Automatic evaluation and recommendation method and device based on analysis model and label association
By defining action templates, configuring labels and calling the evaluation analysis model interface methods, the loose coupling problem of model evaluation and plot planning is solved, and the tight coupling between analysis model and labels is realized, which significantly improves the credibility and recommendation speed of the annotation process.
Patent Information
- Application Number
- CN202510158356.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-13
- Publication Date
- 2025-06-24
AI Technical Summary
In the prior art, there is a loose coupling relationship between model evaluation and command personnel chart planning, which leads to the inability to directly convert model analysis results into chart results, and lacks coordination, which affects the credibility and recommendation speed of using analytical models to support command decisions during the annotation process.
By defining the creation of action templates, configuring corresponding marks, and establishing the association between actions and marks, as well as between actions and parameter configuration libraries, calling the evaluation analysis model interface for automatic analysis and evaluation, using the automatic analysis recommendation rule algorithm to generate recommendation results, and providing a location or location area suitable for site selection analysis.
It significantly improves the credibility and recommendation speed of using analytical models to support command decisions during the annotation process, realizes the tight coupling relationship between the model and the label, and improves the efficiency and accuracy of automatic evaluation and recommendation.
Smart Images
Figure CN120198539A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of computer analysis models, and particularly relates to an automatic evaluation and recommendation method and device based on the association between an analysis model and a label. Background Art
[0002] When assisting commanders in marking labels in unfamiliar areas, it is particularly important to effectively provide suitable marking positions, and the automatic evaluation and recommendation technology becomes particularly important. And how to associate and bind the analysis model with the label and then quickly call the model to evaluate and analyze the positions suitable for recommended marking is one of the core concerns of relevant decision-makers.
[0003] In the prior art, the model evaluation and the map plotting planning of commanders belong to a loose coupling relationship, which is neither conducive to forming a good interaction between the model evaluation process and the planning activities of command decision-makers, nor convenient for directly converting the model analysis results into map plotting results.
[0004] In view of this, how to provide an automatic evaluation and recommendation method based on the association between an analysis model and a label, to solve the problem of lack of coordination in applying the model, which is also an auxiliary command decision-making method, to marking maps in unfamiliar areas, and significantly improve the credibility and recommendation speed of using the analysis model to support command decisions during the marking process. Summary of the Invention
[0005] Embodiments of the present application provide an automatic evaluation and recommendation method based on the association between an analysis model and a label, an automatic evaluation and recommendation device based on the association between an analysis model and a label, a computing device, and a computer storage medium, for solving the problem of how to significantly improve the credibility and recommendation speed of using the analysis model to support command decisions during the marking process when solving the problem of lack of coordination in applying the model, which is also an auxiliary command decision-making method, to marking maps in unfamiliar areas.
[0006] In the first aspect of the embodiments of the present application, an automatic evaluation and recommendation method based on the association between an analysis model and a label is provided, including:
[0007] Define and create an action template corresponding to an action, configure corresponding labels in the action template, and establish an association between the action and the label, as well as an association between the action and a parameter configuration library through the action template, where the action template carries an action type and action plan content, and the label corresponds to the action type and the action plan content; the parameter configuration library is used to be responsible for storing and managing information related to the evaluation analysis model;
[0008] Through an evaluation analysis model call interface, call the evaluation analysis model analysis service corresponding to the evaluation analysis model, automatically analyze and evaluate the action and display it, and display the evaluation analysis result;
[0009] In response to the actions in the evaluation analysis results not meeting the requirements, the automatic analysis recommendation rule algorithm is used to generate a recommendation result, and the recommendation result is stored in the action plan and the evaluation report to generate a target action plan recommendation, where the recommendation result carries a location or location area suitable for site selection analysis.
[0010] In a second aspect of the embodiments of the present application, an automatic evaluation and recommendation device based on the association between an analysis model and a label is provided, including:
[0011] An association module, configured to define and create an action template corresponding to an action, configure corresponding labels in the action template, and establish an association between the action and the label, as well as between the action and a parameter configuration library through the action template, where the action template carries an action type and action plan content, and the label corresponds to the action type and the action plan content; the parameter configuration library is used to be responsible for storing and managing information related to the evaluation analysis model;
[0012] An evaluation module, configured to call the evaluation analysis model analysis service corresponding to the evaluation analysis model through an evaluation analysis model call interface, automatically analyze and evaluate the action for display, and display the evaluation analysis result;
[0013] A recommendation module, configured to, in response to the actions in the evaluation analysis results not meeting the requirements, use the automatic analysis recommendation rule algorithm to generate a recommendation result, and store the recommendation result in the action plan and the evaluation report to generate a target action plan recommendation, where the recommendation result carries a location or location area suitable for site selection analysis.
[0014] In a third aspect of the embodiments of the present application, a computing device is provided, including:
[0015] A memory and a processor;
[0016] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the above-mentioned automatic evaluation and recommendation method based on the association between the analysis model and the label are implemented.
[0017] According to a fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, which stores computer-executable instructions. When the instructions are executed by a processor, the steps of the above-mentioned automatic evaluation and recommendation method based on the association between the analysis model and the label are implemented.
[0018] The present application provides an automatic evaluation and recommendation method based on the association between an analysis model and labels, including: First, define an action template corresponding to a creation action, configure corresponding labels in the action template, and establish an association between the action and the labels, as well as between the action and a parameter configuration library through the action template. Among them, the action template carries an action type and action plan content, and the label corresponds to the action type and the action plan content; the parameter configuration library is responsible for storing and managing information related to the evaluation analysis model; Then, through the evaluation analysis model call interface, call the evaluation analysis model analysis service corresponding to the evaluation analysis model to automatically analyze, evaluate and display the action, and display the evaluation analysis result; Finally, in response to the action in the evaluation analysis result not meeting the requirements, use the automatic analysis recommendation rule algorithm to generate a recommendation result, and store the recommendation result in the action plan and evaluation report to generate a target action plan recommendation. Among them, the recommendation result carries a location or location area suitable for site selection analysis.
[0019] Applying the automatic evaluation and recommendation method based on the association between an analysis model and labels provided by the embodiments of the present application, using scientific and reasonable methods and tools to assist relevant departments in making decisions more quickly. By defining an action template corresponding to a creation action and configuring corresponding labels in the action template, an association between the action and the labels, as well as between the action and a parameter configuration library, is established through the action template; through the evaluation analysis model call interface, the model analysis service can be quickly called for automatic analysis, evaluation and display, and when the automatic evaluation label position does not meet the annotation requirements, use the automatic analysis recommendation rule algorithm to recommend a location or location area suitable for annotating the label, so as to provide the best annotation plan recommendation.
[0020] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the specific embodiments of the present application are specifically exemplified below. Brief Description of the Drawings
[0021] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present application. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:
[0022] Figure 1 It is a schematic flowchart of an automatic evaluation and recommendation method based on the association between an analysis model and labels provided by the embodiments of the present application;
[0023] Figure 2Schematic diagram of the process of associating actions with labels in an automatic evaluation and recommendation method based on the association of an analysis model and labels provided by an embodiment of the present application;
[0024] Figure 3 Schematic diagram of the process of automatically analyzing and evaluating labeled numbers in an automatic evaluation and recommendation method based on the association of an analysis model and labels provided by an embodiment of the present application;
[0025] Figure 4 Schematic diagram of the implementation effect of automatically analyzing and evaluating labeled numbers in an automatic evaluation and recommendation method based on the association of an analysis model and labels provided by an embodiment of the present application;
[0026] Figure 5 Schematic diagram of the process of automatically recommending labeled numbers in an automatic evaluation and recommendation method based on the association of an analysis model and labels provided by an embodiment of the present application;
[0027] Figure 6 Schematic diagram of the implementation effect of automatically recommending labeled numbers in an automatic evaluation and recommendation method based on the association of an analysis model and labels provided by an embodiment of the present application;
[0028] Figure 7 Schematic diagram of the structure of an automatic evaluation and recommendation device based on the association of an analysis model and labels provided by an embodiment of the present application;
[0029] Figure 8 Block diagram of the structure of a computing device provided by an embodiment of the present application. Detailed implementation manners
[0030] Hereinafter, exemplary embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.
[0031] Refer to Figure 1 , Figure 1 which is a schematic diagram of the process of an automatic evaluation and recommendation method based on the association of an analysis model and labels provided by an embodiment of the present application. As Figure 1 shown, it specifically includes the following steps.
[0032] Step S102: Define an action template corresponding to the creation action, configure corresponding labels in the action template, and establish associations between the action and the labels, as well as between the action and the parameter configuration library through the action template. Among them, the action template carries the action type and the action plan content, and the label corresponds to the action type and the action plan content; the parameter configuration library is used to be responsible for storing and managing information related to the evaluation and analysis model.
[0033] Step S104: Through the evaluation and analysis model call interface, call the evaluation and analysis model analysis service corresponding to the evaluation and analysis model, automatically analyze, evaluate and display the action, and display the evaluation and analysis result.
[0034] Step S106: In response to the action in the evaluation and analysis result not meeting the requirements, use the automatic analysis and recommendation rule algorithm to generate a recommendation result, and store the recommendation result in the action plan and the evaluation report to generate a target action plan suggestion. Among them, the recommendation result carries the location or location area suitable for site selection analysis.
[0035] The embodiment of the present application provides an automatic evaluation and recommendation method based on the association between the analysis model and the label. First, it is necessary to establish the association between the action and the label, and the association between the action and the model to complete the binding of the model and the label, providing support for the rapid call of the model; secondly, through the model call interface, quickly call the model analysis service; finally, analyze, evaluate and display the action. If the action does not meet the requirements, use the automatic analysis and recommendation rule algorithm to recommend the location or area suitable for label marking, and store the recommendation result in the action plan and the evaluation report to facilitate providing the best action plan suggestion to further improve the automation level of command. Next, the design and implementation process will be elaborated in detail.
[0036] First is the automatic evaluation technology based on the association between the model and the label.
[0037] In unfamiliar areas, the commanders divide and define different action types for various typical action styles, and then form action types around different styles. In the action type, the key to solving the problem of automatically evaluating whether the area is suitable for marking according to the label is to establish the association between the action and the label, as well as between the action and the model through the action template, so as to complete the binding of the model and the label. Therefore, it is first necessary to define and create an action template, which mainly includes the action type and the action plan content, and configure the corresponding label in the action template to correspond to the corresponding action type and plan. Secondly, read the parameter configuration library to query the parameters required by the model (such as configuring the area conditions, etc.) to realize the evaluation of the area.
[0038] It should be noted that the action templates here are a series of action patterns mainly formulated for various emergencies. Through the setting of relevant attribute information, actions are classified and defined. Taking rescue actions as an example, they are mainly divided into three types: comprehensive emergency rescue, special emergency rescue, and on-site emergency rescue, providing template support for the rapid development of rescue actions.
[0039] In the embodiments of the present application, establishing the association between actions and labels, and between actions and the parameter configuration library through the action template includes:
[0040] Read the existing action templates displayed in the action template library and create action types, where the action templates carry action types and action plan contents;
[0041] When the creation of the action type is successful, obtain the label list according to the label library, define the actions, and associate the actions with the labels. The label library includes label numbers and label levels. The label numbers are used to indicate the unit numbers of the team logos, and the label levels are used to correspond to the configured areas; the labels are plotted on the map by action node triggers or are manually reversely associated with the action nodes from the plotted situation on the map;
[0042] Read the parameter configuration library to obtain the model list, configure the actions, and bind the actions with the evaluation and analysis models;
[0043] Save the action template to the action template library. When the saving is successful, the association between actions and labels, and between actions and the parameter configuration library is completed.
[0044] The association between actions and labels can not only provide deployment location information, but also be quickly displayed on the map with plots that conform to the commander's command and decision-making intentions, and at the same time support users to edit and modify the labels. By establishing an action template management panel, a series of action plan templates automatically generated based on information such as the composition, definition, and environmental impact factors of actions related to typical styles are managed for users to query and retrieve through basic description information. The main design and implementation process is as follows: First, read and display the existing action templates from the action template library; second, create action types. If the creation is successful, obtain the label list according to the label library to define the actions, and read the parameter configuration library to obtain the model list to configure the actions; finally, save the action template to the action template library. If the saving is successful, the association between actions and labels is completed, providing support for the rapid evaluation and analysis of subsequent models. The process is as Figure 2 shown, Figure 2 It is a schematic flow diagram of the association between actions and labels in an automatic evaluation and recommendation method based on the association between analysis models and labels provided by the embodiments of the present application.
[0045] It should be noted that the label library here refers to the collection of various graphics such as various institutions, infrastructures, meteorology, maps, and basic graphic elements. The label number code is used to indicate the number of the team flag, and the level corresponds to the configured area.
[0046] The parameter configuration library here is mainly responsible for storing and managing information related to the evaluation and analysis model, including basic model information, extended information, interface information, version information, input and output parameters, etc.
[0047] The association between actions and labels is applied in the stage of plan formulation. In the development and implementation, an internal mapping relationship is set between specific actions and labels on the map. The prerequisite is that the label is plotted on the map by triggering through an action node or is manually reversely associated with the action node by plotting the situation on the map.
[0048] Through the implementation of the above internal mapping, the commander can intuitively see which plotted situations on the map correspond to the currently selected action. At the same time, it is also possible to reversely know the actions in the corresponding stage by clicking on the situation plot on the map, so as to facilitate quickly viewing the action configuration and deployment situation, etc. The core implementation technology of this function is to use an object-oriented standard mapping linked list. By using the library number lib, number code, and level of the label, each label is bound to an action, and the core problems concerned by the commander are solved with a simple and intuitive implementation idea.
[0049] In the embodiment of the present application, through the evaluation and analysis model call interface, the evaluation and analysis model analysis service corresponding to the evaluation and analysis model is called to automatically analyze, evaluate, and display the action, and the evaluation and analysis result is displayed, including:
[0050] Display the action list corresponding to the content of the current action plan. According to the mapping linked list between the action and the label, obtain the label associated with the current action, and according to the mapping linked list between the action and the parameter configuration library model, obtain the evaluation and analysis model configured for the current action, and perform dynamic situation plotting based on the associated label and the evaluation and analysis model;
[0051] After completing the dynamic situation plotting, use the label and the corresponding label level as input parameters, read the parameter configuration library, and call the evaluation and analysis model analysis service corresponding to the evaluation and analysis model to perform action evaluation and analysis suggestions;
[0052] Automatically analyze, evaluate, and display the action, and display the evaluation and analysis result. Among them, the evaluation and analysis result carries the evaluation values and evaluation grades of each model participating in the analysis, the comprehensive evaluation value, and the analysis conclusion.
[0053] Further, taking the label and the corresponding label level as input parameters, reading the parameter configuration library, and invoking the evaluation analysis model analysis service corresponding to the evaluation analysis model to conduct action evaluation analysis and give suggestions, including:
[0054] Taking the label and the corresponding label level as input parameters, reading the parameter configuration library, and obtaining the corresponding analysis range radius and the input parameters corresponding to the model evaluation;
[0055] Constructing a circular analysis range centered at the label position with the analysis range radius as the radius, and sequentially rotating by a preset angle to obtain the horizontal and vertical coordinates of the surrounding points in the analysis range;
[0056] Automatically distributing the action information corresponding to the current action to each evaluation model parameter list, and invoking the evaluation analysis model analysis service corresponding to the evaluation analysis model through the evaluation analysis model call interface to conduct action evaluation analysis and give suggestions.
[0057] Further, the method for determining the comprehensive evaluation value includes:
[0058] Performing weighted average processing on the evaluation values of the obtained evaluation analysis models to generate a comprehensive evaluation value. Among them, in response to the comprehensive evaluation value meeting the preset evaluation threshold, it is determined that the label position meets the decision automatic evaluation condition, and the analysis results and actions generated by the evaluation analysis model are associated at the memory level and stored in the action plan and evaluation report to give analysis evaluation suggestions for the action.
[0059] The actions can automatically screen out the required analysis evaluation models through the evaluation analysis model list configured in the action template. Action analysis and evaluation facilitate the commander to quickly obtain the configured analysis models. At the same time, information such as the analysis area and deployment location required by the analysis model is automatically calculated from the planning plan and directly pushed to the input parameter request list of the model, improving the execution efficiency of the commander and analyst using the analysis results of the model to make decisions on label marking. At the same time, the analysis results and analysis logs of the model call are structured and saved in the extended attributes of the action, facilitating the preservation and output of the analysis evaluation results. The automatic analysis and evaluation process is as follows.
[0060] First, open a specific action plan to display the action list added in the scenario planning stage. Obtain the label associated with the action according to the mapping linked list between the action and the label, and obtain the analysis model of the current action configuration according to the mapping linked list between the action and the model. Conduct action situation plotting to form a map that conforms to the determination, and then organize the corresponding decision-making documents in accordance with the specified format. It mainly plots the current action deployment on the map through standardized labels to provide auxiliary support for the user's command decision-making. Secondly, after completing the action plotting, use the label and level as input parameters. The level is the configured area of the decision-making deployment location. Then read the parameter configuration library to obtain the corresponding analysis range radius and the input parameters required for model evaluation. Then construct a circular analysis range based on the analysis radius and the label position, rotate the angle in sequence, and obtain the horizontal and vertical coordinates of the points around the analysis range. The system actively distributes the analysis results of information such as the personnel configuration and deployment situation associated with this action to each evaluation analysis model parameter list, and through the model call interface, realizes the automatic acquisition of information such as the model evaluation area, personnel configuration, and location deployment, and quickly calls the model analysis service. Finally, conduct analysis and evaluation display of the action, and display the evaluation analysis results. The evaluation analysis results include the evaluation values and evaluation levels of each model participating in the analysis, the comprehensive evaluation value, and the analysis conclusion. Among them, the comprehensive evaluation value currently uses the weighted average of the evaluation values of each model. If the value is greater than 0.6, it means that the position plotted this time meets the automatic evaluation conditions of the label. Finally, associate the analysis result information and the action at the memory level and store them in the action plan and the evaluation report, thereby realizing the analysis and evaluation suggestions for the action. The process is as Figure 3 shown, where Figure 3 is a schematic flow chart of automatically analyzing and evaluating the marked label in an automatic evaluation and recommendation method based on the association between the analysis model and the label provided by an embodiment of the present application. Taking the site selection model A and the site selection model B as examples, the automatic analysis and evaluation of the label for the site selection analysis effect is as Figure 4 shown, where Figure 4 is a schematic diagram of the implementation effect of automatically analyzing and evaluating the marked label in an automatic evaluation and recommendation method based on the association between the analysis model and the label provided by an embodiment of the present application.
[0061] Then, based on the automatic recommendation technology associated with the model and the label.
[0062] In an embodiment of the present application, in response to the action in the evaluation analysis result not meeting the requirements, the automatic analysis recommendation rule algorithm is used to generate a recommendation result, including:
[0063] In response to the comprehensive evaluation value in the evaluation analysis result not meeting the preset evaluation threshold, it is determined that the label position does not meet the automatic evaluation conditions of the decision, and the automatic analysis recommendation rule algorithm is used to generate a recommendation result.
[0064] Further, generating a recommendation result by using an automatic analysis and recommendation rule algorithm includes:
[0065] Taking the labeled position as the center and based on a preset radius, determining an automatic search range;
[0066] Based on a preset search distance, searching for a position or position area that meets the action requirements within the automatic search range;
[0067] In response to finding a target recommended position or target recommended position area in the first direction, stop the search in the first direction, and display the recommendation result information and the corresponding comprehensive evaluation value;
[0068] Associate the recommendation result information and the action at the memory level, store them in the action plan and the evaluation report, and automatically recommend for the command decision-making.
[0069] In a certain specific action plan, use the pre-made action template, by configuring data such as the environment, action personnel, material equipment, etc., conduct action situation plotting, read the parameter configuration library to query the limiting conditions for site selection analysis, realize the automatic acquisition of information such as the model evaluation area, action personnel, and position deployment, quickly call the model analysis service to analyze and evaluate the action and display it, and display the evaluation analysis result. If the evaluation result shows that the evaluation value is less than 0.6 and the area is not suitable for carrying out the action, then start the automatic recommendation of the labeled position for the command decision-making, set the automatic analysis and recommendation rule algorithm. First, set the surrounding 5 kilometers centered on the plotted position of the label as the automatic search range; secondly, with a step size of 1 kilometer each time, search for a position or area suitable for carrying out the label annotation within a radius of 5 kilometers around the labeled position. According to the fact that a suitable recommended position has been found in a certain direction, obtain the automatic recommended position of the label according to the rule of not continuing to expand the search in that direction, and display the recommended position and the comprehensive evaluation value; finally, associate the recommendation result information and the action at the memory level, store them in the action plan and the evaluation report, and thus realize the automatic recommendation of the labeled position. The process is as Figure 5 shown, and the implementation effect is as Figure 6 shown. It is found that it is suitable to mark the label 1 kilometer to the north and 1 kilometer to the west. Among them, Figure 5 is a schematic flowchart of the automatic recommendation of the label annotation in an automatic evaluation and recommendation method based on the association of an analysis model and a label provided by an embodiment of the present application; Figure 6 is a schematic diagram of the implementation effect of the automatic recommendation of the label annotation in an automatic evaluation and recommendation method based on the association of an analysis model and a label provided by an embodiment of the present application.
[0070] The automatic evaluation and recommendation technology provided by the embodiments of this application mainly realizes the automatic calculation of coordinates, angles, routes, ranges, and index parameters required for model operations, the extraction of parameter configuration libraries, and the input of all of them through plotting the positioning points, lines, directions, and attribute information of labels, and using the newly established algorithm rules, based on the tight coupling relationship where humans pre-associate relevant models with labels, set attribute information, and establish call rules. At the same time, to further improve the automation level of the evaluation model to assist decision-making commanders in marking labels in unfamiliar areas, when the position and range of the evaluated and plotted labels cannot meet the action requirements, an automatic analysis and recommendation rule algorithm for the surrounding area centered on the current position of the label is designed, which can recommend positions or areas that meet the requirements of marking labels nearby to the commander in the form of labels.
[0071] In addition, the embodiments of this application also provide the implementation steps of the automatic evaluation and recommendation method based on the association between the analysis model and the label, as follows:
[0072] Step 1: Define the action type, and associate the action with the label using the library number lib and label number code where it is located;
[0073] Step 2: Read the model list in the parameter configuration library, configure the action, and complete the binding of the action and the model;
[0074] Step 3: Locate the label corresponding to the deployment position on the map;
[0075] Step 4: Query the attributes of the selected label: the library number lib and label number code where it is located, and obtain the associated label;
[0076] Step 5: According to the characteristics of the model, parse the parameter configuration library, obtain the corresponding analysis range radius, index parameters, and input parameters (coordinates, angles, routes, ranges, etc.) required for model evaluation, and distribute the results to each evaluation analysis model parameter list;
[0077] Step 6: Based on the model list configured for the action, open the model call interface, automatically obtain information such as the model evaluation area, and quickly call the model analysis service;
[0078] Step 7: Analyze, evaluate, and display the action, display the evaluation analysis results, and analyze whether the current position is suitable for label marking (determine whether to recommend based on the comprehensive evaluation value);
[0079] Step 8: If the comprehensive evaluation value in Step 7 is not greater than 0.6, then consider the automatic analysis and recommendation rule algorithm to recommend suitable positions or areas for marking;
[0080] Step 9: Associate the analysis result information and the action at the memory level, and store them in the action plan and evaluation report.
[0081] Applying the automatic evaluation and recommendation method based on the association between the analysis model and the label provided by the embodiments of the present application, using scientific and reasonable methods and tools to assist relevant departments in making decisions more quickly. By defining and creating an action template corresponding to an action, and configuring corresponding labels in the action template, the association between the action and the label, and between the action and the parameter configuration library is realized; through the evaluation analysis model call interface, the model analysis service is quickly called for automatic analysis, evaluation and display. When the position of the automatic evaluation label does not meet the annotation requirements, the automatic analysis recommendation rule algorithm is used to recommend the position or position area suitable for annotating the label, and then the best annotation scheme suggestion is provided.
[0082] Corresponding to the above method embodiments, this specification also provides an embodiment of an automatic evaluation and recommendation device based on the association between the analysis model and the label. Figure 7 It is a schematic structural diagram of an automatic evaluation and recommendation device based on the association between the analysis model and the label provided by the embodiments of the present application. As Figure 7 shown, the device includes:
[0083] An association module 702, configured to define and create an action template corresponding to an action, configure corresponding labels in the action template, and establish an association between the action and the label, and between the action and the parameter configuration library through the action template. The action template carries the action type and the action plan content, and the label corresponds to the action type and the action plan content; the parameter configuration library is used to be responsible for storing and managing information related to the evaluation analysis model;
[0084] An evaluation module 704, configured to call the evaluation analysis model analysis service corresponding to the evaluation analysis model through the evaluation analysis model call interface, automatically analyze, evaluate and display the action, and display the evaluation analysis result;
[0085] A recommendation module 706, configured to, in response to the action in the evaluation analysis result not meeting the requirements, use the automatic analysis recommendation rule algorithm to generate a recommendation result, and store the recommendation result in the action plan and the evaluation report to generate a target action plan suggestion. The recommendation result carries the position or position area suitable for site selection analysis.
[0086] In an optional embodiment, the association module 702 is further configured to:
[0087] Read the existing action templates in the action template library, and create an action type. The action template carries the action type and the action plan content;
[0088] When the creation of the action type is successful, obtain a list of labels according to the label library, define the action, and associate the action with the label. Among them, the label library includes a label number and a label level. The label number is used to indicate the unit number of the team flag, and the label level is used to correspond to the configured area. The label is plotted on the map by triggering an action node or manually reversely associated with the action node by plotting the situation on the map.
[0089] Read the parameter configuration library to obtain a list of models, configure the action, and bind the action to the evaluation and analysis model.
[0090] Save the action template to the action template library. When the save is successful, complete the association between the action and the label, and between the action and the parameter configuration library.
[0091] In an alternative embodiment, the evaluation module 704 is further configured to:
[0092] Display the action list corresponding to the current action plan content. According to the mapping linked list between the action and the label, obtain the label associated with the current action, and according to the mapping linked list between the action and the parameter configuration library model, obtain the evaluation and analysis model configured for the current action. Perform dynamic situation plotting based on the associated label and the evaluation and analysis model.
[0093] After completing the dynamic situation plotting, use the label and the corresponding label level as input parameters, read the parameter configuration library, call the evaluation and analysis model analysis service corresponding to the evaluation and analysis model, and perform action evaluation and analysis suggestions.
[0094] Automatically analyze, evaluate, and display the action, and display the evaluation and analysis results. Among them, the evaluation and analysis results carry the evaluation values and evaluation levels of each model participating in the analysis, the comprehensive evaluation value, and the analysis conclusion.
[0095] In an alternative embodiment, the evaluation module 704 is further configured to:
[0096] Use the label and the corresponding label level as input parameters, read the parameter configuration library, and obtain the corresponding analysis range radius and input parameters corresponding to the model evaluation.
[0097] Construct a circular analysis range centered on the label position with the analysis range radius as the radius, rotate by a preset angle in sequence, and obtain the horizontal and vertical coordinates of the surrounding points in the analysis range.
[0098] Automatically distribute the action information corresponding to the current action to each evaluation model parameter list, and through the evaluation and analysis model call interface, call the evaluation and analysis model analysis service corresponding to the evaluation and analysis model to perform action evaluation and analysis suggestions.
[0099] In an alternative embodiment, the evaluation module 704 is further configured to:
[0100] Perform a weighted average process on the evaluation values of the obtained evaluation analysis models to generate a comprehensive evaluation value. Wherein, in response to the comprehensive evaluation value meeting a preset evaluation threshold, it is determined that the labeled position meets the decision automatic evaluation condition, and the analysis result and action generated by the evaluation analysis model are associated at the memory level and stored in the action plan and evaluation report, and analysis and evaluation suggestions are provided for the action.
[0101] In an alternative embodiment, the recommendation module 706 is further configured to:
[0102] In response to the comprehensive evaluation value in the evaluation analysis result not meeting the preset evaluation threshold, it is determined that the labeled position does not meet the decision automatic evaluation condition, and a recommendation result is generated using the automatic analysis recommendation rule algorithm.
[0103] In an alternative embodiment, the recommendation module 706 is further configured to:
[0104] With the labeled position as the center, based on a preset radius, determine an automatic search range;
[0105] Based on a preset search distance, search for positions or position areas that meet the action requirements within the automatic search range;
[0106] In response to a target recommended position or target recommended position area being searched in the first direction, stop the search in the first direction, and display the recommendation result information and the corresponding comprehensive evaluation value;
[0107] Associate the recommendation result information and the action at the memory level, store them in the action plan and evaluation report, and automatically recommend for command decisions.
[0108] Applying the automatic evaluation and recommendation device based on the association of the analysis model and the label provided by the embodiments of the present application, using scientific and reasonable methods and tools to assist relevant departments in making decision problems more quickly. By defining and creating an action template corresponding to the action, and configuring the corresponding label in the action template, the association between the action and the label, as well as the association between the action and the parameter configuration library, is realized; through the evaluation analysis model call interface, the model analysis service is quickly called for automatic analysis evaluation display, and when the automatic evaluation labeled position does not meet the labeling requirements, the automatic analysis recommendation rule algorithm is used to recommend positions or position areas suitable for labeling the label, thereby providing the best labeling scheme suggestions.
[0109] Each embodiment in this specification is described in a progressive manner. For the parts that are the same or similar among the embodiments, reference can be made to each other, and the key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the automatic evaluation and recommendation device based on the association between the analysis model and the label, since it is basically similar to the embodiment of the automatic evaluation and recommendation method based on the association between the analysis model and the label, the description is relatively simple, and reference can be made to the partial description of the embodiment of the automatic evaluation and recommendation method based on the association between the analysis model and the label for the relevant parts.
[0110] Figure 8 It is a structural block diagram of a computing device provided by an embodiment of the present application. The components of the computing device 800 include, but are not limited to, a memory 810 and a processor 820. The processor 820 is connected to the memory 810 through a bus 830, and a database 850 is used to store data.
[0111] The computing device 800 further includes an access device 840, and the access device 840 enables the computing device 800 to communicate via one or more networks 860. Examples of these networks include the Public Switched Telephone Network (PSTN), Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), or a combination of communication networks such as the Internet. The access device 840 may include one or more of any type of wired or wireless network interfaces (for example, a network interface card (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC).
[0112] In an embodiment of this specification, the above components of the computing device 800 and Figure 8 other components not shown in the figure may also be connected to each other, for example, through a bus. It should be understood that Figure 8 the shown structural block diagram of the computing device is only for the purpose of illustration, rather than a limitation on the scope of this specification. Those skilled in the art can add or replace other components as needed.
[0113] The computing device 800 can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.) or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 800 can also be a mobile or stationary server.
[0114] Wherein, the processor 820 is configured to execute the following computer-executable instructions, which when executed by the processor implement the steps of the above-mentioned automatic evaluation and recommendation method based on the association between the analysis model and the label.
[0115] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the embodiment of the computing device, since it is basically similar to the embodiment of the automatic evaluation and recommendation method based on the association between the analysis model and the label, the description is relatively simple, and the relevant parts can be referred to the partial description of the embodiment of the automatic evaluation and recommendation method based on the association between the analysis model and the label.
[0116] An embodiment of this specification also provides a computer-readable storage medium, which stores computer-executable instructions that, when executed by a processor, implement the steps of the above-mentioned automatic evaluation and recommendation method based on the association between the analysis model and the label.
[0117] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the embodiment of the computer-readable storage medium, since it is basically similar to the embodiment of the automatic evaluation and recommendation method based on the association between the analysis model and the label, the description is relatively simple, and the relevant parts can be referred to the partial description of the embodiment of the automatic evaluation and recommendation method based on the association between the analysis model and the label.
[0118] An embodiment of this specification also provides a computer program, wherein when the computer program is executed on a computer, the computer is made to execute the steps of the above-mentioned automatic evaluation and recommendation method based on the association between the analysis model and the label.
[0119] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the computer program embodiments, since they are basically similar to the embodiments of the automatic evaluation and recommendation method based on the association between the analysis model and the label, the description is relatively simple, and for the relevant parts, reference can be made to the partial description of the embodiments of the automatic evaluation and recommendation method based on the association between the analysis model and the label.
[0120] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the specific order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0121] The computer instructions include computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, removable hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.
[0122] It should be noted that the above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the specific order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the embodiments of this specification.
[0123] In the above embodiments, the descriptions of the respective embodiments each have their own emphasis. For parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.
[0124] The preferred embodiments of the present specification disclosed above are only used to help explain the present specification. The alternative embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made according to the content of the embodiments of the present specification. These embodiments are selected and specifically described in this specification in order to better explain the principles and practical applications of the embodiments of the present specification, so that those skilled in the art can well understand and utilize the present specification. The present specification is only limited by the claims and their full scope and equivalents.
Claims
1. An automatic evaluation and recommendation method based on the association between analytical models and labels, characterized in that: include: Define an action template corresponding to the creation action, configure a corresponding label in the action template, and establish an association between the action and the label, and between the action and the parameter configuration library through the action template, wherein the action template carries the action type and the action plan content, and the label corresponds to the action type and the action plan content; the parameter configuration library is responsible for storing and managing the relevant information of the evaluation and analysis model; Through the evaluation and analysis model calling interface, the evaluation and analysis model analysis service corresponding to the evaluation and analysis model is called to automatically analyze and evaluate the action and display the evaluation and analysis results; In response to the action in the evaluation and analysis result not meeting the requirements, an automatic analysis recommendation rule algorithm is used to generate a recommendation result, and the recommendation result is stored in the action plan and evaluation report to generate a target action plan suggestion, wherein the recommendation result carries a location or location area suitable for site selection analysis.
2. The method according to claim 1, characterized in that The establishing of associations between actions and labels, and between actions and parameter configuration libraries through the action templates includes: Reading an existing action template displayed in the action template library, and creating an action type, wherein the action template carries the action type and action plan content; When the action type is created successfully, a label list is obtained according to the label library, the action is defined, and the action is associated with the label, wherein the label library includes the label number and the label level, the label number is used to indicate the number of the team logo, and the label level is used to correspond to the configuration area; the label is triggered by the action node and plotted on the map, or manually reversely associated to the action node by plotting the situation on the map; Read the parameter configuration library to obtain the model list, configure the action, and bind the action to the evaluation analysis model; The action template is saved to the action template library. If the saving is successful, the association between the action and the label, and between the action and the parameter configuration library is established.
3. The method according to claim 1, characterized in that The evaluation and analysis model calling interface calls the evaluation and analysis model analysis service corresponding to the evaluation and analysis model, automatically analyzes and evaluates the action, and displays the evaluation and analysis results, including: Display the action list corresponding to the current action plan content, obtain the label associated with the current action according to the mapping chain table between the action and the label, and obtain the evaluation and analysis model of the current action configuration according to the mapping chain table between the action and the parameter configuration library model, and perform dynamic potential mapping based on the associated label and the evaluation and analysis model; After completing the dynamic potential mapping, the label and the corresponding label level are used as input parameters, the parameter configuration library is read, and the evaluation and analysis model analysis service corresponding to the evaluation and analysis model is called to make action evaluation and analysis suggestions; The actions are automatically analyzed, evaluated and displayed, and the evaluation and analysis results are displayed, wherein the evaluation and analysis results carry the evaluation value and evaluation level of each model involved in the analysis, the comprehensive evaluation value and the analysis conclusion.
4. The method according to claim 3, characterized in that: The method uses the label and the corresponding label level as input parameters, reads the parameter configuration library, calls the evaluation and analysis model analysis service corresponding to the evaluation and analysis model, and makes action evaluation and analysis suggestions, including: The label and the corresponding label level are used as input parameters, and the parameter configuration library is read to obtain the corresponding analysis range radius and the input parameters corresponding to the model evaluation; Construct a circular analysis range with the marked position as the center and the analysis range radius as the radius, rotate it by preset angles in sequence, and obtain the horizontal and vertical coordinates of the surrounding points in the analysis range; The action information corresponding to the current action is automatically distributed to each evaluation model parameter list, and the evaluation analysis model analysis service corresponding to the evaluation analysis model is called through the evaluation analysis model calling interface to make action evaluation analysis suggestions.
5. The method according to claim 3, characterized in that: The method for determining the comprehensive evaluation value includes: The evaluation values of each evaluation and analysis model are weighted averaged to generate a comprehensive evaluation value. In response to the comprehensive evaluation value meeting the preset evaluation threshold, it is determined that the label position meets the decision-making automatic evaluation conditions, and the analysis results and actions generated by the evaluation and analysis model are associated at the memory level and stored in the action plan and evaluation report, and analysis and evaluation recommendations are made for the actions.
6. The method according to claim 1, characterized in that In response to the action not meeting the requirement in the evaluation and analysis result, the automatic analysis and recommendation rule algorithm is used to generate a recommendation result, including: In response to the evaluation analysis result showing that the comprehensive evaluation value does not meet the preset evaluation threshold, it is determined that the label position does not meet the decision automatic evaluation condition, and the automatic analysis recommendation rule algorithm is used to generate a recommendation result.
7. The method according to claim 6, characterized in that The method of using an automatic analysis recommendation rule algorithm to generate a recommendation result includes: Taking the marked position as the center and based on a preset radius, determining an automatic search range; Based on a preset search distance, search for a location or location area that meets the action requirement within the automatic search range; In response to searching for a target recommended position or a target recommended position area in a first direction, stopping the search in the first direction and displaying recommendation result information and a corresponding comprehensive evaluation value; The recommendation result information and the action are associated at the memory level, stored in the action plan and evaluation report, and the command decision is automatically recommended.
8. An automatic evaluation and recommendation device based on the association between analytical models and labels, characterized in that: include: The association module is configured to define an action template corresponding to the creation action, configure a corresponding label in the action template, and establish an association between the action and the label, and between the action and the parameter configuration library through the action template, wherein the action template carries the action type and the action plan content, and the label corresponds to the action type and the action plan content; the parameter configuration library is responsible for storing and managing the relevant information of the evaluation and analysis model; The evaluation module is configured to call the evaluation analysis model analysis service corresponding to the evaluation analysis model through the evaluation analysis model calling interface, automatically analyze and evaluate the action, and display the evaluation analysis result; The recommendation module is configured to generate a recommendation result using an automatic analysis recommendation rule algorithm in response to the action in the evaluation and analysis result not meeting the requirements, and store the recommendation result in an action plan and an evaluation report to generate a target action plan suggestion, wherein the recommendation result carries a location or location area suitable for site selection analysis.
9. A computing device comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method described in any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an implementation program for information transmission, and when the program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.