List item adjustment method and device, electronic equipment and storage medium

Abstract

The invention discloses a list item adjustment method and device, electronic equipment and a storage medium, and the method comprises the steps: collecting the operation data of a plurality of accounts on a list item, and carrying out the clustering of the operation data; constructing a random forest model based on a clustering result; wherein the random forest model comprises a plurality of decision trees corresponding to a plurality of categories; inputting operation data of a current login account and a candidate list item into the random forest model to determine a first importance degree score of the candidate list item; target list items with the first importance degree scores larger than a preset value are determined in the candidate list items, the target list items are sorted according to the first importance degree scores from large to small, and the target list items are displayed according to a sorting result. According to the method and the device, the list items can be automatically adjusted for different accounts, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and more specifically, to a list item adjustment method, device, electronic device, and storage medium. Background Art

[0002] With the rapid development of software development and the rapid increase of software accounts, the demand for server management software has also shown different tendencies. For example, for the list page in the software, different accounts have different focuses. For example, bank accounts may focus more on health status, alarm status, etc., while game accounts may focus more on business ownership, resource ownership, etc.

[0003] Therefore, how to adjust list items for different accounts is a technical problem that those skilled in the art need to solve. Summary of the invention

[0004] The purpose of the present application is to provide a list item adjustment method, device and equipment, storage medium and computer program product, which can realize automatic adjustment of list items for different accounts and improve user experience.

[0005] To achieve the above objectives, the present application provides a list item adjustment method, comprising:

[0006] Collecting operation data of multiple accounts on list items, and clustering the operation data;

[0007] Constructing a random forest model based on the clustering results; wherein the random forest model includes multiple decision trees corresponding to multiple categories;

[0008] Inputting the operation data of the current login account and the candidate list items into the random forest model to determine the first importance score of the candidate list items;

[0009] Determine target list items whose first importance scores are greater than a preset value from the candidate list items, sort the target list items from large to small according to the first importance scores, and display the target list items according to the sorting result.

[0010] The operation data includes any one or a combination of any two of the following: a list item corresponding to the mouse hovering position, a search field, a click list sorting field, and an edit field.

[0011] The step of clustering the operation data includes:

[0012] Select the operation data corresponding to accounts of different role types, and use the operation data corresponding to accounts of different role types as cluster centers respectively;

[0013] Classifying the other operation data into corresponding categories based on the distance between the other operation data and the cluster center;

[0014] Re-determine the cluster center based on all the operation data in each category, and re-enter the step of dividing the other operation data into corresponding categories based on the distance between the other operation data and the cluster center, until the operation data included in all categories no longer changes, and determine the operation data included in each category.

[0015] Wherein, re-determining the cluster center according to all the operation data in each category includes:

[0016] The mean of all operation data in each category is calculated, and the mean of all operation data in each category is re-determined as the cluster center of the corresponding category.

[0017] Among them, it also includes:

[0018] In the process of constructing the random forest model, the optimal splitting point of the decision tree is selected according to the Gini coefficient.

[0019] Among them, it also includes:

[0020] Determine a second importance score of the candidate list item according to the number of times the candidate list item appears in the operation data of the current login account; wherein the second importance score is positively correlated with the number of times the candidate list item appears;

[0021] Accordingly, determining target list items whose first importance scores are greater than a preset value from the candidate list items, sorting the target list items from large to small according to the first importance scores, and displaying the target list items according to the sorting results, includes:

[0022] Assigning a first weight coefficient to the first importance score and assigning a second weight coefficient to the second importance score;

[0023] Calculate a first product of a first importance score of the candidate list item and the first weight coefficient, and calculate a second product of a second importance score of the candidate list item and the second weight coefficient;

[0024] Calculating a sum of the first product and the second product as an importance score of the candidate list item;

[0025] Determine target list items whose importance scores are greater than a preset value from the candidate list items, sort the target list items from large to small according to the importance scores, and display the target list items according to the sorting result.

[0026] After sorting the target list items according to the importance scores from large to small, the method further includes:

[0027] Determine the associated list items of the target list item according to the association rule;

[0028] Inserting the associated list item of the target list item into the next position of the corresponding target list item in the sorting result;

[0029] Accordingly, the target list items are displayed according to the sorting result, including:

[0030] The target list items and the corresponding associated list items are displayed according to the sorting result.

[0031] To achieve the above objectives, the present application provides a list item adjustment device, comprising:

[0032] A clustering unit, used to collect operation data of multiple accounts on list items and cluster the operation data;

[0033] A construction module is used to construct a random forest model based on the clustering results; wherein the random forest model includes multiple decision trees corresponding to multiple categories;

[0034] A first determining unit, configured to input the operation data of the current login account and the candidate list item into the random forest model to determine a first importance score of the candidate list item;

[0035] The sorting unit is used to determine the target list items whose first importance scores are greater than a preset value in the candidate list items, sort the target list items from large to small according to the first importance scores, and display the target list items according to the sorting results.

[0036] To achieve the above objectives, the present application provides an electronic device, including:

[0037] Memory for storing computer programs;

[0038] A processor is used to implement the steps of the above-mentioned list item adjustment method when executing the computer program.

[0039] To achieve the above-mentioned purpose, the present application provides a non-volatile storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned list item adjustment method are implemented.

[0040] It can be seen from the above scheme that a list item adjustment method provided by the present application includes: collecting operation data of multiple accounts on list items, and clustering the operation data; constructing a random forest model based on the clustering results; wherein the random forest model includes multiple decision trees corresponding to multiple categories; inputting the operation data of the currently logged-in account and the candidate list items into the random forest model to determine the first importance score of the candidate list item; determining the target list item whose first importance score is greater than a preset value among the candidate list items, sorting the target list items from large to small according to the first importance score, and displaying the target list items according to the sorting result.

[0041] The list item adjustment method provided by the present application collects the operation data of the account, automatically adjusts the specific list items displayed and the display order of the list items according to the behavior preference of the account, displays the list items that the user is most concerned about in the most obvious position, realizes the automatic adjustment of list items for different accounts, and improves the user experience. The present application also discloses a list item adjustment device, an electronic device, and a non-volatile storage medium, which can also achieve the above technical effects.

[0042] It should be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. The drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific implementation methods, they are used to explain the present disclosure, but do not constitute a limitation to the present disclosure. In the drawings:

[0044] Figure 1 is a flowchart of a method for adjusting list items according to an exemplary embodiment;

[0045] Figure 2 is a flowchart of another list item adjustment method according to an exemplary embodiment;

[0046] Figure 3 A structural diagram of a server in an application embodiment provided by this application;

[0047] Figure 4 A workflow diagram of a collection module in an application embodiment provided in this application;

[0048] Figure 5 A workflow diagram of an analysis module in an application embodiment provided in this application;

[0049] Figure 6 is a structural diagram of a list item adjustment device according to an exemplary embodiment;

[0050] Figure 7 The figure is a structural diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0051] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application. In addition, in the embodiments of the present application, "first", "second", etc. are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0052] The embodiment of the present application discloses a list item adjustment method, which realizes automatic adjustment of list items for different accounts and improves user experience.

[0053] See also Figure 1 , according to an exemplary embodiment, a flowchart of a method for adjusting list items is shown, such as Figure 1 As shown, including:

[0054] S101: Collecting operation data of multiple accounts on list items and clustering the operation data;

[0055] In this step, various operation data generated by the account when interacting with the list items are collected, which may include the list item corresponding to the mouse hover position, the search field, the click list sorting field, the edit field, etc. The operation data collected by each account can be represented as a vector. By performing cluster analysis on these vectors, different behavior patterns of different accounts can be identified.

[0056] As a feasible implementation method, clustering the operation data includes: selecting operation data corresponding to accounts of different role types, such as administrator, common account, R&D engineer, etc. The operation data corresponding to accounts of different role types are respectively used as cluster centers; the other operation data are divided into corresponding categories based on the distance between the other operation data and the cluster center; the cluster center is re-determined according to all the operation data in each category, and the step of dividing the other operation data into corresponding categories based on the distance between the other operation data and the cluster center is re-entered, until the operation data contained in all categories no longer changes, and the operation data contained in each category is determined.

[0057] In the specific implementation, the operation data of accounts of different role types are first selected as the initial cluster centers, and then other operation data are assigned to the nearest category based on their distances from these cluster centers. The Euclidean distance can be used as the distance measure, and the formula is as follows:

[0058] ;in, , are cluster centers and other operation data respectively, i is the dimension index, n is the total number of dimensions contained in the operation data, for The eigenvalue of the i-th dimension, for The eigenvalue of the i-th dimension.

[0059] Next, the cluster center is recalculated for the operation data in each category, and the above allocation process is repeated until the members in the category remain stable and unchanged, and finally the fixed members of each category are determined. As a feasible implementation method, the cluster center is re-determined based on all the operation data in each category, including: calculating the mean of all the operation data in each category, and re-determining the mean of all the operation data in each category as the cluster center of the corresponding category. The above process is an iterative clustering algorithm that aims to group the operation data according to the similarity of account behavior to identify the operation modes of different account roles.

[0060] S102: constructing a random forest model based on the clustering results; wherein the random forest model includes multiple decision trees corresponding to multiple categories;

[0061] In the specific implementation, the random forest model built based on the clustering results is composed of multiple decision trees, each of which represents a category. During the model construction process, each decision tree is trained by randomly selecting a portion of the data and features in the clustering results. In this way, the random forest model can integrate the prediction results of multiple decision trees to improve the overall classification performance and robustness.

[0062] As a feasible implementation method, in the process of constructing the random forest model, the optimal splitting point of the decision tree is selected according to the Gini coefficient. In the specific implementation, the Gini coefficient is used as the splitting criterion, and the optimal splitting point is selected for node splitting to minimize the impurity of the node, thereby improving the classification accuracy of the decision tree. The Gini coefficient measures the unevenness of the category distribution in the data set. The lower its value, the higher the classification purity of the data set. The calculation formula is as follows:

[0063] ; where i is the category index, C is the total number of categories, is the proportion of the operation data of the ith category to all the operation data, and Gini is the calculated Gini coefficient.

[0064] S103: Inputting the operation data of the current login account and the candidate list items into the random forest model to determine the first importance score of the candidate list items;

[0065] In a specific implementation, the operation data of the current login account and the candidate list items are applied as input to the random forest model, the category to which the current login account belongs is determined based on the operation data of the current login account, and a score representing its importance is calculated for each candidate list item based on the category to which the current login account belongs, which is called the first importance score.

[0066] S104: Determine target list items whose first importance scores are greater than a preset value from the candidate list items, sort the target list items from large to small according to the first importance scores, and display the target list items according to the sorting result.

[0067] In a specific implementation, a preset threshold is set to screen out those list items whose first importance scores are higher than the threshold, namely, the target list items, and these target list items are sorted from high to low according to their importance scores, and then the target list items are displayed according to the sorting results.

[0068] The list item adjustment method provided in the embodiment of the present application collects the operation data of the account, automatically adjusts the specific list items displayed and the display order of the list items according to the behavioral preferences of the account, and displays the list items that the user is most concerned about in the most obvious position, thereby realizing automatic adjustment of list items for different accounts and improving the user experience.

[0069] The embodiment of the present application discloses a method for adjusting list items. Compared with the previous embodiment, this embodiment further explains and optimizes the technical solution. Specifically:

[0070] See also Figure 2, a flowchart of another list item adjustment method according to an exemplary embodiment is shown, such as Figure 2 As shown, including:

[0071] S201: Collecting operation data of multiple accounts on list items, and clustering the operation data;

[0072] S202: constructing a random forest model based on the clustering results; wherein the random forest model includes multiple decision trees corresponding to multiple categories;

[0073] S203: Inputting the operation data of the current login account and the candidate list items into the random forest model to determine the first importance score of the candidate list items;

[0074] S204: Determine a second importance score of the candidate list item according to the number of times the candidate list item appears in the operation data of the current login account; wherein the second importance score is positively correlated with the number of times the candidate list item appears;

[0075] In a specific implementation, the second importance score of the candidate list items is determined by counting the number of times they appear in the operation data. Here, the second importance score is proportional to the number of appearances, that is, the more frequently the candidate list items appear, the higher their second importance score, which reflects the actual usage frequency and potential importance of the candidate list items in account operations.

[0076] S205: assigning a first weight coefficient to the first importance score, assigning a second weight coefficient to the second importance score, calculating a first product of the first importance score of the candidate list item and the first weight coefficient, calculating a second product of the second importance score of the candidate list item and the second weight coefficient, and calculating a sum of the first product and the second product as the importance score of the candidate list item;

[0077] In a specific implementation, by assigning different weight coefficients to the two importance indicators of the list items, namely the first importance score and the second importance score, the overall importance of each candidate list item can be comprehensively evaluated. Specifically, the first importance score is multiplied by a first weight coefficient, the second importance score is multiplied by a second weight coefficient, and then the two products are added together to obtain the comprehensive importance score of each candidate list item. The comprehensive importance score reflects the importance of the list item in the random forest model (reflected by the first importance score) and the frequency of occurrence in the operation data (reflected by the second importance score).

[0078] S206: Determine target list items whose importance scores are greater than a preset value from the candidate list items, sort the target list items from large to small according to the importance scores, and display the target list items according to the sorting result.

[0079] In a specific implementation, a preset value is set, candidate list items whose comprehensive importance scores exceed the preset value are screened out as target list items, and the target list items are sorted from high to low according to the importance scores, and then the target list items are displayed according to the sorting results.

[0080] On the basis of the above embodiment, as a preferred implementation manner, after sorting the target list items from large to small according to the importance scores, it also includes: determining the associated list items of the target list items according to the association rules; inserting the associated list items of the target list items into the next position of the corresponding target list items in the sorting result; correspondingly, displaying the target list items according to the sorting result includes: displaying the target list items and the corresponding associated list items according to the sorting result.

[0081] It is understandable that when the target list item appears after the list, other important information associated with the target list item may be the data that the account will focus on next. Therefore, the associated list items of the target list item are determined through the association rules, and these associated list items are inserted into the next position of the target list item to show the correlation between the list items, improve the tactical list, and improve the usability to a greater extent. For example, the CPU (Central Processing Unit) temperature is a target list item. When the CPU temperature is too high, the account may need to check the set CPU temperature threshold to determine why the CPU temperature warning message is generated. Therefore, the CPU temperature threshold is used as the associated list item of the CPU temperature.

[0082] The process of building association rules is as follows: First, a minimum support threshold is set to identify frequent itemsets, that is, those itemsets that appear at a certain minimum frequency in all operational data. Candidate itemsets are generated using the Apriori principle, which states that if an itemset is frequent, then all of its non-empty subsets must also be frequent. Candidate itemsets are counted and their number of occurrences in the data set is determined to determine the support of the candidate itemsets. Pruning is then performed to remove itemsets with support below the threshold to reduce the search space. Further, association rules are generated from the frequent itemsets, and the interestingness of the rules is determined by evaluating the confidence, lift, and support of the rules. A minimum confidence threshold is set to filter out weak rules, and then the rules are sorted to prioritize the most interesting rules.

[0083] An application example provided by the present application is described below. Figure 3 As shown, the server includes a collection module, an analysis module, a backup module, an adjustment module, and a record tuning module.

[0084] Collection module: senses the user's frequent mouse click and drag positions, the user's search fields, the user's sorting fields, the user's frequently modified fields, etc., collects this data, processes it permanently, and provides it to the analysis module.

[0085] The workflow of the acquisition module is as follows: Figure 4 As shown, the modified data is collected from the database, the operated data is collected from the page, the collected data is preprocessed, and the data format is unified. The data may include users, list items, searches, and times. Data cleaning is performed, unqualified data is discarded, and data of the same type is increased by one. Then, the data is binned and stored separately according to the operation type, and persisted in the database.

[0086] Analysis module: Analyzes the various indicators collected by the collection module and generates analysis results in the order of list items.

[0087] The workflow of the analysis module is as follows Figure 5 As shown in the figure, data clustering: the operation of grouping data according to certain features or attributes, and obtaining administrator tribe, asset tribe, monitoring tribe, and performance tribe. The monitoring tribe is analyzed by random forest, and the analysis results may include alarm level, alarm source, alarm location, confirmation status, etc. The monitoring tribe is counted, and the statistical results may include alarm level, occurrence time, alarm source, alarm location, etc. The analysis results of random forest and the analysis results of frequency statistics are weighted averaged to obtain the final data, and then associated learning is performed. The analysis is completed to obtain the results, including level, location, source, threshold, and component.

[0088] Backup module: Based on the notification from the analysis module, the relevant data is backed up and compressed. That is, before adjusting the list, the last list order and list items need to be saved to prevent errors or other unexplainable problems when adjusting the list order and list items. In this way, the system can roll back to the previous state, save server space, and prepare for the execution module to perform tasks.

[0089] Recording and tuning module: records all list items, corresponding analysis results, subsequent list items, subsequent analysis results and other data records, and further adjusts the relevant parameters and preset values ​​of the random forest model and the algorithm weights of the two steps based on this to achieve self-optimization.

[0090] Execution module: According to the commands of the analysis module and the completion of the backup module, the list items begin to be dynamically adjusted. The increase or decrease of list items and the list order can be modified according to different commands.

[0091] A list item adjustment device provided in an embodiment of the present application is introduced below. The list item adjustment device described below and the list item adjustment method described above can be referenced to each other.

[0092] See also Figure 6 , according to an exemplary embodiment, a structural diagram of a list item adjustment device is shown, such as Figure 6 As shown, including:

[0093] A clustering unit 601 is used to collect operation data of multiple accounts on list items and cluster the operation data;

[0094] A construction module 602 is used to construct a random forest model based on the clustering results; wherein the random forest model includes multiple decision trees corresponding to multiple categories;

[0095] A first determining unit 603, configured to input the operation data of the current login account and the candidate list item into the random forest model to determine a first importance score of the candidate list item;

[0096] The sorting unit 604 is used to determine the target list items whose first importance scores are greater than a preset value in the candidate list items, sort the target list items from large to small according to the first importance scores, and display the target list items according to the sorting results.

[0097] The list item adjustment device provided in the embodiment of the present application collects the operation data of the account, automatically adjusts the specific list items displayed and the display order of the list items according to the behavioral preferences of the account, and displays the list items that the user is most concerned about in the most obvious position, thereby realizing automatic adjustment of list items for different accounts and improving the user experience.

[0098] Based on the above embodiments, as a preferred implementation mode, the operation data includes any one or a combination of any several of the list items corresponding to the mouse hovering position, the search field, the click list sorting field, and the edit field.

[0099] On the basis of the above embodiments, as a preferred implementation mode, the clustering unit 601 is specifically used to: select the operation data corresponding to accounts of different role types, and use the operation data corresponding to accounts of different role types as cluster centers respectively; divide the other operation data into corresponding categories based on the distance between the other operation data and the cluster center; redetermine the cluster center according to all the operation data in each category, and re-enter the step of dividing the other operation data into corresponding categories based on the distance between the other operation data and the cluster center, until the operation data contained in all categories no longer changes, and determine the operation data contained in each category.

[0100] Based on the above embodiment, as a preferred implementation, the clustering unit 601 is specifically used to: calculate the mean of all operation data in each category, and redefine the mean of all operation data in each category as the cluster center of the corresponding category.

[0101] Based on the above embodiment, as a preferred implementation mode, in the process of constructing the random forest model, the optimal splitting point of the decision tree is selected according to the Gini coefficient.

[0102] Based on the above embodiment, as a preferred implementation, it also includes:

[0103] A second determining unit, configured to determine a second importance score of the candidate list item according to the number of times the candidate list item appears in the operation data of the current login account; wherein the second importance score is positively correlated with the number of times the candidate list item appears;

[0104] Correspondingly, the sorting unit 604 is specifically used to: assign a first weight coefficient to the first importance score, and assign a second weight coefficient to the second importance score; calculate a first product of the first importance score of the candidate list item and the first weight coefficient, and calculate a second product of the second importance score of the candidate list item and the second weight coefficient; calculate the sum of the first product and the second product as the importance score of the candidate list item; determine the target list items whose importance scores are greater than a preset value among the candidate list items, sort the target list items from large to small according to the importance scores, and display the target list items according to the sorting results.

[0105] Based on the above embodiment, as a preferred implementation, it also includes:

[0106] A third determining unit, configured to determine an associated list item of the target list item according to an association rule;

[0107] An inserting unit, used for inserting the associated list item of the target list item into the next position of the corresponding target list item in the sorting result;

[0108] Accordingly, the sorting unit 604 is specifically configured to display the target list item and the corresponding associated list item according to the sorting result.

[0109] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0110] Based on the hardware implementation of the above program module, and in order to implement the method of the embodiment of the present application, the embodiment of the present application also provides an electronic device, Figure 7 FIG. 1 is a structural diagram of an electronic device according to an exemplary embodiment. Figure 7 As shown, the electronic equipment includes:

[0111] Communication interface 1, capable of exchanging information with other devices such as network devices;

[0112] The processor 2 is connected to the communication interface 1 to implement information exchange with other devices, and is used to execute the list item adjustment method provided by one or more technical solutions when running a computer program. The computer program is stored in the memory 3.

[0113] Of course, in actual application, the various components in the electronic device are coupled together through the bus system 4. It can be understood that the bus system 4 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 4 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, Figure 7 Various buses are labeled as bus system 4.

[0114] The memory 3 in the embodiment of the present application is used to store various types of data to support the operation of the electronic device. Examples of such data include: any computer program used to operate on the electronic device.

[0115] It can be understood that the memory 3 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), and direct RAMbus random access memory (DRRAM, Direct Rambus Random Access Memory).The memory 3 described in the embodiments of the present application is intended to include but is not limited to these and any other suitable types of memories.

[0116] The method disclosed in the above embodiment of the present application can be applied to the processor 2, or implemented by the processor 2. The processor 2 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 2 or the instruction in the form of software. The above processor 2 may be a general-purpose processor, a DSP, or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 2 can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiment of the present application, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium, which is located in the memory 3, and the processor 2 reads the program in the memory 3 and completes the steps of the above method in combination with its hardware.

[0117] When the processor 2 executes the program, the corresponding processes in the various methods of the embodiments of the present application are implemented, which will not be repeated here for the sake of brevity.

[0118] In an exemplary embodiment, the embodiment of the present application further provides a non-volatile storage medium storing a computer program, which can be executed by the processor 2 to complete the steps of the aforementioned method.

[0119] In an exemplary embodiment, the present application also provides a computer program product, including a computer program, which is executed by the processor 2 to complete the steps of the aforementioned method.

[0120] A person of ordinary skill in the art can understand that all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to computer program instructions, and the aforementioned computer program can be stored in a non-volatile storage medium. When the computer program is executed, it executes the steps of the above-mentioned method embodiment. Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a non-volatile storage medium. Based on this understanding, the technical solution of the embodiment of the present application can be essentially or partly embodied in the form of a software product, which is stored in a non-volatile storage medium and includes a number of instructions for an electronic device (which can be a personal computer, a server, a network device, etc.) to execute all or part of the methods described in each embodiment of the present application.

[0121] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.

Claims

1. A method for adjusting list items, characterized in that: include: Collecting operation data of multiple accounts on list items, and clustering the operation data; Constructing a random forest model based on the clustering results; wherein the random forest model includes multiple decision trees corresponding to multiple categories; Inputting the operation data of the current login account and the candidate list items into the random forest model to determine the first importance score of the candidate list items; Determine target list items whose first importance scores are greater than a preset value from the candidate list items, sort the target list items from large to small according to the first importance scores, and display the target list items according to the sorting result.

2. The list item adjustment method according to claim 1, characterized in that: The operation data includes any one or a combination of any two of the following: a list item corresponding to the mouse hovering position, a search field, a click list sorting field, and an edit field.

3. The list item adjustment method according to claim 1, characterized in that: Clustering the operation data includes: Select the operation data corresponding to accounts of different role types, and use the operation data corresponding to accounts of different role types as cluster centers respectively; Classifying the other operation data into corresponding categories based on the distance between the other operation data and the cluster center; Re-determine the cluster center based on all the operation data in each category, and re-enter the step of dividing the other operation data into corresponding categories based on the distance between the other operation data and the cluster center, until the operation data included in all categories no longer changes, and determine the operation data included in each category.

4. The list item adjustment method according to claim 3, characterized in that: The re-determining the cluster center according to all the operation data in each category includes: The mean of all operation data in each category is calculated, and the mean of all operation data in each category is re-determined as the cluster center of the corresponding category.

5. The list item adjustment method according to claim 1, characterized in that: Also includes: In the process of constructing the random forest model, the optimal splitting point of the decision tree is selected according to the Gini coefficient.

6. The list item adjustment method according to any one of claims 1 to 5, characterized in that: Also includes: Determine a second importance score of the candidate list item according to the number of times the candidate list item appears in the operation data of the current login account; wherein the second importance score is positively correlated with the number of times the candidate list item appears; Accordingly, determining target list items whose first importance scores are greater than a preset value from the candidate list items, sorting the target list items from large to small according to the first importance scores, and displaying the target list items according to the sorting results, includes: Assigning a first weight coefficient to the first importance score and assigning a second weight coefficient to the second importance score; Calculate a first product of a first importance score of the candidate list item and the first weight coefficient, and calculate a second product of a second importance score of the candidate list item and the second weight coefficient; Calculating a sum of the first product and the second product as an importance score of the candidate list item; Determine target list items whose importance scores are greater than a preset value from the candidate list items, sort the target list items from large to small according to the importance scores, and display the target list items according to the sorting result.

7. The list item adjustment method according to claim 6, characterized in that: After sorting the target list items according to the importance scores from large to small, the method further includes: Determine the associated list items of the target list item according to the association rule; Inserting the associated list item of the target list item into the next position of the corresponding target list item in the sorting result; Accordingly, the target list items are displayed according to the sorting result, including: The target list items and the corresponding associated list items are displayed according to the sorting result.

8. A list item adjustment device, characterized in that: include: A clustering unit, used to collect operation data of multiple accounts on list items and cluster the operation data; A construction module is used to construct a random forest model based on the clustering results; wherein the random forest model includes multiple decision trees corresponding to multiple categories; A first determining unit, configured to input the operation data of the current login account and the candidate list item into the random forest model to determine a first importance score of the candidate list item; The sorting unit is used to determine the target list items whose first importance scores are greater than a preset value in the candidate list items, sort the target list items from large to small according to the first importance scores, and display the target list items according to the sorting results.

9. An electronic device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the list item adjustment method according to any one of claims 1 to 7 when executing the computer program.

10. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a computer program, and when the computer program is executed, the steps of the list item adjustment method according to any one of claims 1 to 7 are implemented.

Images