the login button are defined as old users, and users selecting the registration button are defined as new users; the new user selects a topic of interest when registering, and is assigned a corresponding consultation assistant for initial simulation consultation after logging in; in the case of data protection, deep data mining is performed through a computer multi-data model, and the mined data is stored in the similar technology database of the current user; the matching degree of the data of the multi-technology database and the content of interest of the new user is calculated in combination with the result of data mining, corresponding technical data is pushed, and experts and star users are recommended, the new user selects technical data or an exchange object, and enters an exchange consultation mode to build a type I user demand model in real time; the old user logs in to obtain the professional nature of the user according to historical records, a type II user demand model is built in real time, the professional similarity and interest matching degree of the multi-technology database and the old user are calculated, corresponding technical data, experts, star users or technical problems are pushed according to the calculation result, and the content is selected to enter the exchange consultation mode; the exchange consultation records of all users are saved to a data protection library for data protection to prevent data leakage.

[0007] As a preferred scheme of the network information technology consultation exchange platform application method, the data mining comprises that the network information technology consultation exchange platform is connected with a multi-technology database, the multi-technology database crawls the latest published technical articles and white papers through a technical forum, a journal and a website; an expert group is set up to review new technologies with current technology trends and determine updated databases; the user is allowed to submit new technologies or new articles considered by the user on the platform, and the new technologies or new articles are updated to the databases after being reviewed by the expert group;

[0008] In the initial simulation consultation process, the system extracts keywords selected by the new user, problems and feedback, records the user interest vector U as [u1, u2, …, u n ], uses a multi-data model to perform data mining, and calculates the comprehensive similarity S1 between the user interest vector U and the technical feature vector P based on the technical feature vector P = [p1, p2, …, p m ].

[0009]

[0010] Wherein, U represents the interest vector selected by the user in the initial simulation consultation, n is the number of keywords, u i is the interest technology keyword expressed by the i-th user, P represents the technical feature vector currently stored in the multi-technology database, m is the number of technical feature vectors, and pj is the jth technical feature vector, S1 represents the similarity between the user interest vector U and the technical feature vector P, k is a constant adjustment term, b is a small positive number to prevent the denominator from being zero, i and j are variable indexes;

[0011] It is judged whether the similarity S1 is higher than a preset threshold θ, when S1> θ, it is considered that the current technology meets the user interest, and the mining result is stored in the similar technology database.

[0012] As a preferred scheme of the network information technology consultation exchange platform application method, the matching degree of the data of the multi-technology database and the content of interest of the new user includes extracting the technical data vector T related to the interest of the new user from the multi-technology database in which the data mining content has been joined, calculating the similarity S2 between the user interest vector U and each technical data vector T g .

[0013]

[0014] Among them, S2 represents the similarity between the new user interest vector U and the gth technical data vector T g , g is a variable index, after the new user browses and selects the multi-technology data, the weighted average of all similarities is calculated to form a comprehensive matching degree:

[0015]

[0016] Among them, M represents the overall matching degree between the new user and the technical data of the multi-technology database, w i represents the weight of the technical data selected by the new user, and the selection frequency is referred to;

[0017] After the new user obtains the matching degree value, the technical data, experts and star users with high matching degrees in the past are pushed according to the matching degree value.

[0018] As a preferred scheme of the network information technology consultation exchange platform application method, the I-type user demand model includes, in the consultation process, the system records the feedback information of the user according to the questions, comments and selection of technical data of the user, and converts the feedback information of the user into a demand signal D to form an I-type user demand model state:

[0019] R t = R t-1 + β · ((D t -R t-1 ) · log (1+ M avg ))

[0020] Among them, R t-1M represents the state of the Type I demand model at time t-1, β represents the learning rate, which controls the impact of new feedback on model updates; avg R represents the average matching degree. t D represents the state of the type I user demand model at time t. t This represents the demand signal that is transformed from user feedback information at time t;

[0021] Furthermore, the platform continuously monitors user engagement and satisfaction levels to adjust the demand model to meet user requirements.

[0022] As a preferred embodiment of the application method of the network information technology consultation and exchange platform described in this invention, the type II user demand model includes: when an existing user logs in, the system automatically extracts the user's historical consultation records, and obtains the existing user's professional characteristics through data analysis and transforms them into a feature vector P. nature User behavior data on the platform includes the topics of user inquiries, the frequency and depth of inquiries, the technical questions users respond to, and the experts they consult.

[0023] Constructing a Type II User Needs Model R old =f(P nature ,history,Y context ), where R old Let f represent the user's requirements, f represent the dynamic function that combines the input parameters to generate the model, and P represent the user's needs. nature The feature vector represents the user's professional nature; history represents the user's historical behavioral data, including past activity records and choices; Y context This represents the context weight, which contains context-related information.

[0024] As a preferred embodiment of the application method of the network information technology consultation and exchange platform described in this invention, the calculation of the professional similarity and interest matching degree between the data of the multi-technology database and the old users includes analyzing the interrelationships between multiple technical fields and calculating professional similarity in combination with the professional nature of the old users:

[0025]

[0026] Among them, S professional This represents professional similarity, specifically the degree of similarity between a user's professional background and technical skills. P is the technical feature vector, and c is a constant controlling the strength of the relationship, used to balance the score. relation This indicates the strength of the connection between user characteristics and technical characteristics;

[0027] Based on professional similarity from highest to lowest, the top 50% of technical data were selected. Interest matching was then calculated by integrating user interaction parameters and using a probabilistic model.

[0028]

[0029] wherein S interest represents the interest matching degree, i.e., the matching degree of the user with the professional similarity selection of the technical data, I user,l is the interaction frequency of the user on any technical data topic l, Q interest,l is the interest intensity weight on any technical data topic l, and L is the total amount of the selected top 50% technical data.

[0030] The weight distribution calculation fusion degree S combined = 0.6·S professional + 0.4·S interest According to the calculation result, the corresponding technical data, expert, star user or technical problem is pushed, and after selecting the content, the communication consultation mode is entered.

[0031] As a preferred scheme of the network information technology consultation communication platform application method, wherein: the data protection includes saving all user communication consultation records to the data protection library for data protection, and setting data protection rules for the platform and the user respectively.

[0032] The data protection rules for the platform are as follows:

[0033] Rule one: adopt a hierarchical storage strategy, different sensitivity data adopts different storage and backup strategies, and is divided into high, medium and low security level storage areas, wherein the low security level storage area is shared data and does not perform data protection.

[0034] Rule two: implement an artificial intelligence driven dynamic data protection library architecture, assess the risk indicators of access frequency and data sensitivity in real time through AI, and when the risk score of the risk indicators is higher than 70% of the specified range, the data is transferred to the high security level storage area.

[0035] Rule three: the platform constructs an environment monitoring unit, performs biological identification audit when a storage request is transmitted, and the biological identification failure rate is guaranteed to be lower than 0.1%, and the biological identification includes fingerprint, voice and pupil.

[0036] The data protection rules for the user are as follows:

[0037] When the user consultation content contains sensitive information, the system automatically marks the current content and stores the data in the isolation area, waits for review, and when the marking rate of the system relative to the total consultation record exceeds 30%, an automatic alarm is performed and risk review is performed.

[0038] When the user accesses the data protection library, the IP address and geographical location are analyzed in real time, the IP access requested by the user is classified into a medium-risk area, when the user starts normal communication consultation mode, the medium-risk area access is immediately converted into low-risk area processing, when the IP requested by the user is not registered in the past or not normally used after registration, the medium-risk area access is immediately converted into high-risk area processing, when the frequency of requests of the new connection IP is not identified more than 5 times, the dual authentication is enabled.

[0039] Another object of the present application is to provide a network information technology consultation communication platform application system, which solves the matching problem between user demand and professional information in the process of network information technology consultation communication, realizes efficient and safe information consultation communication through the construction of personalized user demand model and accurate data pushing mechanism, protects user data privacy, and enhances user experience.

[0040] As a preferred scheme of the network information technology consultation communication platform application system, the application comprises a user management module, a data analysis and recommendation module, and a data protection module.

[0041] The user management module selects the interested topic when a new user registers, and assigns the corresponding consultation assistant for initial simulation consultation after registration and login.

[0042] The data analysis and recommendation module extracts the user interest vector through data mining by multiple data models, calculates the similarity of the technical data vector in the multiple technical database, pushes the matched technical data, experts and star users according to the similarity and user historical behavior data, constructs the user demand model in real time, and adjusts the model according to the user feedback to meet the user demand.

[0043] The data protection module saves all user communication consultation records to the data protection library, implements different data protection rules, and the platform adopts hierarchical storage strategy, AI-driven dynamic data protection library architecture and environment monitoring unit to ensure data security.

[0044] The application has the beneficial effects that the network information technology consultation communication platform is constructed and connected with the multiple technical database, the initial classification of user information and the starting point of personalized service are realized, an efficient information acquisition and communication environment is provided for the user, different service paths are provided for new and old users through the differentiation of user identity, and the user experience and the personalized service level of the platform are improved.

[0045] During the registration process, the in-depth identification of user interests and the construction of similar technology databases are achieved, the platform can more accurately grasp the user's interest points, provide more accurate technical data and expert recommendations for users, and thus improve the quality and efficiency of user communication on the platform.

[0046] Combined with the data mining results, the matching degree is calculated and the corresponding content is pushed, realizing the rapid response to the interests of new users and the provision of personalized content, the platform can dynamically adjust the pushed content to ensure that the information received by the user is highly related to his interests, thus improving the user's satisfaction and the platform's stickiness.

[0047] For old users, the platform achieves a deep understanding of the professional nature and preferences of old users, and can provide more customized services based on the user's historical behavior data, so that old users can obtain more information and resources that meet their professional needs on the platform, thus enhancing the user's loyalty and the platform's attractiveness.

[0048] The platform not only guarantees the privacy and security of users, but also maintains the reputation of the platform and the trust of users in the platform. Through the implementation of hierarchical storage strategy and artificial intelligence driven dynamic data protection library architecture, the platform can effectively cope with data security challenges and ensure the proper handling of sensitive information. BRIEF DESCRIPTION OF DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0050] Figure 1 The overall flowchart of the network information technology consultation and exchange platform application method provided by an embodiment of the present application.

[0051] Figure 2 The system scheme module diagram of the network information technology consultation and exchange platform application system provided by an embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0053] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, it will be apparent to one skilled in the art that the present application can be practiced without the specific details and other implementations can be employed. Therefore, the scope of the present application encompass not only the specific implementations described below, but also other implementations or implementations similarly situated and the scope of the present application is determined by the appended claims.

[0054] Secondly, the "one embodiment" or "an embodiment" referred to herein means a specific feature, structure, or characteristic under discussion. Each of the various embodiments appearing at different places in the specification are not necessarily all directed to the same embodiment, nor are the various embodiments necessarily mutually exclusive, but can each be separate implementations or aspects of the present application.

[0055] The present application is described in detail below in conjunction with the drawings, which show the following items:

[0056] Meanwhile, in the description of the present application, it should be noted that the terms "upper and lower, inner and outer" and the like indicate the positional or directional relationship shown in the drawings, and are merely intended to facilitate the description of the present application and simplify the description, and are not intended to indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore should not be construed as limiting the present application. In addition, the terms "first, second or third" are only for descriptive purposes and should not be construed as indicating or implying relative importance.

[0057] Unless otherwise defined and limited in the present application, the terms "mounting, connecting, and connecting" should be understood broadly, for example: it can be fixedly connected, detachably connected or integrally connected; it can also be mechanically connected, electrically connected or directly connected; it can also be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0058] Embodiment 1, refer to Figure 1 As a first embodiment of the present application, the embodiment provides a network information technology consultation and exchange platform application method, comprising:

[0059] S1: Construct a network information technology consultation and exchange platform connected to a multi-technology database. Users select the login or registration button. Users who select the login button are defined as old users, and users who select the registration button are defined as new users. The platform aims to provide technical consultation and exchange services for new users, promote knowledge sharing and technological progress, and gather the latest information, research results, and technical literature from various technical fields through a multi-channel data acquisition system such as technical forums and journals to ensure the accuracy and timeliness of the information.

[0060] The new user selects a topic of interest when registering, and after logging in, an appropriate consultation assistant is assigned for initial simulation consultation. In the case of data protection, deep data mining is performed through computer multi-data models, and the mined data is stored in the current user's similar technology database. By guiding new users to select topics of interest, the platform effectively captures user preferences, laying the foundation for personalized consultation. The selection data during registration can provide initial data for subsequent recommendation algorithms, effectively improving matching accuracy. In the initial simulation consultation stage, not only can the user's needs be sorted out, but also valuable information can be mined under the framework of data protection, ensuring user privacy while enhancing user trust and improving platform stickiness.

[0061] Furthermore, the network information technology consultation and exchange platform connects to a multi-technology database, which collects the latest published technical articles and white papers through technical forums, journals, and website crawling. An expert group is established to review new technologies and current technology trends, determine updates to the database, and allow users to submit new technologies or articles they believe are valuable. After expert group review, the platform can continuously update and optimize the technology database to keep up with current technological developments, allowing user suggestions and new technologies to be integrated into the database in a timely manner, providing the latest and most comprehensive information resources for all users.

[0062] During the initial simulation consultation process, the system extracts keywords from the new user's selection, questions, and feedback, recording them as a user interest vector U = [u1, u2, …, u n ], and uses a multi-data model for data mining to accurately reflect the user's technical interests and provide strong data support for subsequent knowledge recommendations. Based on the technical feature vector P = [p1, p2, …, p m ], the comprehensive similarity S1 between the user interest vector U and the technical feature vector P is calculated using an improved data mining model.

[0063]

[0064] Wherein, U represents the interest vector selected by the user in the initial simulation consultation, n is the number of keywords, u i is the interest technology keyword of the i-th user, P represents the technology feature vector currently stored in the multi-technology database, m is the number of technology feature vectors, p j is the j-th technology feature vector, S1 represents the similarity between the user interest vector U and the technology feature vector P, k is a constant adjustment term, b is a small positive number to prevent the denominator from being zero, and i and j are variable indices.

[0065] It is judged whether the similarity S1 is higher than a preset threshold θ, and when S1> θ, it is considered that the current technology meets the user's interest, the mining result is stored in the similar technology database, the preference degree of the user for the specific technology is accurately judged through the similarity calculation, and thus the related technology information is stored in the similar technology database to form personalized technology recommendation.

[0066] S2: Combined with the result of data mining, the matching degree of the data of the multi-technology database and the content of interest of the new user is calculated, the corresponding technology data and experts and star users are pushed, and after the new user selects the technology data or the communication object, the communication consultation mode is entered, and the I-type user demand model is constructed in real time.

[0067] Further, the technology data vector T related to the user's interest is extracted from the multi-technology database which has joined the data mining content, the similarity S2 between the user interest vector U and each technology data vector T g is calculated:

[0068]

[0069] Wherein, S2 represents the similarity between the new user interest vector U and the g-th technology data vector T g , and g is a variable index. After the new user browses and selects the multi-technology data, the weighted average of all similarities is calculated to form a comprehensive matching degree:

[0070]

[0071] Wherein, M represents the overall matching degree between the new user and the technology data of the multi-technology database, w i represents the weight of the technology data selected by the new user, and is referenced by the selection frequency;

[0072] After the new user obtains the matching degree value, the technology data, experts and star users with high matching degree selected in the past are pushed according to the matching degree value; by calculating the matching degree between the user's interest and the technology data, the technology data and expert recommendation highly related to the user's demand can be pushed, so as to improve the user experience, for example, the new user can quickly find the required information and avoid information redundancy in the traditional search mode.

[0073] It should be noted that the star user contains a personal quality score and an interaction score for each user, and the personal quality score and the interaction score threshold are set to 80 (percentage) and 4 (tenth) respectively;

[0074] The personal quality score includes the quality of uploaded technology and the quality of answering technical questions, etc.

[0075] According to the proportion of the two scores, the total score is obtained, and the total score is sorted according to the size, and the top 10% of the users are rated as star users, if the user does not select experts for communication consultation, the star users can be recommended for communication consultation; The star user enables the new user to obtain high-quality resource and information exchange in the consultation process, increases the trust of the user, also promotes knowledge sharing and experience exchange, and improves the activity of the whole platform.

[0076] It should be noted that in the consultation process, the system records the feedback information of the user according to the user's question, comment and selection of technical data, and converts the user feedback information into a demand signal D to form a class I user demand model state:

[0077] R t = R t-1 + β · ((D t -R t-1 ) · log(1+M avg ))

[0078] Wherein, R t-1 represents the class I demand model state at time t-1, β represents the learning rate, and controls the influence of new feedback on model updating; M avg represents the average value of matching degree, R t represents the class I user demand model state at time t, D t represents the demand signal converted from the user feedback information at time t.

[0079] And the platform adjusts the demand model to meet the requirements of the user by continuously monitoring the subsequent participation and satisfaction of the user, and the real-time update of the demand model ensures the flexibility of the recommendation system, which helps the user to obtain technical information more in line with the current demand.

[0080] S3: After the old user logs in, the user professional property is obtained according to the historical record, the class II user demand model is constructed in real time, the professional similarity and interest matching degree of the data of the multi-technology database and the old user are calculated, and the corresponding technical data, experts, star users or technical problems are pushed according to the calculation result, and the content is selected to enter the communication consultation mode.

[0081] Furthermore, when a returning user logs in, the system automatically extracts the user's historical consultation records, and through data analysis, obtains the returning user's professional characteristics and transforms them into a feature vector P. nature User behavior data on the platform includes the topics of user inquiries, the frequency and depth of inquiries, the technical questions and experts the user responded to; this reduces the user's active input, improves the system's response efficiency, and reduces redundant information that may occur in traditional interactions.

[0082] Constructing a Type II User Needs Model R old =f(P nature ,history,Y context ), where R old Let f represent the user's requirements, f represent the dynamic function that combines the input parameters to generate the model, and P represent the user's needs. nature The feature vector represents the user's professional nature; history represents the user's historical behavioral data, including past activity records and choices; Y context This represents the context weight, which contains context-related information.

[0083] By combining historical user behavior data with contextual information, a dynamic model representing user needs is constructed to respond to changes in user needs, ensuring the timeliness and relevance of recommended content. This provides experts and technology providers with decision support based on real data, helping them focus on the true needs of users.

[0084] It should be noted that the analysis of the interrelationships between multiple technical fields, combined with the professional characteristics of existing users, calculates the professional similarity:

[0085]

[0086] Among them, S professional This represents professional similarity, specifically the degree of similarity between a user's professional background and technical skills. P is the technical feature vector, and c is a constant controlling the strength of the relationship, used to balance the score. relation It indicates the connection strength between user characteristics and technical characteristics; sorting technical data by professional relevance makes it easier for users to quickly obtain the most suitable technical information for their needs, improves the efficiency of information filtering, reduces the time users spend searching through massive amounts of data, and enables users to find solutions in the shortest possible time.

[0087] Based on professional similarity from highest to lowest, the top 50% of technical data were selected. Interest matching was then calculated by integrating user interaction parameters and using a probabilistic model.

[0088]

[0089] Among them, S interestInterest matching degree, i.e. the matching degree of the user with the professional similarity selection of technical data, I user,l Interaction frequency of the user on any technical data topic l, Q interest,l Interest intensity weight on any technical data topic l, L is the total amount of the selected top 50% technical data; accurate pushing improves the possibility of users obtaining information in a timely manner, promotes interaction between experts and users, forms a virtuous cycle, and thus improves the activity of the overall technical consulting platform.

[0090] Distribution weight calculation fusion degree S combined = 0.6·S professional + 0.4·S interest According to the calculation result, push the corresponding technical data, experts, star users or technical problems, select the content and enter the exchange consultation mode.

[0091] S4: Save all user exchange consultation records to the data protection library for data protection to prevent data leakage.

[0092] Further, save all user exchange consultation records to the data protection library for data protection, and set data protection rules for the platform and users respectively;

[0093] The data protection rules for the platform are as follows:

[0094] Rule one: adopt a hierarchical storage strategy, different sensitivity data adopts different storage and backup strategies, and is divided into high, medium and low security level storage areas, among which the low security level storage area is shared data and does not perform data protection; by dividing the data into high, medium and low security levels, the system can apply different protection measures according to the specific sensitivity of the data. This differentiated management not only improves the efficiency of data storage, but also ensures the maximum protection of sensitive data to prevent unnecessary leakage risks.

[0095] Rule two: implement an artificial intelligence driven dynamic data protection library architecture, assess the risk indicators of access frequency and data sensitivity in real time through AI, and when the risk score of the risk indicators is higher than 70% of the specified range, the data will be transferred to the high security level storage area; the platform can assess the data access frequency and its risk in real time, especially when the risk indicators exceed 70%, it can quickly transfer the data to the high security level storage area, which provides a timely response mechanism when potential leakage risks occur, and the dynamic processing capability significantly enhances the security protection of the data, effectively resisting unauthorized access and other external threats such as hacker attacks.

[0096] Rule three: the platform builds an environment monitoring unit, conducts biological identification audit when incoming storage requests, and ensures that the biological identification failure rate is lower than 0.1%, the biological identification includes fingerprint, voice, and pupil; biological identification audit is conducted when data storage requests, and it is ensured that only authenticated users can access sensitive data. Due to the high accuracy of biological identification technology, the risk of unauthorized access can be effectively reduced. In addition, the low failure rate (lower than 0.1%) of biological identification audit ensures the continuity and smoothness of user experience, which is suitable for application in multiple scenarios.

[0097] It should be noted that the data protection rules for users are as follows:

[0098] When the user's consultation content contains sensitive information, the system automatically marks the current content and stores the data in the isolated area, waits for review, and when the marking rate of the system relative to the total consultation record exceeds 30%, an automatic alarm is given and risk review is conducted;

[0099] When the user accesses the data protection library, the IP address and geographical location are analyzed in real time, the user's IP access is classified into the medium risk area, and when the user starts normal communication consultation mode, the medium risk area access is immediately converted to low risk area processing, when the user's IP is not registered in the past or not normally used after registration, the medium risk area access is immediately converted to high risk area processing, and when the frequency of unidentified requests of the new connection IP exceeds 5 times, double authentication is enabled.

[0100] When the user's consultation content involves sensitive information, the system automatically marks and isolates these contents, forming an active protection mechanism to protect personal privacy, and starting risk review when the marking rate exceeds 30%, effectively preventing potential compliance problems. In addition, real-time analysis of IP addresses and geographical locations, combined with double authentication, provides double protection for data access control.

[0101] Embodiment 2, the second embodiment of the present application, which is different from embodiment 1 is:

[0102] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the part of the technical solutions that essentially contribute to the prior art or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0103] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered a list of executable instructions for implementing logic functions, and can be specifically embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device, such as a computer-based system, a system including a processor, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions, or in conjunction with these instructions execution systems, apparatuses, or devices. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport programs for use by an instruction execution system, apparatus, or device, or in conjunction with these instruction execution systems, apparatuses, or devices.

[0104] More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection having one or more wires (electrical devices), a portable computer diskette (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium can even be paper or other suitable medium on which the program can be printed, as the program can be electronically obtained, for example, by optical scanning of the paper or other medium, followed by editing, interpreting, or otherwise processing, if necessary, in other suitable ways to be electronically obtained, and then stored in the computer memory.

[0105] It should be understood that various parts of the present application can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and as in another embodiment, it can be implemented using any or a combination of the following technologies, which are known in the art: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0106] Embodiment 3, with reference to Figure 2 As a third embodiment of the present application, the embodiment provides a network information technology consultation exchange platform application system, comprising a user management module, a data analysis and recommendation module, and a data protection module.

[0107] The user management module allows new users to select topics of interest when registering, and assigns corresponding consultation assistants for initial simulation consultation after login. After login, the system extracts historical consultation records of old users, analyzes the professional nature and builds a user demand model.

[0108] The data analysis and recommendation module extracts user interest vectors through data mining by multiple data models, calculates the similarity of technical data vectors in the multi-technology database, and according to the similarity and user historical behavior data, pushes matching technical data, experts and star users, real-time builds user demand model, and adjusts the model according to user feedback to meet user demand.

[0109] The data protection module saves all user exchange consultation records to the data protection library, implements different data protection rules, and the platform uses a hierarchical storage strategy, an AI-driven dynamic data protection library architecture and an environment monitoring unit to ensure data security; user data protection rules mark sensitive information, analyze IP addresses and geographic locations, and conduct risk review.

[0110] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the present application, and they should be covered in the scope of the claims of the present application.

Claims

1. A method for applying a network information technology consultation and exchange platform, characterized in that: The application relates to a network information technology consultation and exchange platform. The platform connects a multi-technology database, and users select a login or registration button. Users selecting the login button are defined as old users, and users selecting the registration button are defined as new users. The new users select topics of interest when registering, and are assigned corresponding consultation assistants for initial simulation consultation after registration. In the case of data protection, deep data mining is carried out through computer multi-data models, and the mined data is stored in the similar technology database of the current new user. The matching degree of the data in the multi-technology database and the content of interest of the new user is calculated in combination with the data mining results, corresponding technical data is pushed, and experts and star users are recommended. After the new user selects the technical data or the exchange object, the exchange consultation mode is entered, and a type I user demand model is constructed in real time. ； wherein, denotes the state of the class I demand model at time denotes the learning rate, controlling the influence of new feedback on model updates; denotes the average of the matching degree, denotes the state of the class I user demand model at time t, denotes the demand signal converted from user feedback information at time t;​ The old user's professional properties are obtained according to historical records after login, a type II user demand model is constructed in real time, the professional similarity and interest matching degree of the data in the multi-technology database and the old user are calculated, and corresponding technical data, experts, star users or technical problems are pushed according to the calculation results.

2. The network information technology consultation exchange platform application method of claim 1, wherein: After the content is selected, the exchange consultation mode is entered. In the initial simulation consultation process, the system extracts the keywords of the new user's choices, problems and feedback, and records them as the user interest vector , uses multiple data models for data mining, and calculates the comprehensive similarity between the user interest vector U and the technology feature vector P based on the technology feature vector , and improves the data mining model : ； wherein, U represents the user's selected interest vector in the initial consultation, n is the number of keywords, is the i-th user's expressed interest technology keyword, P represents the currently stored technology feature vector in the multi-technology database, m is the number of technology feature vectors, is the j-th technology feature vector, represents the similarity between the user's interest vector U and the technology feature vector P, k is a constant adjustment term, b is a small positive number to prevent the denominator from being zero, and i and j are variable indices; judging similarity whether it is higher than a preset threshold θ, when > θ, it is considered that the current technology matches the user interest, and the mining result is stored in the similar technology database.

3. The network information technology consultation exchange platform application method of claim 2, wherein: The matching degree of the data of the multi-technology database and the content of interest of the new user includes extracting the technology data vector T related to the interest of the new user from the multi-technology database in which the data mining content has been added, and calculating the similarity of the user interest vector U and each technology data vector T :​ ； wherein, represents the similarity between the new user interest vector U and the gth technical data vector g is the variable index, and the weighted average of all similarities is calculated to form the comprehensive matching degree after the new user browses and selects multiple technical data. ； wherein, represents the overall match between the new user and the technical data of the multi-technology database, represents the weight of the selection of technical data by the new user, referenced by the frequency of selection; The exchange consultation records of all users are saved in a data protection library for data protection to prevent data leakage.

4. The network information technology consultation exchange platform application method of claim 3, wherein: The type II user demand model comprises that when an old user logs in, the system automatically extracts historical consultation records of the user, and obtains professional properties of the old user through data analysis and converts the professional properties into a feature vector The behavior data of the user on the platform comprises a theme of consultation of the user, a frequency and an interaction depth of consultation, technical problems responded by the user, and experts Building a class-Ⅱ user demand model wherein, represents a user demand representation, represents a dynamic function of combining input parameters to generate a model, represents a feature vector corresponding to the professional property of the user; represents historical behavior data of the user, including past activity records and selections; represents a context weight, containing context-related information.

5. The network information technology consultation exchange platform application method of claim 4, wherein: The type I user demand model includes the following steps. ； wherein, represents the professional similarity, i.e. the similarity degree between the professional property of the user and the technology, P is the technology feature vector, represents a constant for balancing the score; represents the connection strength between the user feature and the technology feature; During the consultation process, the system records the feedback information of the user according to the user's questions, comments and selection of technical data, converts the user feedback information into demand signals D, and forms a type I user demand model state. ； wherein, represents the interest match, i.e. the degree of match of the user with the technical data similarity selection, is the frequency of interaction of the user on any technical data topic l, is the interest intensity weight on any technical data topic l, is the total amount of technical data selected in the top 50%. Distribute weight calculation fusion degree According to the calculation result, push corresponding technical data, experts, star users or technical problems, select content and enter communication consultation mode.

6. The network information technology consultation exchange platform application method of claim 5, wherein: The platform adjusts the demand model to meet the requirements of the user by continuously monitoring the participation and satisfaction of the user. The data mining includes the following steps. The network information technology consultation and exchange platform connects a multi-technology database. The multi-technology database crawls the latest published technical articles and white papers through technical forums, journals and websites. An expert group is established to review new technologies with current technology trends and decide to update the database. Users are allowed to submit new technologies or new articles on the platform, which are updated to the database after being reviewed by the expert group. After the new user obtains the matching degree value, the technical data, experts and star users with high matching degrees in the past are pushed according to the matching degree value. The calculation of the professional similarity and interest matching degree of the data in the multi-technology database and the old user includes the following steps. The professional similarity is calculated in combination with the professional properties of the old user. The technical data in the top 50% is selected by fusing the interaction parameters of the user, and the interest matching degree is calculated by using a probability model. The data protection includes the following steps. The exchange consultation records of all users are saved in a data protection library for data protection, and data protection rules are set for the platform and the user. The data protection rules for the platform are as follows. Rule one: a hierarchical storage strategy is adopted, different sensitivity data adopts different storage and backup strategies, and is divided into high, medium and low security level storage areas. The low security level storage area is a shared data, and no data protection is performed. Rule two: Implement an AI-driven dynamic data protection library architecture, assess access frequency and data sensitivity risk indicators in real time through AI, when the risk score of the risk indicator is higher than 70% of the specified range, the data is transferred to the high security level storage area; Rule three: The platform builds an environment monitoring unit, conducts biological identification audit when incoming storage requests, the biological identification failure rate is guaranteed to be less than 0.1%, biological identification includes fingerprint, voice, pupil; The data protection rules for users are as follows: When the user's consultation content contains sensitive information, the system automatically marks the current content and stores the data in the isolation area, waits for review, when the system's marking rate exceeds 30% of the total consultation records, it automatically alarms and conducts risk review; When the user accesses the data protection library, the IP address and geographic location are analyzed in real time, when the user requests IP access, it is classified into the medium risk area, when the user starts normal communication consultation mode, the medium risk area access is immediately transferred to the low risk area for processing, when the user's IP has not been registered or has not been normally used after registration, the medium risk area access is immediately transferred to the high risk area for processing, when the request frequency of the new connection IP is not identified more than 5 times, the double authentication is enabled.

7. A network information technology consultation exchange platform application system applied to the network information technology consultation exchange platform application method of any one of claims 1-6, characterized in that: Including user management module, data analysis and recommendation module, data protection module; The user management module, when a new user registers, selects the topic of interest, and after registering and logging in, assigns the corresponding consultation assistant for initial simulation consultation; After the old user logs in, the system extracts the historical consultation records, analyzes the professional properties and builds the user demand model; The data analysis and recommendation module, the system performs data mining through multiple data models, extracts user interest vectors, calculates the similarity between technical data vectors in the multi-technology database, and according to the similarity and user historical behavior data, pushes the matched technical data, experts and star users, real-time builds user demand model, and adjusts the model according to user feedback to meet user demand; The data protection module saves all user communication consultation records to the data protection library, implements different data protection rules, the platform adopts hierarchical storage strategy, AI-driven dynamic data protection library architecture and environment monitoring unit to ensure data security; User data protection rules mark sensitive information, analyze IP address and geographic location, and conduct risk review.

Images