Method and device for generating resource configuration strategy, computer device and storage medium

Abstract

The application relates to a resource configuration strategy generation method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: obtaining historical passenger flow data corresponding to a plurality of passenger flow indexes generated by a sample object executing a target task and historical task completion amounts; constructing a correlation relationship model based on the historical passenger flow data and the historical task completion amounts, determining task correlation degrees corresponding to the passenger flow indexes according to the correlation relationship model, and determining candidate passenger flow indexes that satisfy a first preset condition; determining task causality degrees corresponding to the candidate passenger flow indexes by using a causality model based on the historical passenger flow data and the historical task completion amounts, and determining target passenger flow indexes that satisfy a second preset condition; and generating a target resource configuration strategy for a target object executing a target task according to the target passenger flow indexes and preset strategy generation rules. The method can improve the accuracy of the generated resource configuration strategy.

Description

Technical Field

[0001] This application relates to the field of big data technology, and in particular to a method, apparatus, computer device, storage medium, and computer program product for generating resource allocation strategies. Background Technology

[0002] Resource allocation strategies for target entities, such as product providers, will influence their customer flow data, thereby affecting their performance in fulfilling target tasks. To improve the performance of target entities in fulfilling target tasks, it is necessary to develop appropriate resource allocation strategies for them.

[0003] In related technologies, resource allocation strategies for target objects are generally formulated by staff based on experience. However, due to the different circumstances of different tasks and the limited experience of staff, the accuracy of the formulated resource allocation strategies is relatively low. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer device, computer-readable storage medium, and computer program product for generating resource allocation strategies that can improve the accuracy of resource allocation strategies, in order to address the above-mentioned technical problems.

[0005] Firstly, this application provides a method for generating a resource allocation strategy. The method includes:

[0006] Obtain historical passenger flow data and historical task completion volume corresponding to various passenger flow indicators generated by the sample object performing the target task;

[0007] A correlation model is constructed based on the historical passenger flow data corresponding to each of the aforementioned passenger flow indicators and the historical task completion volume. The task relevance corresponding to each of the aforementioned passenger flow indicators is determined according to the correlation model. Passenger flow indicators whose task relevance meets the first preset condition are identified as candidate passenger flow indicators. The task relevance represents the correlation strength between the passenger flow indicator and the task completion volume.

[0008] Based on the historical passenger flow data and historical task completion volume corresponding to each candidate passenger flow indicator, a causal relationship model is used to determine the task causality degree corresponding to each candidate passenger flow indicator, and the candidate passenger flow indicator whose task causality degree satisfies the second preset condition is determined as the target passenger flow indicator; the task causality degree represents the strength of the causal relationship between the passenger flow indicator and the task completion volume.

[0009] Based on the target passenger flow index and the preset strategy generation rules, a target resource allocation strategy is generated for the target object to execute the target task.

[0010] In one embodiment, the step of constructing a correlation model based on historical passenger flow data corresponding to each of the passenger flow indicators and the historical task completion volume, determining the task relevance corresponding to each of the passenger flow indicators according to the correlation model, and determining the passenger flow indicators among the passenger flow indicators whose task relevance meets a first preset condition as candidate passenger flow indicators includes:

[0011] A machine learning model is trained based on the historical passenger flow data corresponding to the various passenger flow indicators and the historical task completion volume. The trained machine learning model is determined as a multi-factor correlation model. Based on the weights of each passenger flow indicator in the multi-factor correlation model, the first correlation degree corresponding to each passenger flow indicator is determined.

[0012] For each of the aforementioned passenger flow indicators, the historical passenger flow data corresponding to the passenger flow indicator and the historical task completion amount are linearly fitted to obtain a single-factor correlation model corresponding to the passenger flow indicator, and the second correlation degree corresponding to the passenger flow indicator is determined based on the determination coefficient of the single-factor correlation model.

[0013] Among the various passenger flow indicators, the passenger flow indicators whose first correlation and second correlation satisfy the first preset condition are determined as candidate passenger flow indicators.

[0014] In one embodiment, determining the passenger flow indicators among the various passenger flow indicators whose first correlation and second correlation satisfy a first preset condition as candidate passenger flow indicators includes:

[0015] The passenger flow indicators are sorted from largest to smallest according to the first correlation to obtain a passenger flow indicator sequence, and the first preset number of passenger flow indicators in the passenger flow indicator sequence are determined as the initial passenger flow indicators.

[0016] Among the preliminary passenger flow indicators, the preliminary passenger flow indicators whose second correlation is greater than a preset threshold are determined as candidate passenger flow indicators.

[0017] In one embodiment, determining the candidate passenger flow indicator that satisfies the second preset condition in terms of task causality among the candidate passenger flow indicators includes:

[0018] For each candidate passenger flow indicator, the first relevance and task causality corresponding to the candidate passenger flow indicator are weighted and summed to obtain the score corresponding to the candidate passenger flow indicator;

[0019] The candidate passenger flow indicators are sorted from largest to smallest according to their scores to obtain a candidate passenger flow indicator sequence, and the first preset number of candidate passenger flow indicators in the candidate passenger flow indicator sequence are determined as target passenger flow indicators.

[0020] In one embodiment, the task relevance corresponds to two types: positive correlation and negative correlation; there are multiple target passenger flow indicators; the step of generating a target resource allocation strategy for the target object to execute the target task based on the target passenger flow indicators and preset strategy generation rules includes:

[0021] In the preset mapping relationship between passenger flow indicators and resource items, the target resource items corresponding to each target passenger flow indicator are determined;

[0022] Based on the task relevance type of each target passenger flow indicator, the target resource item, and the preset strategy template information, a target resource configuration strategy is generated for the target object to execute the target task.

[0023] In one embodiment, the method further includes:

[0024] In response to the policy display instruction, the target resource configuration policy is displayed on the display interface of the target object's business system.

[0025] Secondly, this application also provides an apparatus for generating a resource allocation strategy. The apparatus includes:

[0026] The acquisition module is used to acquire historical passenger flow data and historical task completion volume corresponding to various passenger flow indicators generated by the sample object in performing the target task;

[0027] The first determining module is used to construct a correlation model based on the historical passenger flow data corresponding to each of the passenger flow indicators and the historical task completion amount, determine the task relevance corresponding to each of the passenger flow indicators according to the correlation model, and determine the passenger flow indicators among the passenger flow indicators whose task relevance meets the first preset condition as candidate passenger flow indicators; the task relevance represents the correlation strength between the passenger flow indicator and the task completion amount.

[0028] The second determining module is used to determine the task causality corresponding to each of the candidate passenger flow indicators based on the historical passenger flow data and the historical task completion amount, using a causal relationship model, and to determine the candidate passenger flow indicators whose task causality satisfies the second preset condition as the target passenger flow indicators; the task causality represents the strength of the causal relationship between the passenger flow indicator and the task completion amount.

[0029] The generation module is used to generate a target resource configuration strategy for the target object to perform the target task based on the target passenger flow index and the preset strategy generation rules.

[0030] In one embodiment, the first determining module is specifically used for:

[0031] A machine learning model is trained based on historical passenger flow data corresponding to the various passenger flow indicators and the historical task completion volume. The trained machine learning model is determined as a multi-factor correlation model. Based on the weights of each passenger flow indicator in the multi-factor correlation model, a first correlation degree is determined for each passenger flow indicator. For each passenger flow indicator, the historical passenger flow data and the historical task completion volume are linearly fitted to obtain a single-factor correlation model for the passenger flow indicator. Based on the determination coefficient of the single-factor correlation model, a second correlation degree is determined for the passenger flow indicator. Passenger flow indicators among the passenger flow indicators whose first correlation degree and second correlation degree satisfy a first preset condition are determined as candidate passenger flow indicators.

[0032] In one embodiment, the first determining module is specifically used for:

[0033] The passenger flow indicators are sorted from largest to smallest according to the first correlation to obtain a passenger flow indicator sequence, and the first preset number of passenger flow indicators in the passenger flow indicator sequence are determined as preliminary passenger flow indicators; among the preliminary passenger flow indicators, the preliminary passenger flow indicators with the second correlation greater than a preset threshold are determined as candidate passenger flow indicators.

[0034] In one embodiment, the second determining module is specifically used for:

[0035] For each candidate passenger flow indicator, the first relevance and task causality corresponding to the candidate passenger flow indicator are weighted and summed to obtain the score corresponding to the candidate passenger flow indicator; the candidate passenger flow indicators are sorted from largest to smallest according to the score to obtain a candidate passenger flow indicator sequence, and the first preset number of candidate passenger flow indicators in the candidate passenger flow indicator sequence are determined as target passenger flow indicators.

[0036] In one embodiment, the task relevance corresponds to two types: positive correlation and negative correlation; there are multiple target passenger flow indicators; the generation module is specifically used for:

[0037] In the preset mapping relationship between passenger flow indicators and resource items, the target resource items corresponding to each target passenger flow indicator are determined;

[0038] Based on the task relevance type of each target passenger flow indicator, the target resource item, and the preset strategy template information, a target resource configuration strategy is generated for the target object to execute the target task.

[0039] In one embodiment, the device further includes:

[0040] The display module is used to display the target resource configuration strategy on the display interface of the target object's business system in response to the strategy display command.

[0041] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described in the first aspect.

[0042] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the method described in the first aspect.

[0043] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in the first aspect.

[0044] The aforementioned resource allocation strategy generation method, apparatus, computer equipment, storage medium, and computer program product, through historical passenger flow data and historical task completion volume corresponding to various passenger flow indicators generated by sample objects performing target tasks, conducts correlation analysis (constructs a correlation model) on the relationship between each passenger flow indicator and the task completion volume, determines candidate passenger flow indicators whose task relevance meets preset conditions (strong correlation), and then conducts causal relationship analysis (using a causal relationship model) on the candidate passenger flow indicators and the task completion volume to determine the target passenger flow indicator whose task causality meets preset conditions (strong causal relationship), thereby generating a target resource allocation strategy based on the target passenger flow indicator. In this method, the target passenger flow indicator represents a key indicator that has a strong correlation and strong causal relationship with the task completion volume of the target task and has a significant impact on the completion effect of the target task. By adopting a resource allocation strategy that matches the target passenger flow indicator, such as by strengthening or reducing the allocation of corresponding resource items, the passenger flow data corresponding to the target passenger flow indicator generated during the target object's execution of the target task can be affected (increased or decreased), thereby achieving the purpose of improving the target object's task completion effect. Therefore, the resource allocation strategy generated by this method has a high degree of matching with the needs of the target object and the situation of the target task, that is, it has higher accuracy. Attached Figure Description

[0045] Figure 1 This is a flowchart illustrating a method for generating a resource allocation strategy in one embodiment;

[0046] Figure 2 This is a flowchart illustrating the process of determining candidate passenger flow indicators in one embodiment.

[0047] Figure 3 This is a structural block diagram of a resource allocation strategy generation device in one embodiment;

[0048] Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0050] First, before introducing the technical solutions of the embodiments of this application in detail, we will first introduce the technical background or technical evolution on which the embodiments of this application are based. The resource allocation strategy of target objects such as product providers (e.g., car dealerships) generally includes information such as which resource items to configure, the configuration quantity of each resource item (specific values ​​or directional strategies such as strengthening or reducing), etc. The configuration of different resource items will affect the customer flow data of the target object, thereby affecting the task completion effect of the target object in performing the target task (such as converting customers into car orders). For example, for car dealerships, the resource allocation strategy may include whether to configure a rest area, the type of rest area to configure (business, leisure, children's entertainment), how many display vehicles to configure, how many sales personnel to configure, and the skills training of sales personnel (such as reception, negotiation, showing display vehicles, etc.). Different resource allocation strategies will affect various customer flow metrics for the car dealership. For example, providing a rest area can increase customer flow data such as the number of customer visits and total visit duration (indicating that the customer's time spent in the store exceeds a threshold). Increasing the number of display vehicles and / or providing training for sales staff on how to show vehicles to increase their participation can improve customer flow data such as the number of customer visits and visit duration. Furthermore, the customer flow data generated during the target audience's execution of the target task will affect the car dealership's performance in achieving the target task (car order task), such as affecting the task completion volume (number of car orders).

[0051] To improve the task completion performance of a target object, it is necessary to formulate a suitable resource allocation strategy. In related technologies, resource allocation strategies for target objects are generally formulated by staff based on experience. However, due to the different circumstances of different tasks (e.g., different car order tasks require different resource allocation strategies), and the limited experience of staff leads to a low degree of matching between the formulated resource allocation strategy and the needs and circumstances of the target object, i.e., low accuracy of the resource allocation strategy. Against this background, the applicant, through long-term research and development and experimental verification, proposes a method for generating resource allocation strategies. The target resource allocation strategy generated by this method has a high degree of matching with the needs and circumstances of the target object, i.e., higher accuracy, which is beneficial to improving the task completion performance of the target object. Furthermore, it should be noted that the applicant has devoted considerable creative effort to discovering the technical problem of this application and the technical solutions described in the following embodiments.

[0052] In one embodiment, such as Figure 1 As shown, a method for generating resource allocation strategies is provided. This embodiment illustrates the application of this method to a terminal (such as a business system targeting a car dealership). It is understood that this method can also be applied to a server, and to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0053] Step 101: Obtain historical passenger flow data and historical task completion amount corresponding to various passenger flow indicators generated by the sample object in performing the target task.

[0054] Here, "sample object" refers to an object that has performed the target task. This can be the target object itself or other objects of the same type. For example, for the target task of converting customers visiting a store into orders for a specific car model, multiple car stores may have already performed this task; therefore, these stores can be considered as sample objects. "Historical customer flow data" refers to the customer flow data generated by the sample object during the execution of the target task within a historical period (such as the previous 3 months, 6 months, 1 year, or other preset periods). "Historical task completion volume" refers to the amount of task completed by the sample object during the execution of the target task within a historical period (such as the number of car orders for a specific car model). It is understandable that historical customer flow data and historical task completion volume can include data corresponding to multiple historical periods, and there is a corresponding relationship between them. For example, historical customer flow data includes the customer flow data generated by the sample object each month during the execution of the target task in the previous 6 months; correspondingly, historical task completion volume includes the target task completion volume of the sample object each month in the previous 6 months. If there are multiple sample objects, data for each sample object is included.

[0055] Historical customer flow data specifically includes customer flow data corresponding to various customer flow indicators, each of which is related to the behavior of customers visiting the sample. For example, customers visiting a car dealership may engage in behaviors such as browsing display vehicles, entering and exiting display vehicles, being received by sales staff, being shown display vehicles by sales staff, negotiating with sales staff, and exploring the store in depth. Therefore, customer flow data can be categorized based on the behavior of customers visiting the sample and the duration of each behavior, resulting in customer flow data corresponding to various indicators, such as the number of customer batches and duration for each indicator, including those for browsing display vehicles, entering and exiting display vehicles, receiving staff, showing display vehicles by sales staff, negotiating, and exploring the store in depth.

[0056] During implementation, as sample subjects perform their target tasks, the intelligent passenger flow system can identify and analyze the behavioral information of customers visiting the sample subjects, obtaining passenger flow data corresponding to various passenger flow indicators, and storing the data in a database. Thus, the terminal can retrieve historical passenger flow data and historical task completion figures corresponding to various passenger flow indicators generated by the sample subjects performing their target tasks from the database. Specifically, the intelligent passenger flow system can determine customer behavior information based on human behavior trajectory recognition technology. For example, browsing display vehicles is an important behavior for customers during their stay in the showroom, manifested as actions such as circling and observing, stopping to look, paying attention to signs, touching and experiencing, opening and closing car doors / trunks, and trying out the car, with the aim of comprehensively understanding the vehicle situation and selecting a preferred model and color. The intelligent passenger flow system can identify display vehicle browsing behavior by analyzing information such as the distance between the customer's trajectory and the display vehicle, and the duration of the browsing behavior, and record information such as the time of occurrence of the browsing behavior, customer identification, and display vehicle identification. Therefore, based on the information of the sample objects who visited within the historical period recorded by the intelligent passenger flow system, such as the customer identifiers who browsed the exhibition vehicles and the duration of such behavior, passenger flow data such as the number of passenger batches and duration of browsing exhibition vehicles within that historical period can be obtained.

[0057] Step 102: Construct a correlation model based on the historical passenger flow data and historical task completion volume corresponding to each passenger flow indicator. Determine the task relevance corresponding to each passenger flow indicator according to the correlation model, and determine the passenger flow indicators whose task relevance meets the first preset condition as candidate passenger flow indicators.

[0058] In this context, task relevance represents the strength of the correlation between passenger flow indicators and task completion volume. The correlation model can be a machine learning model or other models (such as a linear regression model). For example, the correlation model can be a machine learning model (such as a LightGBM tree model). The terminal can use historical passenger flow data and historical task completion volumes corresponding to each passenger flow indicator as training samples to train the machine learning model (such as a LightGBM tree model). Each passenger flow indicator corresponds to an input feature. The machine learning model processes the passenger flow data corresponding to each input passenger flow indicator and outputs a predicted value for task completion volume. The training objective is to minimize the difference between the predicted value and the actual value of task completion volume. The trained model is the correlation model. Then, the importance of each feature (corresponding to the passenger flow indicator) can be output from the trained model, and the value of the feature importance is used as the magnitude of the task relevance. In another implementation, the terminal can use a machine learning model interpretation tool (such as SHAP) to analyze and process the trained machine learning model (i.e., the correlation model) to obtain the task relevance (such as the Shapley value) of each passenger flow indicator (i.e., each input feature of the machine learning model). Task relevance can be positive or negative. A positive Shapley value indicates a positive correlation between passenger flow and task completion, while a negative value indicates a negative correlation. Subsequent descriptions of task relevance generally refer to the absolute value of the relevance. To improve the training effect of machine learning models, training samples can include basic information such as weather and date from historical periods; that is, input features can also include weather and date features, resulting in more accurate task relevance for each passenger flow indicator.

[0059] In another implementation, the terminal can also perform linear fitting on the historical passenger flow data and historical task completion volume corresponding to each passenger flow indicator, where the historical passenger flow data is the independent variable (the historical passenger flow data corresponding to passenger flow indicator a can be denoted as x). a Let the number of historical tasks completed be the dependent variable (denoted as y). Through linear fitting, a linear regression model y = kx can be obtained. a +m, where k is the slope and m is the intercept. Then, the terminal can calculate the coefficient of determination R2 of the linear regression model, use the coefficient of determination R2 as the magnitude of the task relevance, and determine the type of task relevance according to the sign (positive or negative) of the slope (positive slope indicates positive correlation, negative slope indicates negative correlation).

[0060] After determining the task relevance of each passenger flow indicator, the terminal can identify passenger flow indicators whose task relevance meets a first preset condition as candidate passenger flow indicators. For example, the terminal can identify passenger flow indicators whose task relevance (absolute value) is greater than a preset threshold as candidate passenger flow indicators.

[0061] Step 103: Based on the historical passenger flow data and historical task completion volume corresponding to each candidate passenger flow indicator, a causal relationship model is used to determine the task causality corresponding to each candidate passenger flow indicator, and the candidate passenger flow indicator whose task causality satisfies the second preset condition is determined as the target passenger flow indicator.

[0062] Among them, task causality represents the strength of the causal relationship between passenger flow indicators and task completion volume.

[0063] In implementation, causal inference methods, such as conditional outcome models, causal trees, and causal forests, can be used to determine the strength of the causal relationship between candidate passenger flow indicators and task completion amounts (with candidate passenger flow indicators as the cause and task completion amounts as the effect), which serves as the task causality degree of the candidate passenger flow indicators. In other implementation methods, A / B experiments and difference-in-differences can also be used to analyze the causal strength between each candidate passenger flow indicator and the task completion amount, obtaining the task causality degree of each candidate passenger flow indicator.

[0064] Then, the terminal can determine the candidate passenger flow indicators that meet the second preset condition in terms of task causality among the candidate passenger flow indicators as the target passenger flow indicators. For example, the terminal can use the candidate passenger flow indicators with task causality greater than a preset threshold as the target passenger flow indicators, or it can sort the candidate passenger flow indicators according to the size of task causality (such as from large to small), and use a preset number (which can be one or more) of the candidate passenger flow indicators before sorting as the target passenger flow indicators.

[0065] Step 104: Generate a target resource allocation strategy for the target object to perform the target task based on the target passenger flow index and the preset strategy generation rules.

[0066] In implementation, after the terminal determines the target customer flow indicator, it can generate a target resource configuration strategy according to preset strategy generation rules. This strategy serves as the resource configuration strategy adopted by the target object to execute the target task. For example, a mapping relationship between customer flow indicators and resource items can be established in advance, where one customer flow indicator can correspond to several resource items. If the target object increases the resource items corresponding to the customer flow indicator in the configuration mapping relationship, the customer flow data corresponding to that indicator can be improved. Conversely, if the resource items corresponding to the customer flow indicator are reduced, the customer flow data corresponding to that indicator can be reduced. For example, for the "deep shopping" indicator, configuring resource items such as leisure areas, children's play areas, and activity items can improve the customer flow data corresponding to the "deep shopping" indicator. For the "show car viewing" indicator, configuring resource items such as training sales staff in show car viewing skills, increasing the number of sales staff skilled in show car viewing, and increasing the number of show cars can improve the customer flow data corresponding to the "show car viewing" indicator. It is understandable that the mapping relationship between passenger flow indicators and resource items has a certain degree of universality, but it is less related to the target task (such as the task of ordering cars of different models). Therefore, it can be obtained in advance through manual experience analysis or by using machine learning models to analyze historical data.

[0067] The terminal can obtain the target resource item corresponding to the target passenger flow indicator from the mapping relationship between passenger flow indicators and resource items. Then, the terminal can generate a target resource configuration strategy based on the target resource item corresponding to the target passenger flow indicator and the preset strategy template information. For example, the strategy template information could be "To improve the task completion rate of vehicle type A, it is recommended to strengthen the configuration of resource item B1 to improve indicator C1." The terminal can replace "A" in the strategy template information with the vehicle type corresponding to the target task, replace "B1" with the target resource item, and replace "C1" with the name of the target passenger flow indicator. It is understandable that the target passenger flow indicator can include positively correlated and negatively correlated indicators. Therefore, the terminal can generate a target resource configuration strategy based on the type of task correlation (positive or negative) corresponding to the target passenger flow indicator, the target resource item, and the preset strategy template information. For example, the strategy template information could be "To improve the task completion rate of vehicle type A, it is recommended to strengthen the configuration of resource item B1 to improve indicator C1; reduce the configuration of resource item B2 to reduce indicator C2." In this framework, "B1" corresponds to the target resource item for a positively correlated target customer flow indicator, and "C1" corresponds to the name of the positively correlated target customer flow indicator. Similarly, "B2" corresponds to the target resource item for a negatively correlated target customer flow indicator, and "C2" corresponds to the name of the negatively correlated target customer flow indicator, thus generating a target resource allocation strategy. Staff at the target location (car dealership) can then use this strategy to allocate resources accordingly, thereby improving the target location's performance in fulfilling its target tasks.

[0068] In this embodiment, by analyzing the historical passenger flow data and historical task completion volume corresponding to various passenger flow indicators generated by the sample object performing the target task, a correlation model is constructed between each passenger flow indicator and the task completion volume. Candidate passenger flow indicators whose task relevance meets preset conditions (strong correlation) are identified. Then, a causal relationship analysis is performed between the candidate passenger flow indicators and the task completion volume (using a causal relationship model) to determine the target passenger flow indicator whose task causality meets preset conditions (strong causal relationship). Based on the target passenger flow indicator, a target resource allocation strategy is generated. In this method, the target passenger flow indicator represents a key indicator that has a strong correlation and strong causal relationship with the task completion volume of the target task and has a significant impact on the completion effect of the target task. By adopting a resource allocation strategy that matches the target passenger flow indicator, such as by strengthening or reducing the allocation of corresponding resource items, the passenger flow data corresponding to the target passenger flow indicator generated during the target object's execution of the target task can be affected (increased or decreased), thereby improving the target object's task completion effect. Therefore, the target resource allocation strategy generated by this method has a high degree of matching with the target object's needs and the target task situation, i.e., higher accuracy.

[0069] In one embodiment, such as Figure 2 As shown, the process of determining candidate passenger flow indicators in step 102 above specifically includes the following steps:

[0070] Step 201: Train a machine learning model based on historical passenger flow data and historical task completion volume corresponding to various passenger flow indicators. Determine the trained machine learning model as a multi-factor correlation model. Based on the weights of each passenger flow indicator in the multi-factor correlation model, determine the first correlation degree corresponding to each passenger flow indicator.

[0071] In implementation, the terminal can train a machine learning model (such as a LightGBM tree model) based on historical passenger flow data and historical task completion volumes corresponding to various passenger flow indicators. Each passenger flow indicator corresponds to an input feature of the machine learning model, and the model's output is the predicted task completion volume. The training objective is to minimize the difference between the predicted task completion volume and the measured task completion volume (i.e., historical task completion volume). The trained machine learning model is defined as a multi-factor correlation model, and the first correlation degree corresponding to each passenger flow indicator is determined based on the weights corresponding to each passenger flow indicator in the multi-factor correlation model. Specifically, the weights of each passenger flow indicator can be obtained by outputting the feature importance (numerical value) of each feature (corresponding to the passenger flow indicator) from the trained model. The terminal can then determine these weights as the first correlation degree corresponding to each passenger flow indicator. The method for outputting feature importance by the machine learning model (including the LightGBM tree model) will not be elaborated here. In other implementation methods, machine learning model interpretation tools (such as SHAP tools) can be used to obtain the weights of each passenger flow indicator in the multi-factor correlation model (the absolute value of the shapley value output by the SHAP tool is used as the weight, or the ratio of the shapley value of each passenger flow indicator to the sum of all shapley values ​​is used as the weight, and the weights are all positive numbers). The terminal can directly determine the weight as the first correlation degree corresponding to each passenger flow indicator.

[0072] Step 202: For each passenger flow indicator, perform linear fitting on the historical passenger flow data and historical task completion amount corresponding to the passenger flow indicator to obtain the single-factor correlation model corresponding to the passenger flow indicator, and determine the second correlation degree corresponding to the passenger flow indicator based on the determination coefficient of the single-factor correlation model.

[0073] In implementation, for each passenger flow indicator, the terminal can linearly fit the historical passenger flow data and historical task completion volume corresponding to that passenger flow indicator to obtain a linear regression model (such as y = kx in the previous example). a +m) represents the single-factor correlation model corresponding to this passenger flow indicator. The terminal can then calculate the determination coefficient R of this single-factor correlation model. 2 This serves as the second correlation for the passenger flow indicator. The terminal can combine the first and second correlations as the task correlation and determine the type of task correlation based on the sign (positive or negative) of the slope in the single-factor correlation model (a positive slope indicates a positive correlation, and a negative slope indicates a negative correlation).

[0074] Step 203: Among the various passenger flow indicators, the passenger flow indicators whose first correlation and second correlation meet the first preset conditions are determined as candidate passenger flow indicators.

[0075] In implementation, the terminal can filter candidate passenger flow indicators that meet the first preset condition based on the first and second relevance values ​​corresponding to each passenger flow indicator. For example, the terminal can use passenger flow indicators with a first relevance value greater than the first preset threshold and a second relevance value greater than the second preset threshold as candidate passenger flow indicators.

[0076] In this embodiment, a multi-factor correlation model is constructed to perform multi-factor correlation analysis on each passenger flow indicator to obtain the first correlation degree. Then, a single-factor correlation model is constructed to perform single-factor correlation analysis on each passenger flow indicator to obtain the second correlation degree. Candidate passenger flow indicators that meet the preset conditions for both the first and second correlation degrees are then selected. The candidate passenger flow indicators determined by this method have a strong correlation with the task completion amount and a high confidence level, thereby further improving the accuracy of the generated resource allocation strategy.

[0077] In one embodiment, the process of determining candidate passenger flow indicators in step 203 above specifically includes the following steps: sorting each passenger flow indicator from largest to smallest according to the first relevance to obtain a passenger flow indicator sequence, and determining the first preset number of passenger flow indicators in the passenger flow indicator sequence as preliminary passenger flow indicators; and determining the preliminary passenger flow indicators among the preliminary passenger flow indicators whose second relevance is greater than a preset threshold as candidate passenger flow indicators.

[0078] In implementation, after the terminal determines the primary and secondary relevance of each passenger flow indicator, it can sort the indicators according to their primary relevance (e.g., from largest to smallest) and identify the top few indicators (those with higher primary relevance) as initial passenger flow indicators. Then, the terminal can compare the secondary relevance of each initial passenger flow indicator with a preset threshold, identifying those with a secondary relevance (i.e., the coefficient of determination r-squared in the single-factor correlation model) greater than the preset threshold (e.g., greater than 0.2) as candidate passenger flow indicators. Alternatively, in another implementation, the terminal can first compare the secondary relevance of each passenger flow indicator with the preset threshold, filtering out initial passenger flow indicators with a secondary relevance greater than the preset threshold. Then, the initial passenger flow indicators can be sorted according to their primary relevance (from largest to smallest), and the top few indicators are identified as candidate passenger flow indicators.

[0079] In this embodiment, a specific implementation method is provided for determining candidate passenger flow indicators based on the first correlation and the second correlation. The determined candidate passenger flow indicators have a strong correlation with the task completion volume and have a high confidence level, thereby further improving the accuracy of the generated resource allocation strategy.

[0080] In one embodiment, step 102 specifically includes steps 201 to 203. Meanwhile, the process of determining the target passenger flow indicator in step 103 specifically includes the following steps: for each candidate passenger flow indicator, the first relevance and task causality corresponding to the candidate passenger flow indicator are weighted and summed to obtain the score corresponding to the candidate passenger flow indicator; the candidate passenger flow indicators are sorted according to the score from largest to smallest to obtain a candidate passenger flow indicator sequence, and the first preset number of candidate passenger flow indicators in the candidate passenger flow indicator sequence are determined as the target passenger flow indicator.

[0081] In implementation, after determining candidate passenger flow indicators based on the first and second relevance, the terminal, for each candidate passenger flow indicator, can perform a weighted sum of the first relevance of the candidate passenger flow indicator determined in step 201 based on the multi-factor correlation model and the task causality corresponding to the candidate passenger flow indicator determined in step 103. The sum is then used as the score of the candidate passenger flow indicator. The weights of the first relevance and task causality can be preset; they can be the same (e.g., both are 1) or different (e.g., the weight of task causality can be set to be greater than the weight of the first relevance). Optionally, the first relevance and task causality corresponding to each candidate passenger flow indicator can be normalized first, and then the normalized data can be weighted and summed to obtain the score of each candidate passenger flow indicator. Then, the terminal can sort the candidate passenger flow indicators from largest to smallest according to their scores to obtain a candidate passenger flow indicator sequence, and determine the first preset number of candidate passenger flow indicators in the candidate passenger flow indicator sequence as target passenger flow indicators.

[0082] Optionally, the terminal can sort the candidate passenger flow indicators from highest to lowest score to obtain a candidate passenger flow indicator sequence, and determine the top preset number of candidate passenger flow indicators as preferred passenger flow indicators. Then, the terminal can determine the indicator benefit of each preferred passenger flow indicator based on the slope of the single-factor correlation model (see step 202) corresponding to the preferred passenger flow indicator and a preset indicator benefit determination strategy. The indicator benefit represents the return on investment of the passenger flow indicator. That is, if according to the single-factor correlation model (y = kx... a +m), increase the passenger flow data x for this passenger flow indicator. a This can increase the amount of task completion y; however, due to the different slopes k, the amount of task completion y varies with the passenger flow index x. a The rates of change are different. Therefore, the slope k corresponding to each preferred passenger flow indicator can be normalized to the same dimension to obtain the indicator benefit of each preferred passenger flow indicator. Then, the terminal can determine the preferred passenger flow indicators whose indicator benefit meets preset conditions as the target passenger flow indicators. For example, the preset conditions can be greater than a preset threshold, or a preset number in the order of size.

[0083] In this embodiment, a weighted sum of the first relevance and task causality is used as the score for the candidate passenger flow indicator. Then, target passenger flow indicators (a predetermined number of candidate indicators with higher scores) are selected based on these scores. The score of the candidate passenger flow indicator incorporates information from both the first relevance and task causality dimensions, resulting in higher accuracy for the target passenger flow indicators determined based on the score. Furthermore, the return on investment (indicator benefit) of the passenger flow indicator can be further considered to further filter the indicators, ensuring that the determined target passenger flow indicators better meet the needs of the target audience.

[0084] In one embodiment, task relevance corresponds to two types: positive correlation and negative correlation, and there are multiple target passenger flow indicators. The process of generating the target resource configuration strategy in step 104 above specifically includes the following steps: in the preset mapping relationship between passenger flow indicators and resource items, determine the target resource item corresponding to each target passenger flow indicator; based on the task relevance type of each target passenger flow indicator, the target resource item, and the preset strategy template information, generate the target resource configuration strategy for the target object to execute the target task.

[0085] In implementation, a pre-established mapping relationship between passenger flow indicators and resource items can be established, where one passenger flow indicator can correspond to several resource items. If the target object adds a resource item corresponding to a passenger flow indicator in the configuration mapping relationship, the passenger flow data corresponding to that indicator can be increased; conversely, if the resource item corresponding to a passenger flow indicator is reduced, the passenger flow data corresponding to that indicator can be decreased. The terminal can determine the target resource item corresponding to each target passenger flow indicator in this pre-mapping relationship. The strategy template information can include first strategy template information corresponding to positively correlated task relevance and second strategy template information corresponding to negatively correlated task relevance. If the task relevance of all target passenger flow indicators is positively correlated (or all is negatively correlated), the terminal can obtain the first strategy template information (or the second strategy template information) and replace the preset replacement item in the template information with the target resource item to obtain the target resource configuration strategy. If each target passenger flow indicator includes two types of passenger flow indicators: positively correlated and negatively correlated, the terminal can obtain the first strategy template information and the second strategy template information, replace the preset replacement item in the first strategy template information with the target resource item corresponding to the positively correlated target passenger flow indicator, replace the preset replacement item in the second strategy template information with the target resource item corresponding to the negatively correlated target passenger flow indicator, and then integrate the replaced first strategy template information and the second strategy template information to obtain the target resource configuration strategy.

[0086] This embodiment provides a specific implementation method for generating target resource configuration strategies. The generated resource configuration strategies have high accuracy and meet the needs of the target object and the actual situation of the target task.

[0087] In one embodiment, the method further includes the following step: in response to a policy display instruction, displaying the target resource configuration policy on the display interface of the target object's business system.

[0088] In implementation, the terminal can respond to a strategy display command and display the target resource configuration strategy on the display interface of the target object's business system. For example, the business system's display interface can display a strategy display button. When the user clicks this button, the terminal can display the content of the target resource configuration strategy on the current page based on the content of the target resource configuration strategy and preset page configuration information. Understandably, the user can also select different tasks (car order tasks for different car models) on the business system's display interface and then click the strategy display button. The terminal can then respond to the strategy display command, designate the user-selected task as the target task, retrieve historical data of sample objects executing the target task from the database, generate the corresponding target resource configuration strategy, and display the content of the target resource configuration strategy on the current page of the business system for the user to view. Optionally, the terminal can also display the content of the target resource configuration strategy, target customer flow indicators, resource items corresponding to the target customer flow indicators, and the task relevance type (positive or negative) of the target customer flow indicators, etc., to facilitate the user's understanding of the specific content of the target resource configuration strategy and the relevant indicator information corresponding to the strategy, assisting the user in making the final resource configuration strategy decision.

[0089] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0090] Based on the same inventive concept, this application also provides a resource allocation strategy generation apparatus for implementing the resource allocation strategy generation method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more resource allocation strategy generation apparatus embodiments provided below can be found in the limitations of the resource allocation strategy generation method described above, and will not be repeated here.

[0091] In one embodiment, such as Figure 3As shown, a resource allocation strategy generation device 300 is provided, including: an acquisition module 301, a first determination module 302, a second determination module 303, and a generation module 304, wherein:

[0092] The acquisition module 301 is used to acquire historical passenger flow data and historical task completion volume corresponding to various passenger flow indicators generated by the sample object in performing the target task.

[0093] The first determining module 302 is used to construct a correlation model based on the historical passenger flow data and historical task completion volume corresponding to each passenger flow indicator, determine the task relevance corresponding to each passenger flow indicator according to the correlation model, and determine the passenger flow indicators whose task relevance meets the first preset condition as candidate passenger flow indicators; the task relevance represents the correlation strength between the passenger flow indicator and the task completion volume.

[0094] The second determining module 303 is used to determine the task causality corresponding to each candidate passenger flow indicator based on the historical passenger flow data and historical task completion amount corresponding to each candidate passenger flow indicator, using a causal relationship model, and to determine the candidate passenger flow indicator whose task causality satisfies the second preset condition as the target passenger flow indicator; the task causality represents the strength of the causal relationship between the passenger flow indicator and the task completion amount.

[0095] The generation module 304 is used to generate a target resource configuration strategy for the target object to perform the target task based on the target passenger flow index and the preset strategy generation rules.

[0096] In one embodiment, the first determining module 302 is specifically used to: train a machine learning model based on historical passenger flow data and historical task completion volume corresponding to multiple passenger flow indicators; determine the trained machine learning model as a multi-factor correlation model; and determine the first correlation degree corresponding to each passenger flow indicator according to the weights corresponding to each passenger flow indicator in the multi-factor correlation model; for each passenger flow indicator, perform linear fitting on the historical passenger flow data and historical task completion volume corresponding to the passenger flow indicator to obtain a single-factor correlation model corresponding to the passenger flow indicator; and determine the second correlation degree corresponding to the passenger flow indicator according to the determination coefficient of the single-factor correlation model; and determine the passenger flow indicators among the passenger flow indicators whose first correlation degree and second correlation degree satisfy the first preset condition as candidate passenger flow indicators.

[0097] In one embodiment, the first determining module 302 is specifically used to: sort each passenger flow indicator from largest to smallest according to the first relevance to obtain a passenger flow indicator sequence, and determine the first preset number of passenger flow indicators in the passenger flow indicator sequence as preliminary passenger flow indicators; and determine the preliminary passenger flow indicators among the preliminary passenger flow indicators whose second relevance is greater than a preset threshold as candidate passenger flow indicators.

[0098] In one embodiment, the second determining module 303 is specifically used to: for each candidate passenger flow indicator, perform a weighted summation of the first relevance and task causality corresponding to the candidate passenger flow indicator to obtain the score corresponding to the candidate passenger flow indicator; sort each candidate passenger flow indicator according to the score from largest to smallest to obtain a candidate passenger flow indicator sequence, and determine the first preset number of candidate passenger flow indicators in the candidate passenger flow indicator sequence as the target passenger flow indicator.

[0099] In one embodiment, task relevance can be either positive or negative; there are multiple target passenger flow indicators. The generation module 304 is specifically used to: determine the target resource item corresponding to each target passenger flow indicator in a preset mapping relationship between passenger flow indicators and resource items; and generate a target resource configuration strategy for the target object to execute the target task based on the task relevance type of each target passenger flow indicator, the target resource item, and preset strategy template information.

[0100] In one embodiment, the device further includes a display module for displaying the target resource configuration policy on the display interface of the target object's business system in response to a policy display instruction.

[0101] Each module in the above-mentioned resource allocation strategy generation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0102] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for generating a resource allocation strategy. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0103] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0104] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0105] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0106] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0107] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0108] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0109] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0110] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for generating a resource allocation strategy, characterized in that, The method includes: Obtain historical passenger flow data and historical task completion volume corresponding to various passenger flow indicators generated by the sample object performing the target task; A correlation model is constructed based on the historical passenger flow data corresponding to each of the aforementioned passenger flow indicators and the historical task completion volume. The task relevance corresponding to each of the aforementioned passenger flow indicators is determined according to the correlation model. Passenger flow indicators whose task relevance meets a first preset condition are identified as candidate passenger flow indicators. The task relevance represents the correlation strength between the passenger flow indicator and the task completion volume. The first preset condition is that the task relevance is greater than a preset threshold. Based on the historical passenger flow data and historical task completion volume corresponding to each candidate passenger flow indicator, a causal relationship model is used to determine the task causality corresponding to each candidate passenger flow indicator, and the candidate passenger flow indicators whose task causality satisfies the second preset condition are determined as target passenger flow indicators; the task causality represents the strength of the causal relationship between the passenger flow indicator and the task completion volume; the second preset condition is that the task causality is greater than a preset threshold or a preset number of indicators ranked first according to the size of the task causality. Based on the target passenger flow index and the preset strategy generation rules, a target resource allocation strategy is generated for the target object to execute the target task; The step of generating a target resource allocation strategy for the target object to perform the target task based on the target passenger flow index and preset strategy generation rules includes: In the preset mapping relationship between passenger flow indicators and resource items, the target resource items corresponding to each target passenger flow indicator are determined; based on the task relevance type of each target passenger flow indicator, the target resource items, and the preset strategy template information, a target resource configuration strategy for the target object to execute the target task is generated.

2. The method according to claim 1, characterized in that, The process involves constructing a correlation model based on historical passenger flow data corresponding to each of the aforementioned passenger flow indicators and the historical task completion volume; determining the task relevance corresponding to each of the aforementioned passenger flow indicators based on the correlation model; and identifying passenger flow indicators whose task relevance satisfies a first preset condition as candidate passenger flow indicators, including: A machine learning model is trained based on the historical passenger flow data corresponding to the various passenger flow indicators and the historical task completion volume. The trained machine learning model is determined as a multi-factor correlation model. Based on the weights of each passenger flow indicator in the multi-factor correlation model, the first correlation degree corresponding to each passenger flow indicator is determined. For each of the aforementioned passenger flow indicators, the historical passenger flow data corresponding to the passenger flow indicator and the historical task completion amount are linearly fitted to obtain a single-factor correlation model corresponding to the passenger flow indicator, and the second correlation degree corresponding to the passenger flow indicator is determined based on the determination coefficient of the single-factor correlation model. Among the various passenger flow indicators, the passenger flow indicators whose first correlation and second correlation satisfy the first preset condition are determined as candidate passenger flow indicators.

3. The method according to claim 2, characterized in that, The step of determining the passenger flow indicators among the various passenger flow indicators that satisfy the first correlation and the second correlation conditions as candidate passenger flow indicators includes: The passenger flow indicators are sorted from largest to smallest according to the first correlation to obtain a passenger flow indicator sequence, and the first preset number of passenger flow indicators in the passenger flow indicator sequence are determined as the initial passenger flow indicators. Among the preliminary passenger flow indicators, the preliminary passenger flow indicators whose second correlation is greater than a preset threshold are determined as candidate passenger flow indicators.

4. The method according to claim 2, characterized in that, The step of determining the candidate passenger flow indicators that satisfy the second preset condition in terms of task causality among the candidate passenger flow indicators includes: For each candidate passenger flow indicator, the first relevance and task causality corresponding to the candidate passenger flow indicator are weighted and summed to obtain the score corresponding to the candidate passenger flow indicator; The candidate passenger flow indicators are sorted from largest to smallest according to their scores to obtain a candidate passenger flow indicator sequence, and the first preset number of candidate passenger flow indicators in the candidate passenger flow indicator sequence are determined as target passenger flow indicators.

5. The method according to claim 1, characterized in that, The task relevance has two types: positive correlation and negative correlation; there are multiple target passenger flow indicators.

6. The method according to claim 1, characterized in that, The method further includes: In response to the policy display instruction, the target resource configuration policy is displayed on the display interface of the target object's business system.

7. A resource allocation strategy generation apparatus, characterized in that, The device includes: The acquisition module is used to acquire historical passenger flow data and historical task completion volume corresponding to various passenger flow indicators generated by the sample object in performing the target task; The first determining module is used to construct a correlation model based on the historical passenger flow data corresponding to each of the passenger flow indicators and the historical task completion volume, determine the task relevance corresponding to each of the passenger flow indicators according to the correlation model, and determine the passenger flow indicators whose task relevance meets the first preset condition as candidate passenger flow indicators; the task relevance represents the correlation strength between the passenger flow indicator and the task completion volume; the first preset condition is that the task relevance is greater than a preset threshold. The second determining module is used to determine the task causality corresponding to each candidate passenger flow indicator based on the historical passenger flow data and the historical task completion amount, using a causal relationship model, and to determine the candidate passenger flow indicators whose task causality satisfies a second preset condition as target passenger flow indicators; the task causality represents the strength of the causal relationship between the passenger flow indicator and the task completion amount; the second preset condition is that the task causality is greater than a preset threshold or a preset number of indicators ranked first according to the size of the task causality. The generation module is used to generate a target resource configuration strategy for the target object to perform the target task based on the target passenger flow index and the preset strategy generation rules. The generation module is specifically used to determine the target resource item corresponding to each target passenger flow indicator in the preset mapping relationship between passenger flow indicators and resource items; and to generate a target resource configuration strategy for the target object to execute the target task based on the task relevance type of each target passenger flow indicator, the target resource item and the preset strategy template information.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

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

Images