Derivative recommendation method and device for data indexes and medium

Abstract

The invention provides a derivative recommendation method and device for data indexes and a medium, relates to the technical field of software, and is used for solving the problem of how to obtain and display derivative data indexes meeting user requirements. The method comprises the following steps: obtaining the preference degree of a user for each original data index when the user uses software; obtaining a derivative data index according to the plurality of first original data indexes with the maximum preference degree; and recommending the derivative data indexes to use software of the user for display. According to the preference degree of the user for the original data indexes, the derivative data indexes which may be preferred by the user as well are obtained, the derivative data indexes are recommended to the software of the user to be displayed and used, in the process that the user uses the software, display of the software can be optimized according to the actual use condition of the user, and the user experience is improved. And the software can better meet the use requirements of the user.

Description

Technical Field

[0001] The present disclosure at least relates to the field of software technology, and in particular to a method for recommending a derivative of a data indicator, a device for recommending a derivative of a data indicator, and a computer-readable storage medium. Background Art

[0002] In industrial management systems, IoT equipment systems, and business BI (Business Intelligence) systems, data indicators are important components and are key measurement criteria for quantifying specific business performance. These indicators can help organizations understand the status of their operational efficiency, customer satisfaction, product performance, and other aspects, and can guide the decision-making process. However, for the above systems, because the business is constantly developing, it is often impossible to know in advance all the data indicators that users are concerned about. Therefore, how to create indicators that are closer to the business is an important and difficult task. Summary of the invention

[0003] The technical problem to be solved by the present disclosure is to provide a method for recommending a derivative of a data indicator, a device for recommending a derivative of a data indicator, and a computer-readable storage medium in response to the above-mentioned shortcomings, so as to solve the problem of how to obtain and display derivative data indicators that meet user needs.

[0004] In a first aspect, the present disclosure provides a method for deriving and recommending data indicators,

[0005] Methods include:

[0006] Obtain the user's preference for each raw data indicator when using the software;

[0007] Obtaining derived data indicators according to a plurality of first original data indicators with the largest preference;

[0008] The derived data indicators are recommended to the user's software for display.

[0009] Furthermore, the user's preference for each raw data indicator when using the software is obtained, including:

[0010] Acquire the usage parameters of each display interface of the software, the display position of each raw data indicator in each interface, and the display format of each raw data indicator during the use of the software by the user, wherein the usage parameters include at least one of usage operation, usage frequency, and usage duration;

[0011] According to the usage parameters and predefined usage parameter weight conversion rules, the usage weights of each display interface, each display position, and each display format of the software used by the user are obtained;

[0012] According to the display interface where each raw data indicator is located, the display position where it is located and the usage weights corresponding to each display format, the user's preference for each raw data indicator when using the software is obtained.

[0013] Furthermore, according to the usage parameters and the predefined usage parameter weight conversion rules, the usage weights of each display interface, each display position, and each display format of the software used by the user are obtained, specifically including:

[0014] Count the number of times users use each display interface, each display position, and each display format of the software;

[0015] Calculate the usage ratio of each display interface in all display interfaces of the software, the usage ratio of each display position in its own interface, and the usage ratio of each display format in all display formats of the corresponding original data;

[0016] According to each usage frequency ratio, the usage weight of each display interface, each display position, and each display format of the software used by the user is obtained.

[0017] Further, the derived data indicators are obtained according to the first original data indicators with the largest preference, specifically including:

[0018] Acquire a pre-collected combined data indicator from an indicator combination library, where the combined data indicator is composed based on a plurality of second original data indicators;

[0019] Get the top N original data indicators with the highest preference;

[0020] In response to a number of second original data indicators constituting a certain combined data indicator being located in the TopN first original data indicators, the certain combined data indicator is determined as a derived data indicator.

[0021] Furthermore, the derived data indicators are recommended to the user's software for display, specifically including:

[0022] Acquire each first data indicator of the software to be displayed to the user, each first data indicator at least including a first original data indicator and a derived data indicator;

[0023] Acquire first display layout parameters of each first data indicator in the software used by the user, where the display layout parameters include parameters characterizing the interface, position, and format of the display;

[0024] The user's usage software is controlled to display each first data indicator according to the first display layout parameter.

[0025] Further, obtaining first display layout parameters of each first data indicator in the software used by the user specifically includes:

[0026] Obtaining a user preference vector for each first data indicator, the user preference vector comprising a first usage weight for each first original data indicator and a second usage weight for the derived data indicator during the user's use of the software, the second usage weight being obtained according to a third usage weight of at least one of a plurality of second original data indicators constituting the derived data indicator;

[0027] Obtaining a display layout vector of a display solution to be selected, wherein the display layout vector includes parameters of an interface, a position, and a format of each first data indicator to be displayed in the user's software;

[0028] The similarity between the user preference vector and the display layout vector is obtained, and the parameters in the display layout vector with the greatest similarity are obtained as the first display layout parameters of each first data indicator in the software used by the user.

[0029] Further, obtaining the user preference vector of each first data indicator specifically includes:

[0030] Obtaining first usage weights corresponding to the interfaces, locations, and display formats of the first original data indicators;

[0031] Obtaining each third usage weight of a second original data indicator with the largest preference constituting the derived data indicator, and using the third usage weight as the second usage weight;

[0032] The first usage weight and the second usage weight are combined to obtain a user preference vector for each first data indicator.

[0033] Furthermore, obtaining a display layout vector of a display solution to be selected specifically includes:

[0034] Obtaining display weights defined for each display interface, each display position, and each display format of the software;

[0035] The display weights corresponding to the display interface, display position, and display format of each first data indicator in the display scheme to be selected are obtained, and combined into display layout vectors of each display scheme to be selected.

[0036] In a second aspect, the present disclosure provides a device for recommending derivatives of data indicators, the device comprising:

[0037] The preference module is used to obtain the user's preference for each raw data indicator when using the software;

[0038] A derivation module, connected to the preference module, for obtaining a derived data indicator according to a plurality of first original data indicators with the largest preference;

[0039] The recommendation module is connected with the derivative module and is used to recommend the derivative data indicators to the user's software for display.

[0040] In a third aspect, the present disclosure provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the method for deriving recommendations for data indicators as described above is implemented.

[0041] The present disclosure provides a method for recommending a derivative of a data indicator, a device for recommending a derivative of a data indicator, and a computer-readable storage medium. According to the user's preference for the original data indicator, the derivative data indicator that the user may also prefer is obtained, and the derivative data indicator is recommended to the user's software for display and use. During the user's use of the software, the display of the software can be optimized according to the user's actual usage, so that the software can better meet the user's usage needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a flow chart of a method for deriving and recommending data indicators according to an embodiment of the present disclosure;

[0043] Figure 2 is a flow chart of another method for deriving and recommending data indicators according to an embodiment of the present disclosure;

[0044] Figure 3 It is a system architecture diagram of a data indicator derivative recommendation device according to an embodiment of the present disclosure;

[0045] Figure 4 It is a structural diagram of a data indicator derivative recommendation device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0046] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, the embodiments of the present disclosure will be further described in detail below with reference to the accompanying drawings.

[0047] It should be understood that the specific embodiments and drawings described herein are only used to explain the present disclosure rather than to limit the present disclosure.

[0048] It can be understood that, in the absence of conflict, the various embodiments of the present disclosure and the various features in the embodiments can be combined with each other.

[0049] It can be understood that, for the convenience of description, the drawings of the present disclosure only show parts related to the present disclosure, while parts irrelevant to the present disclosure are not shown in the drawings.

[0050] It can be understood that each unit and module involved in the embodiments of the present disclosure may correspond to only one physical structure, or may be composed of multiple physical structures, or multiple units and modules may be integrated into one physical structure.

[0051] It will be understood that, in the absence of conflict, the functions and steps marked in the flowcharts and block diagrams of the present disclosure may occur in an order different from that marked in the drawings.

[0052] It is understood that the flowcharts and block diagrams of the present disclosure illustrate the possible architectures, functions, and operations of the systems, devices, equipment, and methods according to the various embodiments of the present disclosure. Each box in the flowchart or block diagram may represent a unit, module, program segment, or code, which contains executable instructions for implementing the specified functions. Moreover, each box or combination of boxes in the block diagram and flowchart may be implemented by a hardware-based system that implements the specified functions, or may be implemented by a combination of hardware and computer instructions.

[0053] It can be understood that the units and modules involved in the embodiments of the present disclosure can be implemented by software or hardware, for example, the units and modules can be located in a processor.

[0054] In order to facilitate understanding of the present disclosure, the main inventive concept of the present disclosure is first introduced.

[0055] The present invention discloses a method for self-creating derived data indicators based on a content recommendation system algorithm and an indicator combination library, which is mainly used for data indicator derivative recommendation in industrial management systems, Internet of Things equipment systems, and commercial BI systems.

[0056] In industrial software, data indicators are used to monitor production efficiency, equipment operation status, product quality, etc., including various key performance indicators (KPIs). Commercial BI software focuses more on indicators such as sales performance, customer behavior, and market trends. For example, equipment efficiency (OEE, Overall Equipment Effectiveness), mean time between failures (MTBF, Mean Time Between Failures), mean time to repair (MTTR, Mean Time To Failure), scrap rate, order fulfillment cycle, sales, customer acquisition cost (CAC, Customer Acquisition Cost), customer lifetime value (CLV, Customer Lifetime Value), website conversion rate, etc. are all commonly used data indicators. Reasonable data indicator design helps to quickly identify bottlenecks or problem areas in business processes. Through in-depth analysis of abnormal indicators, the root cause of the problem can be found and corresponding corrective measures can be taken.

[0057] Custom data indicators refer to data measurement standards created by users based on their specific needs and business scenarios. These indicators can be designed based on specific business goals or specific data sets to provide information that is more in line with the actual situation. They usually have the following characteristics: 1) Flexibility: They can be customized according to different business needs and goals. 2) Targeted: They directly reflect key issues in specific business scenarios. 3) In-depth analysis: They allow for more in-depth analysis and interpretation of data. 4) Dynamic adjustment: Indicators can be adjusted or updated at any time as the business changes. However, allowing users to customize data indicators requires users to understand the business situation and configure / develop indicators in a timely manner before they can be seen in subsequent use. This is costly and has a lag.

[0058] Therefore, the present disclosure provides a method for self-creating derived data indicators based on a content recommendation system algorithm and an indicator combination library. After collecting and storing data such as the composition of the software and the user's operating behavior (specific to the indicator granularity), the data is imported into the content recommendation system algorithm, and then the recommended content obtained from the recommendation algorithm is imported into the indicator combination library to match the indicator list, and then the final indicator list is displayed in modules such as the cockpit and data charts.

[0059] The method disclosed in the present invention can fix the time frequency of updating a data indicator according to business conditions, such as calculating it once a month (that is, the calculation basis is the user behavior data and module data indicator information of the most recent month), so as to achieve the purpose of rapid and automatic adjustment according to user habits and save time for customized research and development.

[0060] The content-based recommendation system algorithm (Content-Based Filtering) adopted in this disclosure is a personalized recommendation technology. Its core principle is to use the user's past behavior and interests as well as data indicator characteristics to perform similarity matching, so as to recommend items that are similar to their preferences or have the same attribute characteristics to users. The specific algorithm process includes the following steps:

[0061] 1) Feature Extraction:

[0062] Conduct content analysis on each data indicator to be recommended and extract key feature information. These features can be keywords, tags, categories, and other data in the text description that can reflect the characteristics of the data indicator.

[0063] 2) User Preference Calculation (User Profile Construction):

[0064] Based on the user's historical behavior records (such as browsing, clicking, and collecting), the user's personal interest model or preference profile is constructed. For each user, the system will assign a corresponding preference score to each feature dimension to quantify the user's preference degree under different features.

[0065] 3) Similarity Computation:

[0066] The similarity between the user profile and all candidate data indicators is calculated using a specific similarity measurement method (such as cosine similarity, Euclidean distance, Pearson correlation coefficient, etc.). Cosine similarity is a commonly used calculation method, which measures their similarity by representing the features of users and items as vectors and calculating the cosine value of the angle between the two vectors.

[0067]

[0068] 4) Recommendation Generation:

[0069] According to the above similarity calculation results, find the items (data indicators) that best match the user's interests and have the highest similarity as the recommendation results. Generally speaking, the recommendation list will be sorted from high to low according to the similarity, and the most relevant items will be displayed to the user first.

[0070] Content-based recommendation systems do not need to rely on the behavioral data of a large number of user groups, but focus on the personalized needs of individual users. Therefore, in some scenarios, especially for new users or sparse data, they can also provide relatively accurate recommendations. At the same time, the algorithm has a certain effect on alleviating the cold start problem, because it can infer the user's interest characteristics from the limited behavioral data of a single user.

[0071] The present disclosure comprehensively refers to various behaviors of users operating software and the characteristics of each data indicator, and is analogous to a content-based recommendation system of a search engine for browsing web pages. When outputting an indicator list, it not only considers a single output data indicator, but also automatically derives combined data indicators through an indicator combination library.

[0072] The present disclosure adopts a content-based recommendation system algorithm module to dynamically adjust the displayed data indicators, and the basis of the adjustment is generated by the user's behavioral operations. Therefore, it can flexibly adjust the data indicators that are closely aligned with the actual business situation according to the user's usage habits, thereby better adapting to business needs.

[0073] Based on the above inventive concept, specific embodiments are provided below.

[0074] Embodiment 1:

[0075] like Figure 1 As shown, the present disclosure provides a method for deriving and recommending data indicators, the method comprising:

[0076] S1. Obtain the user's preference for each raw data indicator when using the software;

[0077] S2. Obtaining a derived data index according to a plurality of first original data indexes with the largest preference;

[0078] S3. Recommend the derived data indicators to the user's software for display.

[0079] In this embodiment, a derivative recommendation method for data indicators obtains derivative data indicators that the user may also prefer based on the user's preference for the original data indicators, and recommends the derivative data indicators to the user's software for display and use. During the user's use of the software, the display of the software can be optimized based on the user's actual usage, so that the software can better meet the user's usage needs.

[0080] In one implementation, S1, obtaining the user's preference for each raw data indicator when using the software, specifically includes:

[0081] Acquire the usage parameters of each display interface of the software, the display position of each raw data indicator in each interface, and the display format of each raw data indicator during the use of the software by the user, wherein the usage parameters include at least one of usage operation, usage frequency, and usage duration;

[0082] According to the usage parameters and predefined usage parameter weight conversion rules, the usage weights of each display interface, each display position, and each display format of the software used by the user are obtained;

[0083] According to the display interface where each raw data indicator is located, the display position where it is located and the usage weights corresponding to each display format, the user's preference for each raw data indicator when using the software is obtained.

[0084] In this embodiment, it is assumed that the current software has the functions / modules shown in Table 1 below, wherein the functions / modules correspond to the display interfaces of the software, and the data indicators contained therein are displayed on the corresponding interfaces, which is equivalent to having a designed display position on the corresponding interfaces. The data may have multiple display formats, such as quantity format, percentage format, etc. If a data can be represented in multiple formats at the same time, then it is necessary to count which format the user prefers. The specific method for obtaining user preference data can be, for example, using parameters including use operation a1, use frequency a2, and use duration a3. If the user performs a write operation on a data indicator, a1=1, if only browses, a1=0.7, if browses and collects, a1=0.8, if browses, collects and downloads, a1=0.9, etc.; the use weight of the data indicator can be a1*a2*a3; similarly, if the data indicator includes two representation modes, numerical and percentage, respectively obtain their use weights, and for the interface where the indicator is located, count the number of times the user enters the interface, the length of stay, etc., to obtain the user's preference for using the interface. The final preference degree can be obtained by combining these three preferences.

[0085] Table 1 Example of functions / modules of a certain software

[0086]

[0087] In one embodiment, according to the usage parameters and the predefined usage parameter weight conversion rules, the usage weights of each display interface, each display position, and each display format of the software used by the user are obtained, specifically including:

[0088] Count the number of times users use each display interface, each display position, and each display format of the software;

[0089] Calculate the usage ratio of each display interface in all display interfaces of the software, the usage ratio of each display position in its own interface, and the usage ratio of each display format in all display formats of the corresponding original data;

[0090] According to each usage frequency ratio, the usage weight of each display interface, each display position, and each display format of the software used by the user is obtained.

[0091] In this embodiment, an example of user preference calculation is as follows:

[0092] The preference is calculated based on the user's operation behavior. For example, the preference is obtained based on the number of user clicks and the ranking, as shown in the following Table 2-4:

[0093] Table 2 Examples of user preferences for each display interface

[0094] Modules Total clicks Preference Overview 100 1 Production Scheduling 80 0.8 Production quality inspection 70 0.7 ...(More) ... ..

[0095] Table 3 Examples of user preferences for various display positions

[0096] Classification Total clicks Preference Production tasks 100 1 Product Quality 80 0.8 ...(More) ... ..

[0097] Table 4 Examples of user preferences for each display format

[0098] Indicator Type Total clicks Preference percentage 100 1 quantity 70 0.7 ...(More) ... ..

[0099] In one implementation, S2, obtaining a derived data indicator according to a plurality of first original data indicators with the largest preference, specifically includes:

[0100] Acquire a pre-collected combined data indicator from an indicator combination library, where the combined data indicator is composed based on a plurality of second original data indicators;

[0101] Get the top N original data indicators with the highest preference;

[0102] In response to a number of second original data indicators constituting a certain combined data indicator being located in the TopN first original data indicators, the certain combined data indicator is determined as a derived data indicator.

[0103] In this embodiment, the method of obtaining derived data indicators through the data indicator combination library is to obtain the data indicator sorting input combination library from the preference sorting. Assuming that the indicators obtained are the number of qualified products and the number of produced products are relatively high (for example, TOP10 is defined as desirable according to business conditions), and the indicator combination library has a new indicator yield rate = number of qualified products / number of produced products, then the data indicator of yield rate will be created at this time and displayed on the corresponding homepage / cockpit.

[0104] In one embodiment, S3, recommending the derived data indicator to the user's software for display, specifically includes:

[0105] Acquire each first data indicator of the software to be displayed to the user, each first data indicator at least including a first original data indicator and a derived data indicator;

[0106] Acquire first display layout parameters of each first data indicator in the software used by the user, where the display layout parameters include parameters characterizing the interface, position, and format of the display;

[0107] The user's usage software is controlled to display each first data indicator according to the first display layout parameter.

[0108] In this embodiment, a method for self-creating derived data indicators based on a content recommendation system algorithm and an indicator combination library is provided. After collecting and storing data such as the composition of the software and the user's operating behavior (specific to the indicator granularity), the data is imported into the content recommendation system algorithm, and then the recommended content obtained from the recommendation algorithm is imported into the indicator combination library to match the indicator list, and then the final indicator list is displayed in the cockpit, data chart and other modules. The overall logic is as follows: Figure 2 As shown, including:

[0109] 1) The system itself has a default homepage or cockpit interface, statistical analysis and other modules. These modules are composed of data indicator boards, line charts, bar charts, pie charts, tables and other elements. Each element contains data indicators (these indicators are basic data indicators by default).

[0110] 2) Collect various behaviors of the software users (multiple people under the same software if it is private, or multiple users of the same account if it is public) using the software, including browsing, clicking, collecting, etc.

[0111] 3) Input behavioral data, system module and other parameters into the content recommendation algorithm.

[0112] 4) The results obtained by the content recommendation algorithm are used to obtain the recommended new data indicators through the indicator combination library.

[0113] 5) According to the recommended new data indicators, the data indicators of the original cockpit are replaced, or the original cockpit remains unchanged, but there is a new cockpit, and the data indicators contained in the new cockpit are the recommended new data indicators.

[0114] In one embodiment, obtaining the first display layout parameters of each first data indicator in the software used by the user specifically includes:

[0115] Obtaining a user preference vector for each first data indicator, the user preference vector comprising a first usage weight for each first original data indicator and a second usage weight for the derived data indicator during the user's use of the software, the second usage weight being obtained according to a third usage weight of at least one of a plurality of second original data indicators constituting the derived data indicator;

[0116] Obtaining a display layout vector of a display solution to be selected, wherein the display layout vector includes parameters of an interface, a position, and a format of each first data indicator to be displayed in the user's software;

[0117] The similarity between the user preference vector and the display layout vector is obtained, and the parameters in the display layout vector with the greatest similarity are obtained as the first display layout parameters of each first data indicator in the software used by the user.

[0118] In this embodiment, the content-based recommendation system algorithm usually needs to calculate the similarity between user preferences and items to be recommended. The most commonly used is the cosine similarity based on the feature vector. Therefore, two corresponding feature vectors are formed, the user preference vector and the display layout vector. The user preference vector represents the user's preference for each data indicator to be recommended, and the display layout vector represents the display characteristics of each data indicator in the display scheme to be recommended. The maximum similarity between the two is calculated to obtain the typesetting and display method of the data indicators that best suits the user's usage habits.

[0119] Similarity calculation, there are similarity methods based on Pearson correlation coefficient, Jaccard, etc., and there are also some other methods:

[0120] 1) Matching based on statistical information:

[0121] Bag-of-words model and TF-IDF: In scenarios with rich text content, the bag-of-words model and TF-IDF (TermFrequency-Inverse Document Frequency) can be used to quantify the similarity of text content. The bag-of-words model ignores the order of words and only focuses on the frequency of word occurrence; TF-IDF further considers the importance of words in the entire document, reduces the influence of common words, and highlights unique words related to the topic.

[0122] 2) Models based on machine learning:

[0123] Naive Bayes classifier: Based on the user’s preference history for the feature labels of items (such as the type of movie, actors, directors, etc.), a Naive Bayes model is constructed to predict the probability of the user’s preference for new items.

[0124] Decision tree or random forest: By building a decision tree or integrating multiple decision trees (such as random forest), recursive division is performed based on the characteristic attributes of users and items to predict users' preferences for items.

[0125] In terms of the indicator combination library, you can also automatically combine various indicators (but the derived indicators combined in this way may not be logical). For example, if the indicator combination library has original indicators A and B, you can directly add derived indicators A+B, A / B, etc. to the combination library.

[0126] In one implementation, obtaining a user preference vector for each first data indicator specifically includes:

[0127] Obtaining first usage weights corresponding to the interfaces, locations, and display formats of the first original data indicators;

[0128] Obtaining each third usage weight of a second original data indicator with the largest preference constituting the derived data indicator, and using the third usage weight as the second usage weight;

[0129] The first usage weight and the second usage weight are combined to obtain a user preference vector for each first data indicator.

[0130] In this embodiment, after obtaining the multi-dimensional user preference data as shown in Tables 2-4, these preference degrees can be organized into a user preference vector, where the user preference vector of the derived data indicator can be determined based on its basic data indicator, such as the example of yield rate = number of qualified products / number of produced products. If the user often checks the number of qualified products, the yield rate can be displayed after the number of qualified products.

[0131] In one implementation, obtaining a display layout vector of a display solution to be selected specifically includes:

[0132] Obtaining display weights defined for each display interface, each display position, and each display format of the software;

[0133] The display weights corresponding to the display interface, display position, and display format of each first data indicator in the display scheme to be selected are obtained, and combined into display layout vectors of each display scheme to be selected.

[0134] In this embodiment, the characteristics of the data indicator represent its display layout, so the display layout vector of the selected display scheme can be obtained according to the display layout of the data indicator. For example, the characteristics of each data indicator are: module (such as overview, production scheduling, etc.), classification (such as product quality, production task, etc.), indicator type (such as quantity, percentage, etc.), so the characteristic vector of the data indicator is: M: (overview, production scheduling,..., product quality, production task,..., quantity, percentage,...), for example, the characteristics of the number of qualified products are overview, product quality, and quantity, that is, the vectors corresponding to the overview, product quality, and quantity are 1, so M=(1,0,0,...,1,0,...,1,0,0...).

[0135] Based on the data in Table 2-4 and the above data, the specific method for calculating the similarity of data indicators, such as calculating the similarity between the number of qualified products of the candidate data indicators of the user and solution A, is:

[0136]

[0137] In this way, the similarity of all data indicators can be calculated. If they are sorted from large to small according to similarity, the data indicator arrangement scheme with the highest score is selected as the output result.

[0138] A more specific example is Figure 3 As shown:

[0139] On the technical side, it can be implemented on different mobile phones and other terminals, different systems such as Apple or Android, different APPs (applications) such as WeChat, and it can also be implemented on a PC (personal computer).

[0140] The basic technical architecture for implementing this solution includes the following parts:

[0141] 1) Client, including PC and mobile (Apple, Android, etc.), the account browses, clicks, collects and performs other operations on the client.

[0142] 2) The server stores data, including user usage behavior data, module (including corresponding indicators) content data, and feature vector data of each data indicator.

[0143] 3) The content-based recommendation system algorithm module uses the recommendation algorithm to calculate the similarity between each data indicator and each user (of course including the preference calculated before calculating the similarity) based on the data in 2).

[0144] 4) The indicator combination library stores the original indicators and derived indicators, and matches the indicator results obtained in 3) to all the original indicators and derived indicators.

[0145] 5) Display module, based on the recommended original indicators and derived indicators.

[0146] The process of implementing this solution includes the following steps:

[0147] Step 1: On the client, the user logs in to the account and performs various operations on the client, such as browsing the cockpit and analyzing the contents of the statistical analysis module.

[0148] Step 2: The client obtains the user behavior and configuration information module get_user_mode, which mainly records the user's usage operations on the client (including browsing, collecting, clicking, etc.).

[0149] Step 3, the server get_user_data, including behavioral operation data, detailed information of each software module and data indicator content (such as module classification, included data indicator name, content, etc.), and characteristic data of each data indicator.

[0150] Step 4, the content-based recommendation system algorithm module analysis_mode, after inputting the parameters of step 3 into the recommendation system algorithm model, obtains the similarity of each user's preference for each data indicator, and outputs a list of recommended data indicators.

[0151] Step 5, the indicator combination library matches the data indicator Match_mode, and matches the corresponding indicator of the indicator library according to the recommended data indicator list in step 4. This indicator combination library can add custom indicators according to the business, and can also be updated by adding industry indicators learned on the network.

[0152] Step 6, the decision support display module Decision_support, adjusts the data indicator display of the homepage / cockpit and statistical analysis module according to the list of recommended content.

[0153] Embodiment 2:

[0154] like Figure 4 As shown, the present disclosure provides a data indicator derivative recommendation device, the device comprising:

[0155] Preference module 1, used to obtain the user's preference for each raw data indicator when using the software;

[0156] Derivation module 2, connected to preference module 1, for obtaining derived data indicators according to a plurality of first original data indicators with the greatest preference;

[0157] The recommendation module 3 is connected to the derivation module 2 and is used to recommend the derived data indicators to the user's software for display.

[0158] In one embodiment, the preference module 1 specifically includes:

[0159] A usage parameter acquisition unit is used to acquire usage parameters of each display interface of the software, the display position of each raw data indicator in each interface, and the display format of each raw data indicator during the use of the software by the user, wherein the usage parameters include at least one of usage operation, usage frequency, and usage duration;

[0160] A usage weight conversion unit, connected to the usage parameter acquisition unit, is used to obtain the usage weight of each display interface, each display position, and each display format of the user's use of the software according to the usage parameters and a predefined usage parameter weight conversion rule;

[0161] The preference acquisition unit is connected to the usage weight conversion unit and is used to obtain the user's preference for each original data indicator when using the software according to the display interface, display position and usage weights corresponding to each display format of each original data indicator.

[0162] In one embodiment, a weight conversion unit is used, specifically including:

[0163] A statistics unit, used to count the number of times a user uses each display interface, each display position, and each display format of the software;

[0164] A ratio calculation unit, connected to the statistical unit, for respectively calculating the usage ratio of each display interface in all display interfaces of the software, the usage ratio of each display position in its own interface, and the usage ratio of each display format in all display formats of the corresponding original data;

[0165] The usage weight acquisition unit is connected to the ratio calculation unit and is used to acquire the usage weight of each display interface, each display position, and each display format of the user's use of the software according to each usage frequency ratio.

[0166] In one embodiment, the derivative module 2 specifically includes:

[0167] An indicator reading unit, used for acquiring pre-collected combined data indicators from an indicator combination library, where the combined data indicators are composed based on a plurality of second original data indicators;

[0168] An indicator sorting unit is used to obtain the first original data indicators with the highest preference of TopN;

[0169] The indicator comparison unit is connected to the indicator reading unit and the indicator sorting unit, and is used to determine a certain combined data indicator as a derived data indicator in response to a number of second original data indicators constituting a certain combined data indicator being located in the TopN first original data indicators.

[0170] In one embodiment, the recommendation module 3 specifically includes:

[0171] The to-be-displayed indicator unit is used to obtain each first data indicator of the software to be displayed to the user, each first data indicator at least including a first original data indicator and a derived data indicator;

[0172] The to-be-displayed layout unit is connected to the to-be-displayed indicator unit and is used to obtain first display layout parameters of each first data indicator in the user's software, where the display layout parameters include parameters characterizing the display interface, position, and format;

[0173] The display control unit is connected to the layout unit to be displayed, and is used to control the user's usage software to display each first data indicator according to the first display layout parameter.

[0174] In one implementation, the layout unit to be displayed specifically includes:

[0175] A first vector unit is used to obtain a user preference vector for each first data indicator, the user preference vector includes a first usage weight for each first original data indicator and a second usage weight for the derived data indicator during the user's use of the software, the second usage weight is obtained according to a third usage weight of at least one of the plurality of second original data indicators constituting the derived data indicator;

[0176] A second vector unit is used to obtain a display layout vector of a display solution to be selected, wherein the display layout vector includes parameters of an interface, a position, and a format of each first data indicator to be displayed in the user's software;

[0177] The layout determination unit is connected to the first vector unit and the second vector unit, and is used to obtain the similarity between the user preference vector and the display layout vector, and obtain the parameters in the display layout vector with the greatest similarity as the first display layout parameters of each first data indicator in the user's software.

[0178] In one implementation, the first vector unit specifically includes:

[0179] A first usage weight acquisition unit to be displayed, used for acquiring each first usage weight corresponding to the interface, location and display format of each first original data indicator;

[0180] A second usage weight acquisition unit to be displayed is used to acquire the third usage weights of a second original data indicator with the greatest preference constituting the derived data indicator, and use the third usage weight as the second usage weight;

[0181] The first vector combining unit is connected to the first usage weight obtaining unit to be displayed and the second usage weight obtaining unit to be displayed, and is used to combine the first usage weight and the second usage weight to obtain the user preference vector of each first data indicator.

[0182] In one implementation, the second vector unit specifically includes:

[0183] A display weight definition unit, used to obtain display weights defined for each display interface, each display position, and each display format of the software;

[0184] The second vector combination unit is connected to the display weight definition unit, and is used to obtain the display weights corresponding to the display interface, display position, and display format of each first data indicator in the display scheme to be selected, and combine them into display layout vectors of each display scheme to be selected.

[0185] Embodiment 3:

[0186] Embodiment 3 of the present disclosure provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the method for deriving recommendation of data indicators as described in Embodiment 1 is implemented, or the device for deriving recommendation of data indicators as described in Embodiment 2 is implemented.

[0187] The computer-readable storage medium includes volatile or non-volatile, removable or non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, computer program modules or other data). Computer-readable storage media include, but are not limited to, RAM (Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable read only memory), flash memory or other memory technology, CD-ROM (Compact Disc Read-Only Memory), digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer.

[0188] In addition, the present disclosure may also provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes the method for deriving recommendations for data indicators as described in Example 1. The computer device may be a device for deriving recommendations for data indicators as described in Example 2.

[0189] The memory is connected to the processor, the memory may be a flash memory or a read-only memory or other memory, and the processor may be a central processing unit or a single-chip microcomputer.

[0190] Embodiments 1-3 of the present disclosure provide a method for recommending a derivative of a data indicator, a device for recommending a derivative of a data indicator, and a computer-readable storage medium. By obtaining derivative data indicators that the user may also prefer based on the user's preference for the original data indicator, and recommending the derivative data indicators to the user's software for display and use, during the user's use of the software, the display of the software can be optimized based on the user's actual usage, so that the software can better meet the user's usage needs.

[0191] The present disclosure can be applied to the cockpit and data analysis module of the Internet of Things business platform. The business platform is the business analysis platform of the Internet of Things, which has many data indicators. Therefore, creating applicable indicators can better assist the business in business analysis. In addition, it can also be applied to industrial management or Internet of Things equipment management platform, because the equipment management platform has more intelligent data indicators based on the object model.

[0192] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present disclosure, but the present disclosure is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and substance of the present disclosure, and these modifications and improvements are also considered to be within the scope of protection of the present disclosure.

Claims

1. A method for recommending derivatives of data indicators, characterized in that: The method comprises: Obtain the user's preference for each raw data indicator when using the software; Obtaining derived data indicators according to a plurality of first original data indicators with the largest preference; The derived data indicators are recommended to the user's software for display.

2. The method according to claim 1, characterized in that: Obtain the user's preference for each raw data indicator when using the software, including: Acquire the usage parameters of each display interface of the software, the display position of each raw data indicator in each interface, and the display format of each raw data indicator during the use of the software by the user, wherein the usage parameters include at least one of usage operation, usage frequency, and usage duration; According to the usage parameters and predefined usage parameter weight conversion rules, the usage weights of each display interface, each display position, and each display format of the software used by the user are obtained; According to the display interface where each raw data indicator is located, the display position where it is located and the usage weights corresponding to each display format, the user's preference for each raw data indicator when using the software is obtained.

3. The method according to claim 2, characterized in that According to the usage parameters and the predefined usage parameter weight conversion rules, the usage weights of each display interface, each display position, and each display format of the software used by the user are obtained, specifically including: Count the number of times users use each display interface, each display position, and each display format of the software; Calculate the usage ratio of each display interface in all display interfaces of the software, the usage ratio of each display position in its own interface, and the usage ratio of each display format in all display formats of the corresponding original data; According to each usage frequency ratio, the usage weight of each display interface, each display position, and each display format of the software used by the user is obtained.

4. The method according to any one of claims 2 to 3, characterized in that: The derived data indicators are obtained according to the first original data indicators with the largest preference, including: Acquire a pre-collected combined data indicator from an indicator combination library, where the combined data indicator is composed based on a plurality of second original data indicators; Get the top N original data indicators with the highest preference; In response to a number of second original data indicators constituting a certain combined data indicator being located in the TopN first original data indicators, the certain combined data indicator is determined as a derived data indicator.

5. The method according to claim 4, characterized in that Recommend the derived data indicators to the user's software for display, including: Acquire each first data indicator of the software to be displayed to the user, each first data indicator at least including a first original data indicator and a derived data indicator; Acquire first display layout parameters of each first data indicator in the software used by the user, where the display layout parameters include parameters characterizing the interface, position, and format of the display; The user's usage software is controlled to display each first data indicator according to the first display layout parameter.

6. The method according to claim 5, characterized in that Acquiring first display layout parameters of each first data indicator in the software used by the user specifically includes: Obtaining a user preference vector for each first data indicator, the user preference vector comprising a first usage weight for each first original data indicator and a second usage weight for the derived data indicator during the user's use of the software, the second usage weight being obtained according to a third usage weight of at least one of a plurality of second original data indicators constituting the derived data indicator; Obtaining a display layout vector of a display solution to be selected, wherein the display layout vector includes parameters of an interface, a position, and a format of each first data indicator to be displayed in the user's software; The similarity between the user preference vector and the display layout vector is obtained, and the parameters in the display layout vector with the greatest similarity are obtained as the first display layout parameters of each first data indicator in the software used by the user.

7. The method according to claim 6, characterized in that Obtaining the user preference vector of each first data indicator specifically includes: Obtaining first usage weights corresponding to the interfaces, locations, and display formats of the first original data indicators; Obtaining each third usage weight of a second original data indicator with the largest preference constituting the derived data indicator, and using the third usage weight as the second usage weight; The first usage weight and the second usage weight are combined to obtain a user preference vector for each first data indicator.

8. The method according to claim 6, characterized in that Obtain the display layout vector of the display scheme to be selected, including: Obtaining display weights defined for each display interface, each display position, and each display format of the software; The display weights corresponding to the display interface, display position, and display format of each first data indicator in the display scheme to be selected are obtained, and combined into display layout vectors of each display scheme to be selected.

9. A data indicator derivative recommendation device, characterized in that: The device comprises: The preference module is used to obtain the user's preference for each raw data indicator when using the software; A derivation module, connected to the preference module, for obtaining a derived data indicator according to a plurality of first original data indicators with the largest preference; The recommendation module is connected with the derivative module and is used to recommend the derivative data indicators to the user's software for display.

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

Images