A dynamic management method and system for automatic parts standard selection library

Abstract

The present invention provides a dynamic management method and system for a standard selection library of automated parts, which relates to the technical field of selection library management, including: reading a first search feature of a target user; transferring to a user portrait library for similarity matching to obtain a first selection set; evaluating the suitability of the selection, determining a plurality of first suitability coefficients, and constructing a first suitability sequence; performing component visualization based on the first suitability sequence; wherein, evaluating the suitability of the selection includes: determining whether the type discreteness of the first selection set meets a predetermined discrete index; if not, evaluating the suitability based on the frequency of occurrence; if satisfied, evaluating the suitability based on the type difference and the frequency of occurrence. The present invention solves the technical problem that the recommendation method of the prior art mainly relies on explicit user input or makes recommendations based on fixed rules, and cannot effectively deal with scenarios where user needs are unclear or diverse, resulting in low recommendation efficiency and accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of model selection library management, and in particular to a dynamic management method and system for a standard model selection library of automation components. Background Art

[0002] The automation parts standard selection library provides a large number of standard parts. When users choose on the platform, they often encounter the problem of too many categories and difficult screening. On the one hand, there are many types of automation parts, and there are tens of thousands of products of different brands, specifications, and functions. Traditional search methods usually rely on users to enter keywords or manually screen, which is particularly unfriendly to new users. Users often lack professional knowledge or in-depth understanding of the product and find it difficult to quickly find suitable parts. On the other hand, in the process of parts selection, user needs are sometimes not clear. Existing recommendation methods mainly rely on users' explicit input or make recommendations based on fixed rules, but such recommendations are often too single and cannot effectively deal with scenarios where user needs are unclear or diverse. When user needs are unclear, it is impossible to provide a variety of product choices, resulting in the recommendation results being not smart and accurate enough and the user experience being poor. Summary of the invention

[0003] The present application provides a dynamic management method and system for an automated parts standard selection library, aiming to solve the technical problem that the recommendation methods in the prior art mainly rely on explicit user input or make recommendations based on fixed rules, but such recommendations are often too single and cannot effectively deal with scenarios where user needs are unclear or diverse, resulting in low recommendation efficiency and accuracy.

[0004] The first aspect disclosed in the present application provides a dynamic management method for a standard selection library of automation parts, the method comprising: reading a first search feature of a target user, wherein the target user is a new user who registers for the first time; transferring the first search feature to a user portrait library for similarity matching, and obtaining a first associated user set and a first selection set; performing selection suitability evaluation on multiple parts in the first selection set, determining multiple first suitability coefficients, and constructing a first suitability sequence; performing a visual display of parts of the standard selection library of automation parts based on the first suitability sequence; wherein, performing selection suitability evaluation on multiple parts in the first selection set, comprising: determining whether the type discreteness of the multiple parts in the first selection set meets a predetermined discrete index; if not, performing suitability evaluation based on the occurrence frequency of the parts; if satisfied, performing suitability evaluation based on the type difference and occurrence frequency of the parts.

[0005] The second aspect disclosed in the present application provides a dynamic management system for a standard selection library of automated parts, the system being used for the above-mentioned dynamic management method for a standard selection library of automated parts, the system comprising: a retrieval feature reading module, the retrieval feature reading module being used to read a first retrieval feature of a target user, wherein the target user is a new user who registers for the first time; a similarity matching module, the similarity matching module being used to transfer the first retrieval feature to a user portrait library for similarity matching, and obtain a first associated user set and a first selection set; a fitness evaluation module, the fitness evaluation module being used to respectively perform selection fitness evaluation on a plurality of parts in the first selection set, determine a plurality of first fitness coefficients, and construct a first fitness sequence; a visualization display module, the visualization display module being used to perform visualization display of parts of the standard selection library of automated parts based on the first fitness sequence; wherein, the selection fitness evaluation is respectively performed on a plurality of parts in the first selection set, including: determining whether the type discreteness of the plurality of parts in the first selection set meets a predetermined discrete index; if not, performing fitness evaluation based on the occurrence frequency of the parts; if satisfied, performing fitness evaluation based on the type difference and occurrence frequency of the parts.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] For new users who register for the first time, we collect their initial behavioral characteristics and perform similarity matching with the user portrait library to quickly identify the needs of new users. Compared with traditional manual screening, users do not need to browse a large number of irrelevant products. The system can accurately screen out the first selection set related to user needs based on the similar behaviors of historical users, thereby shortening the user's search and decision-making time; the selection suitability of multiple parts in the initially screened first selection set is evaluated separately to ensure that it is not just a simple listing of recommended products, but a personalized recommendation based on the user's demand characteristics. Through further judgment of type discreteness, the system can make different response strategies based on the clarity of user needs. If the user's needs are clear, high-frequency products will be recommended first; if the needs are unclear, a variety of product choices will be provided to ensure that users have a wealth of choices. This dynamic adjustment based on real-time analysis improves the accuracy and flexibility of recommendations, ensuring that the most appropriate suggestions can be provided regardless of whether the user's needs are clear or not; components are visualized based on the fitness sequence, allowing users to browse recommended products more intuitively. Through the visual display method, users can not only quickly view components that meet their needs, but also more easily understand the characteristics and fitness of different components. This visual display method improves the user experience, enables users to make selection decisions more efficiently, and reduces decision fatigue.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic flow chart of a method for dynamically managing a standard selection library of automated components provided in an embodiment of the present application;

[0010] Figure 2 A schematic diagram of the structure of a dynamic management system for a standard selection library of automated components provided in an embodiment of the present application.

[0011] Explanation of reference numerals: retrieval feature reading module 10 , similarity matching module 20 , fitness evaluation module 30 , visualization display module 40 . DETAILED DESCRIPTION

[0012] The embodiments of the present application provide a dynamic management method and system for a standard selection library of automated parts, thereby solving the technical problem that the recommendation methods in the prior art mainly rely on explicit user input or make recommendations based on fixed rules, but such recommendations are often too simple and cannot effectively deal with scenarios where user needs are unclear or diverse, resulting in low recommendation efficiency and accuracy.

[0013] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically introduced below in conjunction with the accompanying drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0014] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a method for dynamically managing an automation component standard selection library, the method comprising:

[0015] A first search feature of a target user is read, wherein the target user is a new user who registers for the first time.

[0016] The target users are new users who register for the first time, that is, users who have just entered and started using the automation parts standard selection library. New users usually have no historical data, so it is necessary to rely on their initial operation behavior for recommendation and matching. Read the first search feature of the target user. The first search feature refers to the behavioral characteristics exhibited by the user during the interaction with the system. These characteristics include the user's access behavior in the system, the search keywords entered, the pages browsed, and the type of device used. When the user registers for the first time and starts using it, these search features are automatically monitored and recorded. By collecting these feature data, the user's needs can be better understood, which lays the foundation for subsequent matching and recommendations.

[0017] The first search feature flow is transferred to the user portrait library for similarity matching to obtain a first associated user set and a first selected product set.

[0018] The user portrait library is a database used to store and analyze user behavior and preference characteristics, with the goal of providing users with more accurate personalized recommendations. The first search feature is transferred to the user portrait library, which stores a large amount of historical behavior data of users. The search features of new users are compared with the features of these historical users. Based on multiple dimensions, including access nodes, search keywords, browsing nodes, device types, etc., association analysis is performed to calculate the similarity between new users and historical users. Through similarity matching, a set of historical users whose similarity with the first search feature of the new user meets the similarity threshold is finally screened out as the first associated user set. The historical behavior of these users can provide a reference for new users; based on the first associated user set, the products that these historical users often choose when purchasing parts are extracted to form a recommendation candidate set as the first selection set, which is the product set most relevant to the interests of new users.

[0019] The product selection suitability is evaluated for each of the multiple components in the first product selection set, multiple first adaptation coefficients are determined, and a first adaptation sequence is constructed.

[0020] Product selection suitability evaluation is a process used to measure the degree of matching between parts and target user needs. In this process, the suitability coefficient of each part is calculated based on the different characteristics of the parts and the degree of matching between user needs. First, determine whether the type dispersion of multiple parts in the first product selection set meets the predetermined dispersion index. Type dispersion refers to the distribution of part types, which is used to measure the diversity of different types of parts in the product selection set. If the type dispersion is small, it means that the user has concentrated on browsing or searching for a certain type of parts; conversely, if the type dispersion is large, it means that the parts browsed or searched by the user cover many different categories.

[0021] Furthermore, if the dispersion does not meet the predetermined indicators, the adaptability evaluation is performed based on the frequency of occurrence of the components. For example, components with high frequency of occurrence may be more relevant to the needs of users. If the dispersion meets the predetermined indicators, the adaptability is comprehensively evaluated based on the type difference, that is, the difference between components, and the frequency of occurrence. Finally, the corresponding adaptation coefficient is generated based on the adaptation evaluation results of each component, indicating the degree of matching between the component and the needs of the target user. The higher the adaptation coefficient, the more suitable the component is for the needs of the target user.

[0022] The first adaptation sequence is a list of components sorted from high to low according to the adaptation coefficient of each component. This sequence represents the sorting of components that best meets the needs of the target users, thereby providing a basis for subsequent display and recommendation.

[0023] Execute a visual display of components of the automation component standard selection library based on the first adaptation sequence.

[0024] According to the generated first adaptation sequence, the parts are presented to the user in a graphical and modular manner. For example, the parts that meet the user's needs are listed by priority, and the user can browse them in order; according to the fitness coefficient of the parts, the recommended content is displayed in the form of charts or graphics, such as heat maps, pie charts, etc., so that the user can see at a glance which parts are more suitable. This way of visual display of parts can enhance the interactive experience between users and the system, allowing users to easily and quickly browse and select parts that meet their needs.

[0025] In addition, based on data such as user browsing behavior and duration of stay, the subsequent display content can be further adjusted to achieve multi-step recommendations based on user behavior and access paths, further optimize the display effect, and ensure the relevance and effectiveness of the recommendations.

[0026] The product suitability evaluation is performed on the multiple components in the first product selection set, including:

[0027] Determine whether the type discreteness of the multiple components in the first selection set meets the predetermined discrete index; if not, perform a fitness evaluation based on the occurrence frequency of the components; if satisfied, perform a fitness evaluation based on the type difference and occurrence frequency of the components.

[0028] Type dispersion refers to the distribution of component types, which is used to measure the diversity of different types of components in the selection set. The specific type dispersion calculation method will be developed in the subsequent steps and will not be described here. The predetermined dispersion index is a threshold set according to the specific application scenario, which is used to determine the degree of dispersion of component types.

[0029] If the type dispersion of the first selection set does not meet the preset discrete index, that is, the dispersion is small, it means that the user has concentrated on browsing or searching for a certain type of parts. This shows that the user's needs are relatively clear, and parts with a higher frequency of appearance in this category should be recommended first to improve the accuracy of the recommendation.

[0030] In this case, the adaptability is evaluated mainly based on the frequency of occurrence of components. The frequency of occurrence refers to the number of times a component appears in the first set of selected products. The higher the frequency of occurrence, the more users pay attention to the component. Based on the statistical results of the frequency of occurrence, components with higher frequency of occurrence are given a higher adaptation coefficient and are displayed to users first in subsequent recommendations.

[0031] If the type dispersion of the first product set meets the preset discrete index, that is, the dispersion is large, it means that the parts browsed or searched by the user cover many different categories, which means that the user's needs are unclear or there is no particularly clear goal. At this time, it is necessary to recommend products of multiple categories to cover the user's potential needs as much as possible.

[0032] In this case, a more complex fitness evaluation mechanism is adopted, specifically, a comprehensive evaluation is conducted by combining type difference and frequency of occurrence. Type difference refers to the difference between different types of parts. The greater the difference between the types of parts, the more significant the difference between them. By calculating the difference between parts, we can better understand the user's demand for diversified products and recommend multiple types of products. The calculation of type difference can be analyzed through multi-dimensional characteristics such as the function, specification, material and application scenario of the parts, and the overall difference of each type of parts can be calculated using topological diagrams and other methods. On the basis of type difference, the frequency of occurrence of parts is also considered. If the frequency of occurrence of a certain type of part is high, it means that this type of product is more in line with the user's potential needs. Finally, a weighted evaluation is performed based on the type difference and frequency of occurrence of each part. By combining these factors, users can be provided with both diversified and accurate recommendations.

[0033] Furthermore, the first search feature includes a first access node, a first search keyword, a first browsing node, and an access device type.

[0034] The first search feature includes the first access node, the first search keyword, the first browsing node and the access device type, among which the first access node is the time node when the target user first enters the system; the first search keyword is the keyword entered by the target user when searching in the system, such as keywords such as motor and sensor; the first browsing node is the specific content page or product selection page browsed by the target user in the system, and different pages represent the user's interest in different types of components; the access device type is the type of device used by the target user, such as PC, mobile phone or tablet, and the usage scenarios of different devices reflect the differences in user needs.

[0035] Furthermore, transferring the first search feature to the user portrait library for similarity matching to obtain a first associated user set and a first selected product set includes:

[0036] Based on the user portrait library, correlation analysis is performed on the access nodes, search keywords, browsing nodes, access device types and final product selection features to determine multiple correlations; multiple similarity judgment thresholds are configured according to the multiple correlations, wherein the similarity judgment threshold is positively correlated with the correlation; based on the multiple similarity judgment thresholds, similarity matching between the first search feature and the user portrait library is performed.

[0037] The final selection features refer to the attributes of the parts that users finally choose after a series of browsing and selection, including the functions, specifications, price ranges, brands, etc. of the parts. The correlation analysis is performed on the access nodes, search keywords, browsing nodes, access device types and the final selection features. Specifically, it can be calculated by counting the number of co-occurrences between user behavior and selection features, mining association rules, etc. For example, users who visit a certain node have a high probability of eventually choosing a certain type of parts, so the correlation between the access node and the type of parts is high; users who use certain search keywords have a high frequency of eventually purchasing specific parts, indicating that the keywords have a high correlation with the type of products. Through these analyses, the correlation between each dimension and the final selection features can be obtained, which is usually expressed as a value between 0 and 1. The higher the correlation, the closer the value is to 1.

[0038] The similarity judgment threshold is a value used to judge whether the first search feature is similar enough to the user in the user portrait library. If the similarity between the first search feature and a user's feature is greater than the similarity judgment threshold, the two are considered similar. Different dimensions correspond to different threshold settings. For example, the matching requirements for search keywords and access device types are different. The threshold is configured based on the calculated correlation. The higher the correlation, the stricter the threshold setting and the more precise the requirement; the lower the correlation, the more relaxed the threshold can be, allowing for greater differences.

[0039] According to multiple similarity judgment thresholds, each search feature of the target user, including the first access node, the first search keyword, the first browsing node and the access device type, is compared with the corresponding features of the users in the user portrait library. When the similarity between the target user's features and the behavioral features of a historical user in all dimensions is greater than the threshold, the historical user is judged to be similar to the target user. According to this standard, all users similar to the target user are screened out from the user portrait library to form a first associated user set.

[0040] Furthermore, calculating the type dispersion of multiple components in the first product set includes:

[0041] Extract the types of the multiple parts to determine the types of the multiple parts; and construct a type dispersion evaluation function:

[0042]

[0043] in, is the type discreteness, is the total number of parts, is the number of component types, is the frequency of occurrence of the nth component, is the average frequency; and using the type dispersion evaluation function, the dispersion of the multiple component types is calculated.

[0044] The types of parts can be extracted based on features such as function, purpose, specification, material, etc. After extracting the types of parts, these parts are classified into different categories to determine multiple types of parts. These types of parts are counted to determine the total number of types of parts N included, providing basic data for subsequent discrete calculations;

[0045] The construction type discreteness evaluation function is as follows:

[0046]

[0047] This type of dispersion evaluation function is used to measure the degree of distribution difference of component types. The function calculates the difference between the frequency of occurrence of each type and the average frequency, and sums the squares of these difference values ​​to finally obtain the dispersion result. The higher the dispersion value, the more dispersed the distribution of component types, that is, some types of components appear more and other types appear less; low dispersion means that the frequency of occurrence of various types of components is more uniform.

[0048] This type of discreteness evaluation function is used to calculate the discreteness of multiple component types. This discreteness calculation method helps analyze the distribution of component types and provides a basis for subsequent component recommendations.

[0049] Furthermore, the suitability evaluation is performed based on the type difference and frequency of occurrence of parts, including:

[0050] The overall differences of the multiple component types are calculated to determine multiple type differences; weights are configured for the multiple component types according to the multiple type differences to determine multiple weight ratios, wherein the weight ratio is positively correlated with the type difference; and the adaptability is evaluated according to the multiple weight ratios and the frequency of occurrence.

[0051] The differences of multiple component types in the first selection set are calculated. The differences reflect the differences between different types of components in terms of function, specification, material, application scenarios, etc. The greater the difference, the greater the difference, the greater the difference in characteristics of these components, and they are suitable for different needs. Specifically, the key features of each component type are first extracted. These features include function, specification, material, application scenario, etc. Each type of component has different performance in these dimensions. The extracted features are calculated through an algorithm to calculate the differences. For example, topological structure analysis is used to measure the differences between different component types. The calculated differences between each pair of component types are combined to obtain the overall difference of each component type. Types with higher differences indicate that they are clearly distinguished from other types.

[0052] According to multiple type differences, a weight is assigned to each corresponding component type, indicating the influence of the component type in the final fitness evaluation. The higher the type difference, the greater the difference between the component type and other types, and a higher weight ratio is assigned to it to reflect its importance in the recommendation process. Therefore, the weight ratio is positively correlated with the type difference. The weight ratio indicates the contribution ratio of each component type in the final recommendation ranking. Component types with larger weights will have higher priorities in the recommendation.

[0053] The frequency of occurrence of parts is another important factor. The frequency of occurrence refers to the number of times a part appears in the first selection set. The higher the frequency of occurrence, the more users pay attention to the part. Combining the weight ratio and the frequency of occurrence, we evaluate the suitability of each part. The goal of the suitability evaluation is to measure the degree of match between each part and the needs of the target users. By combining the comprehensive evaluation of the weight ratio and the frequency of occurrence, we can give priority to recommending parts that appear more frequently in categories with higher differences, so as to ensure that the recommended products meet the diverse needs of users and focus on the products that users may be most interested in.

[0054] Furthermore, performing overall difference calculation on the multiple component types to determine multiple type differences includes:

[0055] Acquire multiple component feature sets of the multiple component types, wherein the component features include at least functions, specifications, materials, and application scenarios; construct a structural topology diagram of the component type according to the functions, specifications, materials, and application scenarios to obtain multiple structural topology diagrams; and calculate the overall differences of the multiple component types based on the multiple structural topology diagrams to determine the differences of multiple types.

[0056] Extract key component features for multiple component types and obtain multiple component feature sets, where component features include at least function, specification, material and application scenario, where function is the basic purpose or core function of the component, for example, a component is used for motor drive, and another component is used for sensor measurement, which is one of the core features reflecting the difference in component types; specification is the physical or technical specifications of the component, such as size, power, weight, voltage, etc. These parameters are important indicators for judging whether the component can be applied to a specific scenario; material is the manufacturing material of the component, such as plastic, metal, composite material, etc. Components of different materials may have different durability, temperature resistance or applicable environment; application scenario is the specific use scenario of the component, for example, some components are used for industrial manufacturing equipment, while others are used for consumer electronic devices. The difference in application scenarios can significantly affect the user's selection decision. By extracting these key features for multiple component types, a feature set of each component type is formed, laying the foundation for subsequent structured analysis.

[0057] A structural topology map is built based on component features. The structural topology map is a graphical representation method used to describe the multi-dimensional features of component types and help analyze the overall differences of component types. Specifically, the component features are mapped to nodes of the topology map. Since functions, specifications, materials, and application scenarios are features of multiple dimensions, the topology map of the component type is multi-dimensional, and each dimension represents specific features. By integrating these dimensions, an independent topological structure is built for each component type, and ultimately multiple structural topology maps of multiple components are obtained.

[0058] Based on the multiple structural topological graphs, each structural topological graph is compared with other structural topological graphs respectively, and the similarity between different topological graphs is evaluated. This can be done by comparing nodes. For example, the more similar two topological graphs are in terms of function, specification, material and other nodes, the higher the similarity. The difference is complementary to the similarity. For the topological graphs of two component types, the lower the similarity, the greater the difference. The difference set is calculated using the similarity set, and finally the overall type difference of each component type is obtained by taking the mean. The difference is used to characterize the difference between component types, thereby helping to evaluate the fit in subsequent steps.

[0059] Furthermore, based on the multiple structural topological diagrams, the overall difference calculation of the multiple component types includes:

[0060] A first structural topology map is randomly selected from the multiple structural topology maps; a similarity comparison is performed on the first structural topology map and other structural topology maps in the multiple structural topology maps to determine a first similarity set; a first deviation degree set is calculated based on the first similarity set, and a mean calculation is performed on the first deviation degree set to determine a first type difference, which is added to the multiple type differences.

[0061] From the multiple constructed structural topological maps, a topological map is randomly selected as an analysis object as the first structural topological map, so as to ensure that all topological maps have the same chance to be used as analysis objects for similarity comparison.

[0062] The selected first structural topology map is compared with other structural topology maps one by one, the similarity between them is calculated, and the results are summarized into a similarity set. Specifically, the similarity can be performed by comparing whether the nodes in the two topology maps are consistent, including calculating the similarity of nodes such as functions, specifications, materials and application scenarios, and weighted averaging the similarity of each node to obtain the similarity between the two topology maps, and obtain the first similarity. By analogy, continue to use the first structural topology map as a benchmark, traverse other structural topology maps one by one and perform similarity calculations respectively, and finally obtain the first similarity set.

[0063] The deviation degree indicates the degree of difference between the first structural topology diagram and other structural topology diagrams. The higher the similarity, the smaller the deviation degree; the lower the similarity, the larger the deviation degree. The deviation degree can be obtained by calculating 1 minus the similarity. According to the first similarity set, the first deviation degree set is calculated, that is, the degree of difference between the first structural topology diagram and other structural topology diagrams. The first deviation degree set is averaged to obtain the first type difference degree, which indicates the average degree of difference between the first structural topology diagram and other topology diagrams. After the calculation is completed, the first type difference degree is added to multiple type difference degrees to summarize and analyze the overall difference degrees of all component types.

[0064] Furthermore, the visual display of components of the automation component standard selection library is performed based on the first adaptation sequence, and then the method further includes:

[0065] Read the second search feature of the target user, wherein the second search feature includes a second browsing node and a second dwell time; based on the first associated user set, perform similarity matching according to the second browsing node and the second dwell time to obtain the second associated user set and the second product selection set; generate a second adaptation sequence based on the second product selection set to perform subsequent parts visualization.

[0066] Read further behavior data of the target user in subsequent operations to obtain a second retrieval feature, wherein the second retrieval feature includes a second browsing node and a second dwell time, wherein a browsing node is a specific page or functional module visited by a user when browsing the system, and the second browsing node is a page visited by the user in subsequent operations, which may be a component details page, a product classification page, etc.; the second dwell time is the time a user stays on a specific page. Generally, the longer the dwell time, the more interested the user is in the content of the page. This data can be automatically collected from the system log.

[0067] Compare the target user's second browsing node and second stay duration with the user behavior in the first associated user set. Specifically, compare the similarity of the target user and other users in the first associated user set in browsing paths, for example, whether the users browse the same page; compare whether the stay duration is similar, for example, two users stay on a specific page for a long time, indicating that they have similar interests in the page. Through similarity calculation, obtain the browsing path similarity between each user in the first associated user set and the target user, and filter the first associated user set according to the path similarity to obtain the second associated user set whose similarity meets the threshold, and obtain the second selected product set of the second associated user set. This recommended set is more in line with the user's preference than the first selected product set.

[0068] The same processing method as the first product set is used to evaluate the product suitability of multiple parts in the second product set, determine multiple second fitness coefficients, construct a second fitness sequence, and perform subsequent parts visualization according to the second fitness sequence to help users find the parts of interest more quickly.

[0069] In summary, the method for dynamically managing an automated component standard selection library provided by the embodiment of the present application has the following technical effects:

[0070] For new users who register for the first time, we collect their initial behavioral characteristics and perform similarity matching with the user portrait library to quickly identify the needs of new users. Compared with traditional manual screening, users do not need to browse a large number of irrelevant products. The system can accurately screen out the first selection set related to user needs based on the similar behaviors of historical users, thereby shortening the user's search and decision-making time; the selection suitability of multiple parts in the initially screened first selection set is evaluated separately to ensure that it is not just a simple listing of recommended products, but a personalized recommendation based on the user's demand characteristics. Through further judgment of type discreteness, the system can make different response strategies based on the clarity of user needs. If the user's needs are clear, high-frequency products will be recommended first; if the needs are unclear, a variety of product choices will be provided to ensure that users have a wealth of choices. This dynamic adjustment based on real-time analysis improves the accuracy and flexibility of recommendations, ensuring that the most appropriate suggestions can be provided regardless of whether the user's needs are clear or not; components are visualized based on the fitness sequence, allowing users to browse recommended products more intuitively. Through the visual display method, users can not only quickly view components that meet their needs, but also more easily understand the characteristics and fitness of different components. This visual display method improves the user experience, enables users to make selection decisions more efficiently, and reduces decision fatigue.

[0071] Embodiment 2, based on the same inventive concept as the method for dynamically managing a standard selection library of automated components in the aforementioned embodiment, Figure 2 As shown, the embodiment of the present application provides a dynamic management system for an automated component standard selection library, the system comprising:

[0072] A retrieval feature reading module 10, the retrieval feature reading module 10 is used to read the first retrieval feature of the target user, wherein the target user is a new user who registers for the first time; a similarity matching module 20, the similarity matching module 20 is used to transfer the first retrieval feature to the user portrait library for similarity matching, and obtain a first associated user set and a first product selection set; a fitness evaluation module 30, the fitness evaluation module 30 is used to perform product selection fitness evaluation on multiple components in the first product selection set, determine multiple first fitness coefficients, and construct a first fitness sequence; a visualization display module 40, the visualization display module 40 is used to perform component visualization of the automation component standard selection library based on the first fitness sequence; wherein, the product selection fitness evaluation is performed on multiple components in the first product selection set, including: determining whether the type discreteness of the multiple components in the first product selection set meets the predetermined discrete index; if not, performing fitness evaluation based on the occurrence frequency of the components; if satisfied, performing fitness evaluation based on the type difference and occurrence frequency of the components.

[0073] Furthermore, the first search feature includes a first access node, a first search keyword, a first browsing node, and an access device type.

[0074] Furthermore, the system further includes a similarity matching module to perform the following operation steps:

[0075] Based on the user portrait library, correlation analysis is performed on the access nodes, search keywords, browsing nodes, access device types and final product selection features to determine multiple correlations; multiple similarity judgment thresholds are configured according to the multiple correlations, wherein the similarity judgment threshold is positively correlated with the correlation; based on the multiple similarity judgment thresholds, similarity matching between the first search feature and the user portrait library is performed.

[0076] Furthermore, the system further includes a dispersion calculation module to perform the following operation steps:

[0077] Extract the types of the multiple parts to determine the types of the multiple parts; and construct a type dispersion evaluation function:

[0078]

[0079] in, is the type discreteness, is the total number of parts, is the number of component types, is the frequency of occurrence of the nth component, is the average frequency; and using the type dispersion evaluation function, the dispersion of the multiple component types is calculated.

[0080] Furthermore, the system also includes a fitness evaluation module to perform the following operation steps:

[0081] The overall differences of the multiple component types are calculated to determine multiple type differences; weights are configured for the multiple component types according to the multiple type differences to determine multiple weight ratios, wherein the weight ratio is positively correlated with the type difference; and the adaptability is evaluated according to the multiple weight ratios and the frequency of occurrence.

[0082] Furthermore, the system further includes a plurality of type difference determination modules to perform the following operation steps:

[0083] Acquire multiple component feature sets of the multiple component types, wherein the component features include at least functions, specifications, materials, and application scenarios; construct a structural topology diagram of the component type according to the functions, specifications, materials, and application scenarios to obtain multiple structural topology diagrams; and calculate the overall differences of the multiple component types based on the multiple structural topology diagrams to determine the differences of multiple types.

[0084] Furthermore, the system further includes a plurality of type difference acquisition modules to perform the following operation steps:

[0085] A first structural topology map is randomly selected from the multiple structural topology maps; a similarity comparison is performed on the first structural topology map and other structural topology maps in the multiple structural topology maps to determine a first similarity set; a first deviation degree set is calculated based on the first similarity set, and a mean calculation is performed on the first deviation degree set to determine a first type difference, which is added to the multiple type differences.

[0086] Furthermore, the system also includes a component visualization display module to perform the following operation steps:

[0087] Read the second search feature of the target user, wherein the second search feature includes a second browsing node and a second dwell time; based on the first associated user set, perform similarity matching according to the second browsing node and the second dwell time to obtain the second associated user set and the second product selection set; generate a second adaptation sequence based on the second product selection set to perform subsequent parts visualization.

[0088] Through the above-mentioned detailed description of the dynamic management method of a standard selection library for automated parts in this specification, those skilled in the art can clearly understand the dynamic management system of a standard selection library for automated parts in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0089] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A dynamic management method for an automation component standard selection library, characterized in that: The method comprises: Reading a first search feature of a target user, wherein the target user is a new user who registers for the first time; The first search feature is transferred to the user portrait library for similarity matching to obtain a first associated user set and a first selected product set; Performing product selection suitability evaluation on a plurality of components in the first product selection set, determining a plurality of first suitability coefficients, and constructing a first suitability sequence; Execute a visual display of components of the automation component standard selection library based on the first adaptation sequence; The product suitability evaluation is performed on the multiple components in the first product selection set, including: Determining whether the type dispersion of the plurality of components in the first selected product set meets a predetermined dispersion index; If not, the suitability evaluation is performed based on the frequency of occurrence of the components; If satisfied, the suitability is evaluated based on the type difference and frequency of occurrence of the parts; The first search feature includes a first access node, a first search keyword, a first browsing node, and an access device type; The first search feature is transferred to the user portrait library for similarity matching to obtain a first associated user set and a first selected product set, including: Based on the user portrait library, the access nodes, search keywords, browsing nodes, access device types and final product selection features are analyzed for correlation to determine multiple correlations; configuring a plurality of similarity judgment thresholds according to the plurality of association degrees, wherein the similarity judgment thresholds are positively correlated with the association degrees; Based on the multiple similarity judgment thresholds, performing similarity matching between the first search feature and the user portrait library; Calculate the type dispersion of multiple parts in the first selection set, including: Extracting types of the multiple components to determine multiple component types; Construct type discreteness evaluation function: ； in, is the type discreteness, is the total number of parts, is the number of component types, For the The frequency of occurrence of the components, is the average frequency; The type dispersion evaluation function is used to calculate the dispersion of the multiple component types.

2. The method for dynamic management of a standard selection library of automation components according to claim 1, characterized in that: Compatibility evaluation is performed based on the type differences and frequency of occurrence of parts, including: Calculating overall differences of the multiple component types to determine multiple type differences; According to the multiple type differences, weights are assigned to the multiple component types to determine multiple weight proportions, wherein the weight proportions are positively correlated with the type differences; The degree of adaptability is evaluated based on the multiple weight proportions and occurrence frequencies.

3. The method for dynamic management of a standard selection library of automation components according to claim 2, characterized in that: Performing overall difference calculation on the multiple component types to determine multiple type differences includes: Acquire multiple component feature sets of the multiple component types, wherein the component features at least include functions, specifications, materials, and application scenarios; Building a structural topology diagram of the component type according to the functions, specifications, materials and application scenarios to obtain multiple structural topology diagrams; Based on the multiple structural topological diagrams, overall differences of the multiple component types are calculated to determine multiple type differences.

4. The method for dynamic management of a standard selection library of automated parts according to claim 3, characterized in that: Based on the multiple structural topological diagrams, overall difference calculation is performed on the multiple component types, including: Randomly select a first structural topology map from the multiple structural topology maps; Performing a similarity comparison on the first structural topology graph and other structural topology graphs in the plurality of structural topology graphs to determine a first similarity set; A first deviation degree set is calculated according to the first similarity degree set, and a mean value is calculated on the first deviation degree set to determine a first type difference degree, which is added to the multiple type difference degrees.

5. The method for dynamic management of a standard selection library of automation components according to claim 1, characterized in that: Executing a visual display of components of the automation component standard selection library based on the first adaptation sequence, and then further comprising: Reading a second search feature of the target user, wherein the second search feature includes a second browsing node and a second stay duration; Based on the first associated user set, similarity matching is performed according to the second browsing node and the second stay duration to obtain a second associated user set and a second selected product set; A second adaptation sequence is generated based on the second selection set, and subsequent parts visualization is performed.

6. A dynamic management system for an automation component standard selection library, characterized in that: A method for dynamically managing a standard selection library of automated components according to any one of claims 1 to 5, the system comprising: A search feature reading module, wherein the search feature reading module is used to read a first search feature of a target user, wherein the target user is a new user who registers for the first time; A similarity matching module, wherein the similarity matching module is used to transfer the first search feature flow to a user portrait library for similarity matching, and obtain a first associated user set and a first selected product set; A fitness evaluation module, wherein the fitness evaluation module is used to evaluate the fitness of the multiple components in the first product selection set, determine multiple first fitness coefficients, and construct a first fitness sequence; A visualization display module, the visualization display module is used to perform a visualization display of parts of the automation parts standard selection library based on the first adaptation sequence; The product suitability evaluation is performed on the multiple components in the first product selection set, including: Determining whether the type dispersion of the plurality of components in the first selected product set meets a predetermined dispersion index; If not, the suitability evaluation is performed based on the frequency of occurrence of the components; If satisfied, the suitability is evaluated based on the type differences and occurrence frequencies of the components.

Images