Multi-modal intelligent search engine system based on artificial intelligence

Abstract

The invention discloses a multimodal intelligent search engine system based on artificial intelligence, which belongs to the technical field of retrieval and comprises a channel management module, a channel module and a retrieval module. The channel management module is used for managing each channel party and determining a data sharing range of each channel party; the channel module is used for carrying out data acquisition according to the data sharing range, obtaining channel data, carrying out security processing on the channel data, setting a corresponding use permission requirement for the channel data after security processing, and sharing the channel data; the retrieval module is used for performing retrieval by a user of a corresponding channel party, obtaining a retrieval keyword of the user, performing retrieval according to the retrieval keyword and the shared channel data, obtaining a retrieval result, and displaying the retrieval result to the user; the tedious process that a user screens useful content from a large amount of irrelevant information is avoided, and the efficiency and accuracy of problem solving are greatly improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of retrieval, and in particular to an intelligent search engine system based on artificial intelligence multi-modal. BACKGROUND

[0002] The construction field involves a large number of professional terms and daily language of workers. The traditional text search engine is difficult to match the colloquial query and professional terms due to the lack of industry semantic understanding ability, resulting in low relevance of the search results. For example, the worker inputs "how to deal with the wall peeling", the traditional engine may return decoration data instead of the solution of "improper base treatment" in the construction specification, especially the returned search results are not analyzed in the background of the current construction project, which is easy to have large differences, and some workers and employees cannot accurately identify, resulting in that in the current construction field, many workers and employees rarely use the search engine system for retrieval, and generally adopt oral inquiry, self-searching for data, etc. to solve the problem, which is low in efficiency.

[0003] In view of the above problems, the application provides an intelligent search engine system based on artificial intelligence multi-modal. SUMMARY

[0004] In order to solve the problems existing in the above scheme, the application provides an intelligent search engine system based on artificial intelligence multi-modal.

[0005] The object of the application can be achieved by the following technical scheme: The intelligent search engine system based on artificial intelligence multi-modal comprises a channel management module, a channel module and a retrieval module. The channel management module is used for managing each channel party and determining the data sharing range of each channel party.

[0006] Further, the data sharing range of each channel party comprises: Each channel party is identified, and the data source range possessed by each channel party is obtained; a retrieval question library is established, and the retrieval question library is used for storing various construction retrieval questions; According to the retrieval question library, the material data required by each construction retrieval question is identified; and the data sharing range corresponding to each channel party is determined according to the data source range of each channel party and the material data.

[0007] Further, the data source range of each channel party is adjusted, and the adjustment process comprises: The data source ranges of each channel party are compared to determine the corresponding common range, and the channel party tags corresponding to each common range are marked; The common range is divided into several unit ranges, each unit range is evaluated in priority to determine the priority of the corresponding channel party in the unit range, the unit range is removed from the data source range of the channel party with the non-highest priority, and the adjustment of each data source range is completed.

[0008] Further, the priority of each channel party in the corresponding unit range is determined, including: setting evaluation items and weight coefficients of each evaluation item; evaluating the unit range according to each evaluation item to obtain a single item score of the unit range in the corresponding evaluation item; calculating the priority value of the corresponding channel party in the unit range according to the priority formula, and the priority formula is: ; In the formula, YQ is the priority value of the corresponding channel party in the unit range, i represents the corresponding evaluation item, i=1, 2, …, n, n is the number of evaluation items, βi represents the weight coefficient of the corresponding evaluation item, and DFi represents the single item score of the corresponding evaluation item. The priority of each channel party in the unit range is determined according to the order of the priority value from large to small.

[0009] Further, the data sharing range corresponding to each channel party is determined according to the data source range of each channel party and the material data, including: judging whether the corresponding material data is located in the data source range of the channel party; when the material data is located in the data source range of the channel party, the material data is supplemented into the data sharing range of the channel party; when the material data is not located in the data source range of the channel party, no corresponding processing is performed; By analogy, the data sharing range of each channel party is determined.

[0010] Further, the data sharing range corresponding to each channel party is determined according to the data source range of each channel party and the material data, including: identifying the channel party including the data source range of the material data; when the channel party is one, the material data is supplemented into the data sharing range of the channel party; when the channel party is more than one, the priority of each channel party in the corresponding material data is determined, and the material data is supplemented into the data sharing range of the channel party with the highest priority; By analogy, the data sharing range of each channel party is determined.

[0011] The channel module is used for collecting data according to a data sharing range, obtaining channel data, performing security processing on the channel data, setting corresponding use permission requirements for the channel data after security processing, and sharing the channel data.

[0012] The search module is used for searching by a user of a corresponding channel party, obtaining a search keyword of the user, searching according to the search keyword and the shared channel data, obtaining a search result, and displaying the search result to the user.

[0013] Further, the searching according to the search keyword and the shared channel data comprises: A permission calibration model is established, and the permission calibration model is used for analyzing whether corresponding user information meets use permission requirements of corresponding channel data; According to the search keyword, channel data that needs to be used is determined, corresponding channel data is marked as search material data, permission use requirements corresponding to the search material data are identified, the search material data is filtered through the permission calibration model, and a search result is generated according to the remaining search material data.

[0014] Further, an expression of the permission calibration model is: ; In the formula, (s, BZ) is input data, s is user permission information, BZ is corresponding use permission requirements, s->BZ indicates that the user permission information meets the corresponding use permission requirements, output data is a permission calibration value QP(s, BZ), and the permission calibration value is 1 or 0.

[0015] Further, the filtering of the search material data through the permission calibration model comprises: Permission use requirements of corresponding search material data are identified, and user permission information of the user is obtained according to the permission use requirements; The user permission information and the permission use requirements of the corresponding search material data are integrated as input data, the input data is analyzed through the permission calibration model, a weight calibration value of the corresponding search material data is obtained, and search material data with a permission calibration value of 0 is removed.

[0016] Further, when the user does not meet the corresponding use permission requirements, the user can apply for separate permission from the corresponding channel party.

[0017] Compared with the prior art, the present application has the following beneficial effects: This invention, through the deep integration of artificial intelligence technologies such as natural language processing and knowledge graphs, can deeply understand the semantic information in the construction field and accurately identify the professional intent behind colloquial queries, thereby providing users with highly relevant search results. This not only avoids the tedious process of users sifting through a large amount of irrelevant information, but also greatly improves the efficiency and accuracy of problem-solving, enabling workers to quickly obtain solutions that meet construction specifications and actual needs; at the same time, all the search materials used are precise data provided by various relevant parties, improving search accuracy. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a block diagram illustrating the principle of the present invention. Detailed Implementation

[0020] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0021] like Figure 1 As shown, the intelligent search engine system based on artificial intelligence and multimodal computing includes a channel module, a search module, and a retrieval module. The channel management module is used to manage various channel partners, such as adding or removing channel partners for a construction project, granting corresponding permissions to the channel partners, such as creating user accounts for employees and workers within the channel partner to facilitate their login, and determining the data sharing scope for each channel partner.

[0022] Channel partners include construction companies, developers, contractors, supervisors, designers, and other relevant parties; channel partners have data within the scope of data sharing provided to the system, such as construction specifications, construction plans, regulatory standards, schedule requirements, and other relevant data from all parties.

[0023] In one embodiment, specific channel management methods and access control can be managed according to actual needs based on existing methods.

[0024] In one embodiment, determining the scope of data sharing among various channel partners includes: Identify each channel party, obtain the data source range that each channel party has, that is, which data the channel party has, such as the construction range managed by each construction personnel of the general construction contractor, the construction scheme of each construction project, the detailed construction briefing, the construction specification, etc.

[0025] Based on big data, historical demand, etc. to determine the various construction search problems that may exist in the context of the construction project, and summarize them into a search problem library; the search problem library is dynamically updated according to changes in the later period.

[0026] According to the search problem library, identify various construction search problems, identify the data needed for each construction search problem, and mark it as material data; according to the data source range of each channel party and the material data, determine the data sharing range corresponding to each channel party.

[0027] In one embodiment, the data source range of each channel party is adjusted to avoid a material data corresponding to multiple data source ranges of channel parties; the adjustment process includes: Compare the data source range of each channel party to determine the range intersection, mark it as a common range, and mark the corresponding channel party tag for each common range to indicate which data source range of which channel party is in the common range intersection; Segment the common range to form several unit ranges; that is, the common range is divided into different unit ranges according to whether the corresponding data is the same, such as the common range consisting of data A, B, C, and D, then divided into A, B, C, and D respectively corresponding unit range; each unit range is evaluated in priority to determine the priority of each channel party in the unit range, and the unit range is removed from the data source range of the channel party with the highest priority, and so on, to complete the adjustment of each data source range.

[0028] In one embodiment, the priority of each channel party in the unit range is determined, including: Set the corresponding evaluation items and the weight coefficients of each evaluation item, such as the accuracy, completeness, timeliness, and cost of the data, which have an impact on the priority evaluation items; According to each evaluation item, evaluate the unit range to obtain the single-item score of the unit range in the corresponding evaluation item; unify the score range (such as 0-100 points or 1-5 points) to avoid weight invalidation caused by different index dimension differences; According to the priority formula, calculate the priority value of the corresponding channel party in the corresponding unit range, and the priority formula is: ; In the formula, YQ is the priority value of the corresponding channel party in the unit range; i represents the corresponding evaluation item, i = 1, 2, …, n, n is the number of evaluation items; βi represents the weight coefficient of the corresponding evaluation item; and DFi represents the single item score of the corresponding evaluation item.

[0029] In one embodiment, the priority formula can also be other existing formulas.

[0030] In one embodiment, the unit range is evaluated according to each evaluation item, and the evaluation is performed based on an existing evaluation method, for example: Accuracy: Accuracy score = 100 - (error rate x 100); Completeness: Formula: Completeness score = (actual field number / demand field number) x 100; Timeliness: Delay time method: Formula: Timeliness score = 100 - [(actual delay time / maximum tolerance time) x 100]; Update frequency method: Pre-set reference frequency (such as real-time, daily, weekly), and score by gradient: Real-time: 100 points; Daily: 80 points; Weekly: 60 points; Monthly: 40 points.

[0031] Cost: Formula: Cost score = (minimum cost / actual cost) x 100.

[0032] In one embodiment, the priority of each channel party in the unit range can also be evaluated based on other existing methods, for example, each evaluation item is determined according to the above embodiment, and then the priority is evaluated according to the existing method, as long as it is determined whether it is the highest priority.

[0033] In one embodiment, the data sharing range corresponding to each channel party is determined according to the data source range of each channel party and the material data, which can be determined based on an existing method, for example, it is determined whether the material data is located in the data source range of the channel party, if yes, it is a component of the data sharing range, and so on, to determine the data sharing range of each channel party.

[0034] In one embodiment, the data sharing range corresponding to each channel party is determined according to the data source range of each channel party and the material data, including: The data source range including the material data is identified, and the situation that one material data corresponds to multiple data source ranges can occur. The channel party that needs to share the material data is evaluated according to the priority evaluation mode (the mode for determining the priority of each channel party in the corresponding unit range in the above embodiment), and the multi-source sharing of the same data is avoided. Subsequently, the data sharing range is determined according to the above embodiment.

[0035] In one embodiment, a retrieval question library can not be established, and each construction retrieval question is directly classified according to retrieval requirements to obtain various retrieval requirements, determine the data required to solve the retrieval requirements, determine the corresponding channel party according to the data source range of the corresponding channel party, and then obtain the data range that needs to be shared by the channel party and mark it as a data sharing range.

[0036] The channel module is used to collect data according to the data sharing range, obtain channel data, i.e., data in the collected data sharing range, perform security processing on the channel data, set corresponding use permission requirements for the channel party for the security-processed channel data, such as indicating that the channel data is only applied by the user corresponding to the channel party, and share the current channel data; and the current channel data is generally shared to a unified database, such as a cloud database.

[0037] The channel module can also be managed by the channel party according to the corresponding basic functions, such as opening the user permission of the employee, data uploading, information management, etc.

[0038] In one embodiment, the security processing of the channel data and the sharing of the current channel data need to be determined according to the specific measures adopted, such as the combination of end-to-end encryption and homomorphic analysis, secure indexing and blind retrieval technology, access control and identity verification, federated learning and secure aggregation, blockchain and smart contract, data desensitization and anonymization, etc.

[0039] For example, the process of combining end-to-end encryption and homomorphic analysis: The channel party uses an AES symmetric encryption algorithm to encrypt the data.

[0040] The encrypted data is uploaded to the cloud through HTTPS.

[0041] The cloud uses a KMS-managed key for second-layer encryption storage.

[0042] Subsequently, homomorphic encryption technology is used to combine encrypted data for direct retrieval analysis to obtain the corresponding retrieval result; the retrieval result is returned to the user in an encrypted form, and is displayed to the user after decryption.

[0043] The search module is used for searching by a user of a corresponding channel party, obtaining a search keyword of the user, searching according to the search keyword and shared channel data, obtaining a search result, and displaying the search result to the user.

[0044] In one embodiment, the search result displayed to the user refers to data after decryption, which is decrypted according to the previous security processing measures.

[0045] In one embodiment, searching according to the search keyword and the shared channel data includes searching based on the search keyword and the channel data shared by each channel party according to the existing search technology, and searching based on the channel data with a use permission.

[0046] In one embodiment, searching according to the search keyword and the shared channel data includes: establishing a permission calibration model, the permission calibration model being used for analyzing whether corresponding user information meets a use permission requirement of corresponding channel data; According to the search keyword, the channel data needed to be used is determined. For example, if a user wants to search for the method of plastering construction of No. 2 building, the plastering construction disclosure of the corresponding No. 2 building is needed. The required channel data is determined based on the existing search technology, the corresponding channel data is marked as search material data, the permission use requirement corresponding to the search material data is identified, the search material data is filtered through the permission calibration model, the search material data that does not meet the permission requirement is removed, the search result is generated according to the remaining search material data according to the existing search technology, and if there is no remaining search material data or the data is incomplete, it can be prompted that the permission is insufficient, and the user can apply for a separate permission from the corresponding channel party in the future.

[0047] In one embodiment, the permission calibration model can be established based on existing machine learning, deep learning algorithm or other intelligent algorithm.

[0048] In one embodiment, the expression of the permission calibration model is: ; In the formula, (s, BZ) is input data, s is user permission information, BZ is a corresponding use permission requirement, s→BZ indicates that the user permission information meets the corresponding use permission requirement, a corresponding training set is set by using corresponding historical data for training; the output data is a permission calibration value QP(s, BZ), and the permission calibration value is 1 or 0.

[0049] The search material data is filtered through the permission calibration model, including: The use permission requirement of the corresponding search material data is identified, the user permission information of the user is obtained according to the use permission requirement, that is, the data of the user is collected according to the data required by the use permission requirement, and subsequent comparison and judgment are performed. The user permission information and the use permission requirement of the corresponding search material data are integrated into input data, the input data is analyzed by a permission calibration model, and a weight calibration value of the corresponding search material data is obtained; and search material data with a permission calibration value of 0 is removed.

[0050] In one embodiment, according to the search keyword and the shared channel data, search is performed according to no permission requirement, initial search results are obtained, the use permission requirement of the channel data corresponding to the initial search results is identified, the initial search results are adjusted according to the use permission requirement, and search results are obtained.

[0051] The above formulas are calculated by removing the dimension and taking the numerical value, the formula is obtained by software simulation of a large amount of data to obtain a formula closest to the actual situation, and the preset parameters and the preset threshold in the formula are set by a person skilled in the art according to the actual situation or obtained by a large amount of data simulation.

[0052] The above embodiments are only used to illustrate the technical method of the present application but not limit the present application. Although the present application is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical method of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical method of the present application.

Claims

1. An intelligent search engine system based on artificial intelligence multi-modal, characterized in that, The channel management module, the channel module and the retrieval module are included. The channel management module is used for managing each channel party, identifying each channel party, and obtaining the data source range of each channel party; a retrieval question bank is established, which is used for storing various construction retrieval questions; According to the retrieval question bank, the required material data corresponding to each construction retrieval question is identified; and according to the data source range of each channel party and the material data, the data sharing range corresponding to each channel party is determined; The data source range of each channel party is adjusted, and the adjustment process includes: Comparing the data source range of each channel party to determine the corresponding common range, and marking the corresponding channel party label for each common range; The common range is segmented to form a plurality of unit ranges; the priority of each channel party in the unit range is determined by preferentially evaluating each unit range; the unit range is removed from the data source range of the channel party with the highest priority; and the adjustment of each data source range is completed; The channel module is used for collecting data according to the data sharing range, obtaining channel data, safely processing the channel data, setting the corresponding use permission requirements for the safely processed channel data, and sharing the channel data; The retrieval module is used for the user of the corresponding channel party to perform retrieval, obtain the retrieval keyword of the user, perform retrieval according to the retrieval keyword and the shared channel data, obtain the retrieval result, and display the retrieval result to the user. 2.The artificial intelligence based multi-modal intelligent search engine system according to claim 1, wherein, The priority of each channel party in the corresponding unit range is determined, including: Setting evaluation items and weight coefficients of each evaluation item; According to each evaluation item, the unit range is evaluated to obtain the single-item score of the unit range in the corresponding evaluation item; According to the priority formula, the priority value of the corresponding channel party in the unit range is calculated, and the priority formula is: ； In the formula, YQ is the priority value of the corresponding channel party in the unit range; i represents the corresponding evaluation item, i=1, 2, …, n, and n is the number of evaluation items; βi represents the weight coefficient of the corresponding evaluation item; and DFi represents the single-item score of the corresponding evaluation item; According to the order of the priority value from large to small, the priority of each channel party in the unit range is determined. 3.The artificial intelligence based multi-modal intelligent search engine system according to claim 1, wherein, According to the data source range of each channel party and the material data, the data sharing range corresponding to each channel party is determined, including: Judging whether the corresponding material data is located in the data source range of the channel party; When the material data is located in the data source range of the channel party, the material data is supplemented into the data sharing range of the channel party; When the material data is not located in the data source range of the channel party, no corresponding processing is performed; In this way, the data sharing range of each channel party is determined.

4. The artificial intelligence based multi-modal intelligent search engine system as claimed in claim 1, wherein, According to the data source range of each channel party and the material data, the data sharing range corresponding to each channel party is determined, including: Identifying the channel party including the data source range of the material data; When the channel party is one, the material data is supplemented into the data sharing range of the channel party; When the channel parties are more than one, priorities of the respective channel parties on the corresponding material data are determined, and the material data is supplemented to the data sharing range of the channel party with the highest priority; By analogy, the data sharing range of each channel party is determined. 5.The artificial intelligence based multi-modal intelligent search engine system according to claim 1, wherein, According to the search keyword and the shared channel data, searching is performed, including: A permission calibration model is established, which is used to analyze whether the corresponding user information meets the use permission requirements of the corresponding channel data; According to the search keyword, the channel data to be used is determined, and the corresponding channel data is marked as search material data; the permission use requirements corresponding to the search material data are identified, the search material data is screened through the permission calibration model, and the search results are generated according to the remaining search material data.

6. The artificial intelligence based multi-modal intelligent search engine system as claimed in claim 5, wherein, The expression of the permission calibration model is: ； In the formula: (s, BZ) is input data, s is user permission information, BZ is the corresponding use permission requirement, s→BZ indicates that the user permission information meets the corresponding use permission requirement, and the output data is the permission calibration value QP(s, BZ). The permission calibration value is 1 or 0.

7. The artificial intelligence based multi-modal intelligent search engine system as claimed in claim 6, wherein, The search material data is screened through the permission calibration model, including: The use permission requirements of the corresponding search material data are identified, and the user permission information of the user is obtained according to the use permission requirements; The user permission information and the use permission requirements of the corresponding search material data are integrated as input data, the input data is analyzed through the permission calibration model, and the weight calibration value of the corresponding search material data is obtained; the search material data with the permission calibration value of 0 is removed. 8.The artificial intelligence based multi-modal intelligent search engine system according to claim 5, wherein, When the user does not meet the corresponding use permission requirements, the user can apply for separate permission to the corresponding channel party.

Images