Construction method and system for user-defined list of delivery subject

Abstract

The invention relates to the technical field of data index statistics, and discloses a method and system for constructing a user-defined list of a delivery subject, and the method comprises the steps: obtaining content links of a plurality of delivery subjects, so as to obtain index data; obtaining a standardized index data set; calculating a KCI index of the corresponding delivery subject based on the index data set; and sorting the plurality of delivery subjects based on the KCI index, and completing the construction of the user-defined list. According to the method, the KCI index of the delivery subject is automatically calculated, and the personalized list is generated in combination with the user demand, so that the comprehensiveness and the real-time performance of data acquisition are improved, and the efficiency and the comprehensiveness of data updating are improved. A dynamic normalization processing method is adopted, industry characteristics and a time decay function are introduced, and the influence of data scale difference and timeliness between different delivery subjects is overcome. The KCI indexes of the delivery subjects are calculated based on multi-index weighting, and more accurate value sorting and delivery suggestions are provided.

Description

Technical Field

[0001] The present invention relates to the technical field of data indicator statistics, and in particular to a method and system for constructing a custom list of an investment entity. Background Art

[0002] With the rapid development of the new media industry, various publishers (such as WeChat public accounts, Weibo accounts, etc.) have gradually become important channels for brand promotion, content distribution and traffic monetization. In order to effectively evaluate the marketing value of these publishers, companies usually need to systematically analyze and rank the influence, activity and potential of their published content. However, the methods and tools currently available on the market for evaluating publishers still have the following defects: Data acquisition limitations: Existing tools usually rely on manual data collection or simple crawler technology, and can only obtain basic data of a single dimension, such as the number of readings and likes, and cannot achieve cross-platform multi-dimensional indicator integration and automatic acquisition. The lack of the ability to parse dynamic content links makes it impossible to quickly update and fully obtain the latest data of new media accounts. Irregular data processing: There is a lack of a unified standardization mechanism for indicator data during processing, and the comparison results between different publishers are easily affected by data scale, platform rules and time differences, resulting in insufficient accuracy and fairness of the evaluation results. Industry characteristics cannot be integrated into data processing, and existing tools do not dynamically normalize or adjust weights for content characteristics of different industries (such as frequency, interaction methods, etc.). Insufficient comprehensive evaluation model: Evaluation tools on the market usually focus on single indicator ranking or simple weighted average, and fail to effectively combine multi-dimensional data and dynamic factors such as time decay. Lack of in-depth mining and trend prediction functions for the potential value of the publisher, only static rankings can be provided, which cannot meet the diverse needs of enterprises. List display and scenario adaptation are not intelligent: The existing list generation method lacks customization functions and cannot flexibly adjust indicator dimensions or weight settings according to different user needs. It is impossible to generate personalized strategy recommendations for specific delivery scenarios, and enterprises need to rely on manual analysis and decision-making, which is inefficient. Summary of the invention

[0003] In view of this, the present invention proposes a method and system for constructing a custom list of investment entities, which can construct an intelligent and personalized list of investment entities through automatic acquisition, dynamic normalization and weighted evaluation of multi-dimensional indicator data, and significantly improve the accuracy of investment value evaluation and decision-making efficiency. The present invention provides the following technical solutions: A method for constructing a custom list of delivery entities, the method comprising: obtaining content links of multiple delivery entities to obtain indicator data of corresponding delivery entities; performing data processing on the indicator data to obtain a standardized indicator data set; calculating the KCI index of the corresponding delivery entity based on each indicator data set; sorting multiple delivery entities based on the KCI index, and completing the construction of the custom list of delivery entities.

[0004] Optionally, the method for obtaining content links of multiple delivery entities to obtain indicator data of corresponding delivery entities includes: capturing multiple delivery entities and their corresponding content links through each API interface period; extracting meta information from the content link to determine the indicator data in the content link; performing statistics on the indicator data determined in multiple periods, and using a similar content recommendation algorithm to predict whether there are any missing content links, and prompting the user to review; and performing distributed database storage based on the statistical indicator data to achieve platform and period retrieval of each delivery entity.

[0005] Optionally, the method of processing the indicator data to obtain a standardized indicator data set includes: detecting indicator data and removing duplicate records; detecting abnormal indicator data through statistical analysis and eliminating them; identifying missing indicator data and interpolating based on historical data; setting corresponding normalization rules according to the industry to which the investing entity belongs and the indicator characteristics, and normalizing the indicator values ​​to the interval [0, 1] using the Min-Max normalization method; setting corresponding weights for different normalized indicators, and smoothing time series indicators using the moving average method; and combining the weighted indicators into a multidimensional vector to form an indicator data set.

[0006] Optionally, the method for calculating the KCI index of the corresponding delivery subject based on each indicator data set includes: converting the indicator data corresponding to multiple delivery subjects into a decision matrix; constructing a weighted matrix based on different indicator data and corresponding weights; calculating the Euclidean distance between each delivery subject and the ideal solution and the negative ideal solution based on the weighted matrix; calculating the KCI index of the delivery subject, specifically: , in, is the Euclidean distance between the ith delivery entity and the negative ideal solution, is the Euclidean distance between the ith delivery entity and the ideal solution.

[0007] Optionally, the method for sorting multiple delivery entities based on the KCI index and completing the construction of a custom list of delivery entities includes: sorting the KCI indexes corresponding to the multiple delivery entities from large to small, with the first and last rankings representing that the indicator data of the corresponding delivery entity are the best and the worst, respectively; using the KCI indexes corresponding to delivery entities in different periods as sub-options of the custom list to enable viewing of the KCI indexes in different periods.

[0008] Optionally, the decision matrix R is: ; Among them, m is the number of investment entities, n is the number of indicators, is the corresponding matrix element The index of is the normalized value of the i-th investment entity on the j-th indicator; The weighting matrix V is: ; in, , is the weight of the jth indicator; Ideal solution for: ; Negative ideal solution for: ; The distance between the delivery subject and the ideal solution for: ; The distance between the launch subject and the negative ideal solution for: .

[0009] The present invention further discloses a system for constructing a custom list of delivery entities, including: a link parsing module, used to obtain content links of multiple delivery entities to obtain indicator data of corresponding delivery entities; a data processing module, used to perform data processing on the indicator data to obtain a standardized indicator data set; an index calculation module, used to calculate the KCI index of the corresponding delivery entity based on each indicator data set; and a list construction module, used to sort multiple delivery entities based on the KCI index and complete the construction of a custom list of delivery entities.

[0010] The present invention further discloses a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the method for constructing a custom list of a delivery subject is implemented.

[0011] The present invention further discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for constructing a custom list of delivery entities when executing the program.

[0012] The present invention further discloses a computer program product, including a computer program, which implements the above-mentioned method for constructing a custom list of delivery entities when executed by a processor.

[0013] According to the technical solution of the present invention, by automatically acquiring the multi-dimensional indicator data of the delivery subject, dynamically normalizing the data, and calculating the KCI index of the delivery subject based on multi-indicator weighted calculation, and combining the user's needs to generate personalized lists, the comprehensiveness and real-time nature of data collection are improved: the core indicator data of the delivery subject on multiple new media platforms is automatically acquired by parsing content links, which reduces manual operations and improves the efficiency and comprehensiveness of data updates. Enhance the fairness and industry adaptability of data processing: adopt a dynamic normalization processing method, introduce industry characteristics and time decay functions, overcome the impact of data scale differences and timeliness between different delivery subjects, and ensure that the evaluation results are more scientific and fair. Improve the accuracy of comprehensive value assessment: Calculate the KCI index of the delivery subject based on multi-indicator weighted calculation, quantify multi-dimensional indicators into a single comprehensive score, and provide more accurate value ranking and delivery recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] For the purpose of illustration and not limitation, the present invention is now described in conjunction with the embodiments of the present invention and the accompanying drawings, in which: Figure 1 It is a flowchart of a method for constructing a custom list of a delivery subject in an embodiment of the present invention; Figure 2 It is a structural diagram of a system for constructing a custom list of a delivery subject in an embodiment of the present invention; Figure 3 It is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0015] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the implementation mode of the present application will be clearly and completely described below in conjunction with the drawings in the implementation mode of the present application. Obviously, the described implementation mode is only a part of the implementation mode of the present application, not all the implementation modes. Based on the implementation mode in the present application, all other implementation modes obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application.

[0016] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0017] In the present application, the terms "upper", "lower", "left", "right", "front", "back", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings. These terms are mainly used to better describe the present application and its implementation methods, and are not used to limit the indicated devices, elements or components to have a specific orientation, or to be constructed and operated in a specific orientation.

[0018] In addition, some of the above terms may be used to express other meanings in addition to indicating orientation or positional relationship. For example, the term "on" may also be used to express a certain dependency or connection relationship in some cases. For those of ordinary skill in the art, the specific meanings of these terms in this application can be understood according to the specific circumstances. In addition, the term "plurality" should mean two or more than two.

[0019] It should be noted that, in the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other. The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0020] refer to Figure 1 This embodiment discloses a method for constructing a custom list of a delivery subject, the method comprising: S100: Obtain content links of multiple delivery entities to obtain indicator data of the corresponding delivery entities. Among them, the content link is a link to the content published by the delivery entity on a certain platform, which contains the complete data and interactive data of the content. In order to realize automatic crawling of the delivery entity, after knowing the delivery entity, multiple delivery entities and their corresponding content links are crawled through each API interface period to realize personalized acquisition of the content published by the delivery entity. For example, within a certain period of time, advertisers need to deliver, and if they want to obtain the best delivery period, they can select the delivery period according to the interactive data in the content captured in different periods. After obtaining the content link, the method further includes: Extract meta information from the content link to determine the indicator data in the content link. This embodiment shows a specific processing method as follows: Parse the content link: receive the content link of the new media delivery subject provided by the user, and extract the basic information of the link, such as domain name, path, query parameters, etc., through regular expressions, URL parsing libraries or platform open interfaces. For example, after obtaining the content link, identify the link platform and content type, that is, judge the platform (such as WeChat public account, Weibo, Douyin, etc.) and content type (such as article, video, live broadcast) to which the link belongs based on the domain name or specific parameter rules, and access the platform data interface or page based on the identified platform and content type. Use the information extracted from the link, call the open interface provided by the platform (such as WeChat public account article interface) or crawl the page to obtain meta information (must comply with the platform data acquisition rules). Meta information examples: article title, release time, author name; reading volume, likes, comments, sharing volume; video content playback volume, barrage volume, etc. Parse the obtained meta information into structured data to support subsequent data processing and analysis. Exemplary, indicator dimension example: number of published articles: by counting the number of links or parsing the release time of the content. Reading volume: extract the read_count field in the meta information. Likes: extract the like_count field in the meta information. Average number of views: calculate the average through multiple link data. Through the above steps, the multi-dimensional indicator data of the publisher can be efficiently extracted from the content link, providing a complete and reliable data foundation for subsequent normalization processing and KCI index calculation.

[0021] Statistics are performed on the indicator data determined in multiple cycles, and a similar content recommendation algorithm is used to predict whether there are any missing content links, and the user is prompted to review. This embodiment specifically illustrates a specific processing method, defining statistical cycles according to user needs, such as days, weeks, and months, and grouping indicator data by cycle. Indicator data includes: number of published articles, reading volume, number of likes, number of comments, etc. Example: Cycle A (the fourth week of November 2024): number of published articles = 7, total reading volume = 50,000; Cycle B (the first week of December 2024): number of published articles = 5, total reading volume = 42,000. Statistics are performed on the cumulative value, average value, and fluctuation of each cycle, and multi-cycle trend data is output: Cumulative value: the sum of the indicator in the cycle (such as the total reading volume). Average value: the average value of the indicator data (such as the average reading volume of a single article). Fluctuation: Calculate the rate of change or standard deviation between each cycle, and find abnormal fluctuations (such as a significant decrease in reading volume). For the acquired content links and their corresponding meta-information, extract features to construct feature vectors. Specifically, analyze the title, abstract, keywords, etc. (such as TF-IDF or word embedding model), and then use similar content recommendation algorithms (such as cosine similarity, deep learning model) to calculate the similarity between the acquired links and potential missing content. For example, input: the acquired content feature vector set {V1, V2, ..., Vn}; use the algorithm to retrieve other content link sets of the historical data platform or the delivery entity, and filter out links with high similarity but not acquired. This implementation takes the cosine similarity algorithm as an example. For example, if the similarity between a link and an acquired link is higher than a set threshold, but the link is not in the list of acquired links, it is determined to be a missing link. A candidate list is generated for the detected missing links, and is sorted by similarity score and displayed to the user to prompt the user to review. The user can choose to reload the confirmed missing links into the link data set according to needs for indicator data statistics.

[0022] Based on the statistical index data, the distributed database is stored to realize the platform and period retrieval of each delivery entity. That is, the user can retrieve the index data corresponding to the obtained content link according to the target platform or statistical period and obtain the results.

[0023] S200: Process the indicator data to obtain a standardized indicator data set. Specifically, perform data cleaning operations on the indicator data, including: duplicate value processing: detect and remove duplicate indicator data records. Detect and eliminate abnormal indicator data through statistical analysis: detect abnormal indicator values ​​through statistical analysis, and mark or eliminate data that exceeds a reasonable range. Identify missing indicator data and interpolate based on historical data: For missing indicator data, interpolate based on historical data or industry averages.

[0024] After data cleaning is completed, the corresponding normalization rules are set according to the industry to which the investment entity belongs and the indicator characteristics. This implementation example uses the Min-Max normalization method to normalize the indicator value to the [0, 1] interval. Specifically: , where x is the original indicator value, indicating the data value of a certain indicator of a specific delivery subject, X is the set of all delivery subjects corresponding to the indicator, min(X) is the minimum value in the set X, max(X) is the maximum value in the set X, and x normalized In one or more embodiments, after the index is normalized, the index value may be logarithmically transformed to reduce the difference in the index value, and then the smoothing formula average or weighted average may be used to reduce data volatility and improve the stability of the result.

[0025] Set corresponding weights for different normalized indicators, and use the moving average method to smooth the time series indicators. Set different weights for the indicator data of the delivery subject under different delivery platforms according to user needs. For example, on platform A, the weight of the indicator data reading volume is 0.4, the interaction rate is 0.3, the number of likes is 0.2, and the average number of views is 0.1. Further, the indicators after fusion of weights are combined into a multidimensional vector to form an indicator data set.

[0026] S300: Calculate the KCI index of the corresponding delivery subject based on each indicator data set. Specifically: convert the indicator data corresponding to multiple delivery subjects into a decision matrix, where the decision matrix R is: , where m is the number of entities that place orders, and n is the number of indicators. is the corresponding matrix element The index of is the normalized value of the i-th investment entity on the j-th indicator. A weighted matrix is ​​constructed based on different indicator data and corresponding weights, where the weighted matrix V is: ,in, , is the weight of the jth indicator.

[0027] Based on the weighted matrix, the Euclidean distance between each delivery entity and the ideal solution and the negative ideal solution is calculated. for: , negative ideal solution for: , thus, the distance between the launch subject and the ideal solution for: ; The distance between the launch subject and the negative ideal solution for: .

[0028] Finally, calculate the KCI index of the investment entity, specifically: , in, is the Euclidean distance between the ith delivery entity and the negative ideal solution, is the Euclidean distance between the ith delivery entity and the ideal solution.

[0029] S400: Sort multiple delivery entities based on the KCI index, and complete the construction of a custom list of delivery entities. This custom list provides the selection of statistical period parameters, and can count and sort the KCI index of each delivery entity according to daily, weekly, monthly and other periods. Specifically, the historical indicator data of each delivery entity in the corresponding database is automatically filtered and aggregated according to the selected period. For example, daily statistics: directly extract the data of the day from the database, weekly statistics: extract the data of the last 7 days, calculate the total or average, monthly statistics: extract the data of the last 30 days, and calculate the total or average. Based on this, users can also select data from different platforms for analysis. Through the data normalization and dynamic weight adjustment in this solution, the balance of data on each platform can be guaranteed. In order to meet the user's needs for specific indicator data, the sorting of the list can also introduce a mixed weight sorting method. For example, the user specifies the comprehensive sorting rules of a single indicator and the KCI index as follows: Among them, S i represents the comprehensive score, α and β are user-defined weights, and α+β=1, KCI i Represents the KCI index of the i-th publisher. This enables the generation of lists according to sorting rules, and displays the following content: publisher name; indicator data within the statistical period (such as number of posts, number of reads, number of likes, etc.); corresponding KCI index; specific value of a single indicator data (if the user selects "number of likes" sorting, the corresponding value will be displayed). Users can dynamically switch statistical periods, indicator dimensions or sorting rules, and can also intuitively display the performance of publishers in various dimensions through bar charts, pie charts or heat maps.

[0030] refer to Figure 2 This embodiment further discloses a system for constructing a custom list of a delivery subject, the system comprising: The link parsing module 21 is used to obtain content links of multiple delivery entities to obtain indicator data of the corresponding delivery entities; it is also used to capture multiple delivery entities and their corresponding content links through each API interface period; extract meta information from the content link to determine the indicator data in the content link; count the indicator data determined in multiple periods, and use a similar content recommendation algorithm to predict whether there are any missing content links, and prompt the user to review; based on the statistical indicator data, a distributed database is stored to achieve platform and period retrieval of each delivery entity.

[0031] The data processing module 22 is used to process the indicator data to obtain a standardized indicator data set; it is also used to detect the indicator data and remove duplicate records; detect abnormal indicator data through statistical analysis and eliminate them; identify missing indicator data and interpolate based on historical data; set corresponding normalization rules according to the industry to which the investment entity belongs and the indicator characteristics, and use the Min-Max normalization method to normalize the indicator value to the [0, 1] interval; set corresponding weights for different normalized indicators, and use the moving average method to smooth the time series indicators; combine the indicators after fusion of weights into a multidimensional vector to form an indicator data set.

[0032] The index calculation module 23 is used to calculate the KCI index of the corresponding delivery subject based on each indicator data set; it is also used to convert the indicator data corresponding to multiple delivery subjects into a decision matrix; construct a weighted matrix based on different indicator data and corresponding weights; calculate the Euclidean distance between each delivery subject and the ideal solution and the negative ideal solution based on the weighted matrix; calculate the KCI index of the delivery subject, specifically: ,in, is the Euclidean distance between the ith delivery entity and the negative ideal solution, is the Euclidean distance between the ith delivery entity and the ideal solution.

[0033] The list construction module 24 is used to sort multiple delivery entities based on the KCI index and complete the construction of a custom list of delivery entities; it is also used to sort the KCI indexes corresponding to the multiple delivery entities from large to small, with the first and last rankings representing that the indicator data of the corresponding delivery entity are the best and the worst respectively; the KCI indexes corresponding to delivery entities in different periods are used as sub-options of the custom list to realize the viewing of the KCI indexes in different periods.

[0034] Figure 3 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as Figure 3 As shown, the electronic device 50 includes: a processor 501 (processor), a memory 502 (memory) and a bus 503; The processor 501 and the memory 502 communicate with each other via the bus 503 ; the processor 501 is used to call program instructions in the memory 502 to execute the methods provided by the above-mentioned method implementation methods.

[0035] This embodiment provides a non-transitory computer-readable storage medium, which stores computer instructions. The computer instructions enable a computer to execute the methods provided by the above-mentioned method embodiments.

[0036] A person skilled in the art can understand that all or part of the steps for implementing the above-mentioned method implementation method can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium, which, when executed, executes the steps of the above-mentioned method implementation method; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, etc., various storage media that can store program codes.

[0037] The device implementation described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present implementation scheme. Those of ordinary skill in the art may understand and implement it without creative effort.

[0038] Through the description of the above implementation modes, those skilled in the art can clearly understand that each implementation mode can be implemented by means of software plus a necessary general hardware platform, or of course by hardware. Based on such an understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each implementation mode or some parts of the implementation mode.

[0039] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for constructing a custom list of a delivery entity, characterized in that: The method comprises: Obtain content links of multiple delivery entities to obtain indicator data of corresponding delivery entities; Performing data processing on the indicator data to obtain a standardized indicator data set; Calculate the KCI index of the corresponding investment entity based on each indicator data set; Sort multiple publishers based on the KCI index and build a custom list of publishers.

2. The method for constructing a custom list of a delivery entity according to claim 1, characterized in that: The method of obtaining content links of multiple delivery entities to obtain indicator data of corresponding delivery entities includes: Capture multiple delivery entities and their corresponding content links through each API interface cycle; Extracting meta information from content links to determine indicator data in the content links; Collect statistics on the indicator data determined in multiple periods, and use similar content recommendation algorithms to predict whether there are any missing content links, and prompt users to review; Distributed database storage is performed based on the statistical indicator data to achieve platform and periodic retrieval of each investment entity.

3. The method for constructing a custom list of a delivery entity according to claim 1, characterized in that: The method of performing data processing on the indicator data to obtain a standardized indicator data set includes: Detect indicator data and remove duplicate records; Detect and eliminate abnormal indicator data through statistical analysis; Identify missing indicator data and interpolate based on historical data; According to the industry to which the investment entity belongs and the characteristics of the indicator, the corresponding normalization rules are set, and the indicator value is normalized to the interval [0, 1] using the Min-Max normalization method; Set corresponding weights for different normalized indicators and use the moving average method to smooth the time series indicators; The weighted indicators are combined into a multi-dimensional vector to form an indicator data set.

4. The method for constructing a custom list of a delivery entity according to claim 3, characterized in that: The method for calculating the KCI index of the corresponding delivery subject based on each indicator data set includes: Convert the indicator data corresponding to multiple investment entities into a decision matrix; Construct a weighted matrix based on different indicator data and corresponding weights; Calculate the Euclidean distance between each delivery subject and the ideal solution and the negative ideal solution based on the weighted matrix; Calculate the KCI index of the investment entity, specifically: ， in, is the Euclidean distance between the ith delivery entity and the negative ideal solution, is the Euclidean distance between the ith delivery entity and the ideal solution.

5. The method for constructing a custom list of a delivery entity according to claim 1, characterized in that: The method for ranking multiple delivery entities based on the KCI index and completing the construction of a custom list of delivery entities includes: Sort the KCI indexes corresponding to multiple investment entities from large to small. The first and last rankings represent that the corresponding investment entity has the best and worst indicator data, respectively. The KCI index corresponding to the investment entities in different periods can be used as sub-options of the custom list to view the KCI index in different periods.

6. The method for constructing a custom list of a delivery entity according to claim 4, characterized in that: The decision matrix R is: ； Among them, m is the number of investment entities, n is the number of indicators, is the corresponding matrix element The index of is the normalized value of the i-th investment entity on the j-th indicator; The weighting matrix V is: ； in, , is the weight of the jth indicator; Ideal solution for: ; Negative ideal solution for: ; Euclidean distance between the delivery entity and the ideal solution for: ； Euclidean distance between the delivery subject and the negative ideal solution for: 。 7. A system for constructing a custom list of a delivery entity, characterized in that: include: A link parsing module is used to obtain content links of multiple delivery entities to obtain indicator data of corresponding delivery entities; A data processing module, used for performing data processing on the indicator data to obtain a standardized indicator data set; The index calculation module is used to calculate the KCI index of the corresponding investment entity based on each indicator data set; The list building module is used to sort multiple delivery entities based on the KCI index and complete the construction of a custom list of delivery entities.

8. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images