Detection service matching recommendation method and system, electronic equipment and storage medium

Abstract

The invention discloses a detection service matching recommendation method and system, electronic equipment and a storage medium. The method comprises the following steps: S1, collecting multi-modal data, wherein the multi-modal data comprises a detection task information set, a full-process data resource pool and an operation comprehensive data set; s2, based on the detection whole-process data resource pool, constructing a detection service-oriented intelligent knowledge graph; s3, based on the multi-modal data, constructing a user detection task demand vector and a detection mechanism capability vector; s4, constructing a service efficiency evaluation model based on the operation comprehensive data set; and S5, based on the detection task demand vector, the detection mechanism capability vector and the intelligent knowledge graph, establishing a matching model through similarity calculation, and generating a detection service recommendation result according to the user demand and the service efficiency evaluation model. According to the invention, effective integration and management of detection service related data are realized, and the efficiency and quality of detection service management are improved.

Description

Technical Field

[0001] This invention relates to the fields of artificial intelligence and data processing technology, specifically to a knowledge graph-based detection service matching and recommendation method, system, electronic device, and storage medium. Background Technology

[0002] In the field of testing services, with the continuous expansion of business scale and the increasing diversification of service types, how to efficiently manage and optimize testing service resources and provide users with high-quality and efficient testing services has become an urgent problem to be solved.

[0003] Currently, testing services are mainly completed through offline communication or simple online platforms, which has many drawbacks, such as: (1) Traditional offline transaction processes are cumbersome and inefficient. Customers need to spend a lot of time and energy communicating with testing institutions repeatedly about testing parameters, testing methods and evaluation standards, which not only increases the time cost of customers, but also reduces the transaction efficiency of testing services; (2) Existing online testing service platforms have limited functions and can only provide simple display and ordering functions for testing services. They cannot intelligently match and recommend services according to customer needs, making it difficult to meet the diverse and personalized service needs of customers; (3) For customers who lack professional background in testing technology, when choosing testing services, they cannot accurately describe their testing needs due to a lack of professional knowledge, resulting in a mismatch between the selected testing services and actual needs, which seriously affects the validity and accuracy of the test results; (4) Traditional platforms cannot effectively integrate and deeply associate knowledge such as sample information, testing parameters, testing methods and evaluation standards, and cannot provide customers with comprehensive and accurate guidance on testing services, which further reduces the quality of testing services and customer satisfaction. Furthermore, existing service management systems generally lack in-depth analysis and integration of service data, making it difficult to comprehensively and accurately reflect the actual effectiveness of testing services and to dynamically adjust according to the real-time status of services and user needs. Therefore, a new technical solution is urgently needed to address these technical problems. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a knowledge graph-based detection service matching and recommendation method, system, electronic device, and storage medium. The method first constructs a detection service knowledge graph to effectively integrate and manage relevant data; secondly, it utilizes a multi-dimensional real-time performance scoring mechanism to accurately evaluate the actual performance of detection services; and finally, it collaboratively employs an intelligent ranking optimization algorithm to dynamically adjust service ranking based on user needs and service performance, thereby improving the efficiency and quality of detection service management and enhancing user experience.

[0005] To achieve the aforementioned objectives, the present invention employs the following solution:

[0006] One aspect of the present invention provides a knowledge graph-based detection service matching and recommendation method, comprising the following steps:

[0007] S1. Collect multimodal data, including detection task information set, full-process data resource pool, and operation comprehensive dataset;

[0008] S2. Based on the data resource pool of the entire detection process, construct an intelligent knowledge graph for detection services;

[0009] S3. Based on the multimodal data, construct the user detection task requirement vector and the detection agency capability vector;

[0010] S4. Based on the aforementioned comprehensive operational dataset, construct a service performance evaluation model;

[0011] S5. Based on the detection task requirement vector, the detection agency capability vector, and the intelligent knowledge graph, a matching model is established through similarity calculation. Based on user needs and the service performance evaluation model, a detection service recommendation result is generated.

[0012] A second aspect of the present invention provides a knowledge graph-based detection service matching recommendation system, comprising:

[0013] The data acquisition module is used to collect multimodal data, which includes a detection task information set, a full-process data resource pool, and an operational comprehensive dataset.

[0014] The knowledge graph construction module is used to construct an intelligent knowledge graph for detection services based on the detection full-process data resource pool.

[0015] The vector construction module is used to construct user detection task requirement vectors and detection agency capability vectors based on the multimodal data.

[0016] The service performance evaluation model construction module is used to construct a service performance evaluation model based on the comprehensive operational dataset.

[0017] The testing service recommendation result production module is used to establish a matching model based on the testing task demand vector, the testing institution capability vector, and the intelligent knowledge graph through similarity calculation, and generate testing service recommendation results according to user needs and the service performance evaluation model.

[0018] A third aspect of this application provides an electronic device comprising:

[0019] One or more processors;

[0020] Memory, used to store one or more programs.

[0021] When the one or more programs are executed by the one or more processors, the one or more processors implement the knowledge graph-based detection service matching recommendation method as described above.

[0022] A fourth aspect of this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed, are used to implement the knowledge graph-based detection service matching recommendation method described above.

[0023] Compared with the prior art, the technical solution of this application has at least the following advantages:

[0024] 1. By constructing a knowledge graph of testing services, this invention can effectively integrate and manage complex data in the field of testing services, clearly show the relationships between entities, and provide comprehensive and accurate knowledge support for testing service management.

[0025] 2. This invention adopts a multi-dimensional real-time performance scoring mechanism to evaluate the testing service from multiple dimensions, which can accurately reflect the actual performance of the testing service and provide a scientific basis for service optimization and resource allocation.

[0026] 3. This invention utilizes an intelligent sorting optimization algorithm to dynamically adjust service sorting based on user needs and service performance, thereby achieving personalized recommendations and intelligent management of detection services, improving the efficiency and quality of service management, and enhancing the user experience.

[0027] 4. The system structure of this invention is reasonable, and the division of labor among the modules is clear. It can realize the full-process management of detection services from knowledge graph construction and performance scoring to intelligent ranking. It has good practicality and scalability and can be widely applied to various detection service scenarios. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of the present invention, 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 recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 This is a knowledge graph-based detection service matching and recommendation method provided in a typical embodiment of the present invention;

[0030] Figure 2 This is a structural block diagram of an electronic device provided in this application, which is a typical embodiment of the present invention. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of the present invention clearer, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Examples of these preferred embodiments are illustrated in the drawings. The embodiments of the present invention shown in and described with reference to the drawings are merely exemplary, and the present invention is not limited to these embodiments.

[0032] One aspect of the present invention provides a knowledge graph-based detection service matching and recommendation method, comprising the following steps:

[0033] S1. Collect multimodal data, including detection task information set, full-process data resource pool, and operation comprehensive dataset;

[0034] S2. Based on the data resource pool of the entire detection process, construct an intelligent knowledge graph for detection services;

[0035] S3. Based on the multimodal data, construct the user detection task requirement vector and the detection agency capability vector;

[0036] S4. Based on the aforementioned comprehensive operational dataset, construct a service performance evaluation model;

[0037] S5. Based on the detection task requirement vector, the detection agency capability vector, and the intelligent knowledge graph, a matching model is established through similarity calculation. Based on user needs and the service performance evaluation model, a detection service recommendation result is generated.

[0038] In one embodiment, step S2 specifically includes:

[0039] S21. Based on the testing task information set, obtain the user's engineering information, sample information, and fee voucher information; based on the full-process data resource pool, obtain the testing institution's sample information, testing records, testing reports, personnel information, and qualification certification testing capability range table; based on the operational comprehensive dataset, obtain the testing institution's historical order information, testing efficiency, instrument and equipment utilization rate, personnel qualification coverage rate, customer satisfaction rate, and testing institution rating.

[0040] S22. Use machine learning algorithms to extract feature engineering from the full-process data resource pool;

[0041] S23. Based on the aforementioned feature engineering, establish a feature vector set. Construct an intelligent knowledge graph for testing services.

[0042] In one embodiment, step S3 specifically includes:

[0043] S31. Based on user roles in multimodal data, construct a detection task requirement vector using sample information.

[0044] S32. Perform dimensionality reduction processing on the detection task requirement vector to generate a user detection task vector. The user testing task vector shall include at least the sample name, specifications, model, grade, testing parameters, test method, and evaluation criteria;

[0045] S33. Based on the role of testing institutions in multimodal data, construct the capability vector of each testing institution through sample name, specifications, grade, testing parameters, test methods, and evaluation criteria.

[0046] In one embodiment, step S4 includes:

[0047] S41. Perform data annotation, normalization, and feature analysis on the operational integrated dataset in the multimodal data;

[0048] S42. Based on the comprehensive operational dataset in multimodal data, a service performance evaluation model is constructed using a dynamic weighting algorithm by combining multi-dimensional indicators of testing services performed by testing institutions with user needs.

[0049] In one embodiment, step S5 includes:

[0050] Obtain user detection task vectors and detection agency capability vectors, establish a cosine similarity matching model, and recommend detection agencies based on service effectiveness evaluation scores from high to low.

[0051] In one embodiment, obtaining the user detection task vector and the detection agency capability vector, establishing a cosine similarity matching model, and recommending detection agencies based on service performance evaluation scores from high to low includes:

[0052] User detection task vector With knowledge graph Analysis was conducted, and the results were obtained. That is, there exist detection agencies that can establish matching models;

[0053] Iterate through all testing institutions and determine the capability vector of each institution. The cosine similarity between the user detection task vector and the detection agency capability vector is calculated using the following formula:

[0054] when Furthermore, when both have the same dimension, the cosine similarity...

[0055] when And when the two are in different dimensions, for Dimensionality reduction processing to generate and Subvectors of the same dimension Cosine similarity

[0056] When the cosine similarity result is 1, the demand vector and the capability vector are matched.

[0057] In one embodiment, the method further includes:

[0058] When a user has multiple testing institutions matching their data, the Z-score is used to standardize the comprehensive operational dataset of each institution for that testing project. A service performance evaluation score S is then calculated based on multi-dimensional indicators, specifically:

[0059]

[0060] Where, x ik μ represents the k-th influencing factor for the i-th testing institution; k σ represents the mean of the k-th influencing factor; k Z represents the standard deviation of the k-th influencing factor; k This represents the Z-score of the k-th influencing factor; w ik This represents the weight of the k-th influencing factor, and S represents the service effectiveness assessment score.

[0061] Another aspect of the present invention provides a knowledge graph-based detection service matching recommendation system, comprising:

[0062] The data acquisition module is used to collect multimodal data, which includes a detection task information set, a full-process data resource pool, and an operational comprehensive dataset.

[0063] The knowledge graph construction module is used to construct an intelligent knowledge graph for detection services based on the detection full-process data resource pool.

[0064] The vector construction module is used to construct user detection task requirement vectors and detection agency capability vectors based on the multimodal data.

[0065] The service performance evaluation model construction module is used to construct a service performance evaluation model based on the comprehensive operational dataset.

[0066] The testing service recommendation result production module is used to establish a matching model based on the testing task demand vector, the testing institution capability vector, and the intelligent knowledge graph through similarity calculation, and generate testing service recommendation results according to user needs and the service performance evaluation model.

[0067] To achieve intelligent and convenient interaction in testing services, this invention provides the following technical solution: an intelligent ranking optimization algorithm and system for knowledge graph construction and multi-dimensional real-time performance scoring of testing services, comprising the following steps:

[0068] S1. Collect multimodal data using machine learning algorithms;

[0069] S2. Based on the detection process data resource pool in multimodal data, construct an intelligent knowledge graph for detection services;

[0070] S3. Based on the role types in multimodal data, construct demand vectors and capability vectors;

[0071] S4. Based on the comprehensive dataset of the testing institutions' operations, construct a service performance evaluation model;

[0072] S5. Based on the user's detection task demand vector and the detection agency's capability vector, a matching model is established using the cosine similarity algorithm. According to the user's needs and the service efficiency evaluation model, an intelligent ranking optimization algorithm is formulated to realize personalized recommendation and intelligent management of detection services, thereby improving the efficiency and quality of service management and enhancing the user experience.

[0073] Preferably, the multimodal data includes at least a detection task information set, a full-process data resource pool, and an operational comprehensive dataset.

[0074] Preferably, S2 specifically includes the following steps:

[0075] S21. Based on the testing task information set in the multimodal data, obtain the user's engineering information, sample information, and fee voucher information; based on the full-process data resource pool in the multimodal data, obtain the testing institution's sample information, testing records, testing reports, personnel information, and qualification certification testing capability range table; based on the comprehensive operational dataset in the multimodal data, obtain the testing institution's completed orders, incomplete orders, completed orders in the past year, testing efficiency in the past year, instrument and equipment utilization rate, personnel qualification coverage rate, customer satisfaction rate, and testing institution rating.

[0076] S22. Use machine learning algorithms to extract feature engineering from the full-process data resource pool;

[0077] S23. The feature engineering in the full-process data resource pool shall include at least the sample name, specifications, grade, test parameters, test methods, evaluation criteria, sampling quantity and sampling guidelines of all testing institutions.

[0078] S24. Based on feature engineering, establish a feature vector set. Construct an intelligent knowledge graph for testing services.

[0079] Specifically, the information elements in the intelligent knowledge graph form a structured corresponding mapping relationship through a semantic association mechanism. That is, the information elements are precisely associated and coupled based on their inherent logic, together constituting the core information nodes and association links in the knowledge graph related to the field of sample testing. The information elements include at least: sample name, specifications, grade (if present), testing parameters, test method, evaluation criteria, sampling quantity, and sampling guidelines.

[0080] In a specific embodiment, when the target sample is selected as prestressed concrete steel strand, its specifications are automatically matched to a 15.2mm diameter and a 1×7 structural form through a semantic association mechanism of the knowledge graph. The corresponding test parameters are dynamically selected from a preset parameter set, covering one or more of the following: surface quality, diameter deviation, straightness, nominal mass deviation per meter, maximum force, total elongation at maximum force, 0.2% yield strength, elastic modulus, maximum value of maximum force, and stress relaxation. For this sample, the test method and evaluation criteria are automatically locked to the national standards GB / T21839-2019 and GB / T 5224-2023 based on the semantic association logic of the sample name. The sampling quantity and sampling guidelines are dynamically adapted and adjusted according to the actual selected test parameter type and quantity through preset rules.

[0081] Preferably, S3 specifically includes the following steps:

[0082] S31. Based on user roles in multimodal data, construct a detection task requirement vector using sample information.

[0083] S32. Perform dimensionality reduction on the detection task requirement vector. The processed detection task vector is... It should include at least the sample name, specifications, grade, testing parameters, test method, and evaluation criteria;

[0084] S33. Based on the role of testing institutions in multimodal data, construct the capability vector of each testing institution through sample name, specifications, grade, testing parameters, test methods, and evaluation criteria.

[0085] Preferably, S4 specifically includes the following steps:

[0086] S41. Utilize various data standardization, normalization, and feature processing methods to process and analyze the comprehensive operational dataset in multimodal data; various data standardization, normalization, and feature processing methods include, but are not limited to, Z-score standardization, Min-Max standardization, decimal scaling standardization, and quantile-based data scaling methods;

[0087] S42. Based on the comprehensive operational dataset in multimodal data, a service performance evaluation model is constructed using multi-dimensional indicators such as the number of completed orders, the number of incomplete orders, the number of completed orders in the past year, the testing efficiency in the past year, the utilization rate of instruments and equipment, the coverage rate of personnel qualifications, the customer satisfaction rate, and the testing agency rating. According to the characteristics of user needs, a dynamic weighting algorithm is used to construct the model. The dynamic weighting algorithm includes, but is not limited to, random search, grid search, genetic algorithm, and simulated annealing algorithm.

[0088] Preferably, S5 specifically includes the following steps:

[0089] S51. Obtain the user's detection task vector and the detection agency's capability vector, establish a cosine similarity matching model, and intelligently recommend detection agencies based on the principle of service effectiveness evaluation scores from high to low. This enables personalized recommendation and intelligent management of detection services, improves the efficiency and quality of service management, and enhances the user experience.

[0090] Preferably, after the user's detection task vector and the detection agency's capability vector are matched by cosine similarity, it indicates that the detection agency has the capability to complete the detection task; the higher the service performance evaluation score, the higher the reliability of the detection agency in completing the detection task.

[0091] Preferably, based on the accuracy and time requirements of the testing task vector, a service performance evaluation score is calculated using a dynamic weighting algorithm, and testing institutions are recommended from highest to lowest score.

[0092] Preferably, in order to ensure real-time matching between testing tasks and testing institutions, a two-way dynamic intelligent linkage mechanism is adopted to update the intelligent ranking and recommendation of testing institutions in real time. Specific Implementation Example 1

[0094] The user commissioned a set of steel strand samples, forming a demand vector and a testing task vector, as shown in Tables 1 and 2. The internal knowledge graph of the system is shown in Table 3, and the mechanism capability vector is shown in Table 4.

[0095] Table 1 User Demand Vector

[0096]

[0097]

[0098] Table 2 User Detection Task Vectors

[0099]

[0100] Table 3 Knowledge Graph

[0101]

[0102] Table 4 Capability Vector of Testing Institutions

[0103]

[0104] Table 1 shows the request vectors submitted by users in the system. The detection task vectors are obtained by dimensionality reduction. (Table 2) Integrating detection task vectors with knowledge graphs Analysis was conducted, and the results were obtained. That is, there exists a detection agency that builds a matching model. By traversing all detection agencies, we can find the capability vector of one of the detection agencies. As shown in Table 4; calculate the cosine similarity sim(J) according to the formula. i C i A principal-agent relationship can be established.

[0105] when Furthermore, when the dimensions are the same, cosine similarity is calculated. when When the two are in different dimensions, Dimensional reduction and Subvectors of the same dimension Calculate cosine similarity. When the cosine similarity result is 1, the demand vector and the capability vector are matched, and a delegation relationship is established. Specific Implementation Example 2

[0107] When a user has multiple testing institutions that can complete the matching, the Z-score is used to standardize the comprehensive operational dataset of each testing institution for the testing project (see Table 5), and the service effectiveness evaluation score S is calculated by multi-dimensional indicators.

[0108] Table 5. Comprehensive Data Set of Testing Institutions' Operations

[0109]

[0110]

[0111] Note: x ik - The k-th influencing factor of the i-th testing institution; μ k - The mean of the kth influencing factor; σ k - The standard deviation of the k-th influencing factor; Z k - The Z-score of the kth influencing factor; w ik -The weight of the k-th influencing factor, S - Service performance evaluation score; the higher the score, the higher the recommendation ranking.

[0112] Table 6. Comprehensive operational dataset of testing institutions (Z-score normalized)

[0113]

[0114] The service effectiveness evaluation scores for Institution 1, Institution 2, and Institution 3 were calculated to be -0.307, 0.132, and 0.183, respectively. Institution 3 was selected to establish a commission relationship.

[0115] Figure 2 The diagram illustrates a structural block diagram of an electronic device suitable for implementing the methods described above, according to an embodiment of this application. Figure 2 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0116] like Figure 2 As shown, an electronic device 300 according to an embodiment of this application includes a processor 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage portion 308 into a random access memory (RAM) 303. The processor 301 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 301 may also include onboard memory for caching purposes. The processor 301 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of this application.

[0117] RAM 303 stores various programs and data required for the operation of electronic device 300. Processor 301, ROM 302, and RAM 303 are interconnected via bus 304. Processor 301 executes various operations of the method flow according to embodiments of this application by executing programs in ROM 302 and / or RAM 303. It should be noted that the programs may also be stored in one or more memories other than ROM 302 and RAM 303. Processor 301 may also execute various operations of the method flow according to embodiments of this application by executing programs stored in said one or more memories.

[0118] According to embodiments of this application, the electronic device 300 may further include an input / output (I / O) interface 305, which is also connected to a bus 304. The system 300 may also include one or more of the following components connected to the input / output (I / O) interface 305: an input section 306 including a keyboard, mouse, etc.; an output section 307 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN card, modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the input / output (I / O) interface 305 as needed. A removable medium 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 310 as needed so that computer programs read from it can be installed into the storage section 308 as needed.

[0119] According to embodiments of this application, the method flow according to embodiments of this application can be implemented as a computer software program. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by processor 301, it performs the functions defined in the system of embodiments of this application. According to embodiments of this application, the systems, devices, modules, units, etc., described above can be implemented by computer program modules.

[0120] This application also provides a computer-readable storage medium, which may be included in the device / system / system described in the above embodiments; or it may exist independently and not assembled into the device / system / system. The aforementioned computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of this application.

[0121] According to embodiments of this application, the computer-readable storage medium can be a non-volatile computer-readable storage medium. Examples include, but are not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device.

[0122] For example, according to embodiments of this application, a computer-readable storage medium may include the ROM 302 and / or RAM 303 described above and / or one or more memories other than ROM 302 and RAM 303.

[0123] It should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This way of describing the specification is only for clarity. Those skilled in the art should regard the specification as a whole, and the technical solutions of each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

Claims

1. A knowledge graph-based detection service matching and recommendation method, characterized in that, Includes the following steps: S1. Collect multimodal data, including detection task information set, full-process data resource pool, and operation comprehensive dataset; S2. Based on the data resource pool of the entire detection process, construct an intelligent knowledge graph for detection services; S3. Based on the multimodal data, construct the user detection task requirement vector and the detection agency capability vector; S4. Based on the aforementioned comprehensive operational dataset, construct a service performance evaluation model; S5. Based on the detection task requirement vector, the detection agency capability vector, and the intelligent knowledge graph, a matching model is established through similarity calculation. Based on user needs and the service performance evaluation model, a detection service recommendation result is generated.

2. The detection service matching and recommendation method according to claim 1, characterized in that, Step S2 specifically includes: S21. Based on the testing task information set, obtain the user's engineering information, sample information, and fee voucher information; based on the full-process data resource pool, obtain the testing institution's sample information, testing records, testing reports, personnel information, and qualification certification testing capability range table; based on the operational comprehensive dataset, obtain the testing institution's historical order information, testing efficiency, instrument and equipment utilization rate, personnel qualification coverage rate, customer satisfaction rate, and testing institution rating. S22. Use machine learning algorithms to extract feature engineering from the full-process data resource pool; S23. Based on the aforementioned feature engineering, establish a feature vector set. Construct an intelligent knowledge graph for testing services.

3. The detection service matching and recommendation method according to claim 2, characterized in that, Step S3 specifically includes: S31. Based on user roles in multimodal data, construct a detection task requirement vector using sample information. S32. Perform dimensionality reduction processing on the detection task requirement vector to generate a user detection task vector. The user testing task vector shall include at least the sample name, specifications, model, grade, testing parameters, test method, and evaluation criteria; S33. Based on the role of testing institutions in multimodal data, construct the capability vector of each testing institution through sample name, specifications, grade, testing parameters, test methods, and evaluation criteria.

4. The detection service matching and recommendation method according to claim 1, characterized in that, Step S4 includes: S41. Perform data annotation, normalization, and feature analysis on the operational integrated dataset in the multimodal data; S42. Based on the comprehensive operational dataset in multimodal data, a service performance evaluation model is constructed using a dynamic weighting algorithm by combining multi-dimensional indicators of testing services performed by testing institutions with user needs.

5. The detection service matching and recommendation method according to claim 3, characterized in that, Step S5 includes: Obtain user detection task vectors and detection agency capability vectors, establish a cosine similarity matching model, and recommend detection agencies based on service effectiveness evaluation scores from high to low.

6. The detection service matching and recommendation method according to claim 5, characterized in that, The process of obtaining user detection task vectors and detection agency capability vectors, establishing a cosine similarity matching model, and recommending detection agencies based on service effectiveness evaluation scores from high to low includes: User detection task vector With knowledge graph Analysis was conducted, and the results were obtained. That is, there exist detection agencies that can establish matching models; Iterate through all testing institutions and determine the capability vector of each institution. The cosine similarity between the user detection task vector and the detection agency capability vector is calculated using the following formula: when Furthermore, when both have the same dimension, the cosine similarity... when And when the two are in different dimensions, for Dimensionality reduction processing to generate and Subvectors of the same dimension Cosine similarity When the cosine similarity result is 1, the demand vector and the capability vector are matched.

7. The detection service matching and recommendation method according to claim 7, characterized in that, The method further includes: When a user has multiple testing institutions matching their data, the Z-score is used to standardize the comprehensive operational dataset of each institution for that testing project. A service performance evaluation score S is then calculated based on multi-dimensional indicators, specifically: Where, x ik μ represents the k-th influencing factor for the i-th testing institution; k σ represents the mean of the k-th influencing factor; k Z represents the standard deviation of the k-th influencing factor; k This represents the Z-score of the k-th influencing factor; w ik This represents the weight of the k-th influencing factor, and S represents the service effectiveness assessment score.

8. A knowledge graph-based detection service matching and recommendation system, characterized in that, include: The data acquisition module is used to collect multimodal data, which includes a detection task information set, a full-process data resource pool, and an operational comprehensive dataset. The knowledge graph construction module is used to construct an intelligent knowledge graph for detection services based on the detection full-process data resource pool. The vector construction module is used to construct user detection task requirement vectors and detection agency capability vectors based on the multimodal data. The service performance evaluation model construction module is used to construct a service performance evaluation model based on the comprehensive operational dataset. The testing service recommendation result production module is used to establish a matching model based on the testing task demand vector, the testing institution capability vector, and the intelligent knowledge graph through similarity calculation, and generate testing service recommendation results according to user needs and the service performance evaluation model.

9. An electronic device, comprising: One or more processors; Memory, used to store one or more programs. Wherein, when the one or more programs are executed by the one or more processors, the one or more processors implement the method of any one of claims 1 to 7.

10. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 7.

Images