Mission planning method and device

Abstract

Embodiments of this specification provide a task planning method and apparatus, wherein the task planning method includes: obtaining at least one associated feature of a target task; determining, based on each associated feature, the task execution results of the target task under multiple preset execution strategies; comparing the task execution results under each preset execution strategy to determine the execution impact of each associated feature on the target task; and determining a target execution strategy for the target task based on the execution impact of each associated feature on the target task. This method can effectively improve the efficiency and accuracy of task planning, thereby increasing gains.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of artificial intelligence technology, and in particular to a task planning method. Background Art

[0002] As market competition becomes increasingly fierce, equity penetration and marketing methods have become the core strategies and growth points for businesses or service providers to expand markets and promote their products.

[0003] In the existing technology, merchants or service providers generally enhance their competitiveness through promotional activities. Hundreds of promotional activities are offered, but the only significant impact for merchants or service providers is growth in new users and gross merchandise volume (GMV). These macroeconomic indicators cannot scientifically and accurately measure the true effectiveness of promotional activities, identify the factors influencing them, or provide guidance for improving the effectiveness of subsequent promotional activities. Therefore, an effective solution is urgently needed to address these issues. Summary of the Invention

[0004] In view of this, embodiments of this specification provide a task planning method. One or more embodiments of this specification also relate to a task planning apparatus, a computing device, a computer-readable storage medium, and a computer program to address technical deficiencies in the prior art.

[0005] According to a first aspect of an embodiment of this specification, a task planning method is provided, comprising:

[0006] Obtain at least one relevant feature of the target task;

[0007] Determining, based on the associated features, task execution results of the target task under multiple preset execution strategies;

[0008] Comparing the task execution results under each preset execution strategy to determine the execution impact of each associated feature on the target task;

[0009] A target execution strategy for the target task is determined according to the execution impact of each of the associated features on the target task.

[0010] Optionally, obtaining at least one associated feature of the target task includes:

[0011] Get the attribute information of the target task;

[0012] At least one associated feature of the target task is determined based on the attribute information.

[0013] Optionally, determining at least one associated feature of the target task based on the attribute information includes:

[0014] Determining task influencing factors of the target task based on the attribute information;

[0015] The task influencing factors are integrated to obtain a correlation feature set, wherein the correlation feature set includes at least one correlation feature.

[0016] Optionally, determining the task execution results of the target task under multiple preset execution strategies based on the associated features includes:

[0017] Based on the associated features, configure multiple preset execution strategies and task execution indicators corresponding to the target task;

[0018] Execute each preset execution strategy and obtain the initial task execution results corresponding to each preset execution strategy;

[0019] According to the task execution indicator and the initial task execution result, a target task execution result of the target task under a plurality of preset execution strategies is determined.

[0020] Optionally, configuring a plurality of preset execution strategies and task execution indicators corresponding to the target task based on the associated features includes:

[0021] For any associated feature among the associated features, obtain multiple configuration parameters corresponding to the associated feature;

[0022] According to the multiple configuration parameters under the association feature, multiple preset execution strategies and task execution indicators corresponding to the association feature are configured.

[0023] Optionally, comparing the task execution results under each preset execution strategy to determine the execution impact of each associated feature on the target task includes:

[0024] Compare the task execution results under each preset execution strategy to determine the task execution rate of each associated feature;

[0025] The execution influence of each associated feature relative to the target task is calculated according to the task execution rate of each associated feature.

[0026] Optionally, the associated feature carries a feature type;

[0027] Determining a target execution strategy for the target task based on the execution impact of each of the associated features on the target task includes:

[0028] Adjusting the feature type of each associated feature based on the impact of each associated feature on the execution of the target task;

[0029] Re-determining multiple preset execution strategies for the target task based on the associated features and the feature types of the associated features, and continuing to perform the step of determining the task execution results of the target task under the multiple preset execution strategies;

[0030] In a case where a change rate of the execution influence of each associated feature relative to the target task is less than a preset threshold, a target execution strategy for the target task is determined.

[0031] Optionally, adjusting the feature type of each associated feature based on the execution impact of each associated feature on the target task includes:

[0032] For the associated feature whose feature type is a latent type, if the impact of the associated feature on the execution of the target task is greater than a preset first impact threshold, adjusting the feature type of the associated feature to an explicit type;

[0033] For the associated feature whose feature type is an explicit type, if the impact of the associated feature on the execution of the target task is less than a preset second impact threshold, the feature type of the associated feature is adjusted to an inert type.

[0034] Optionally, re-determining a plurality of preset execution strategies for the target task based on the associated features and the feature types of the associated features includes:

[0035] A plurality of preset execution strategies of the target task are re-determined according to the target-related features in each of the related features, wherein the feature type of the target-related features is an explicit type or an implicit type.

[0036] According to a second aspect of the embodiments of this specification, a task planning device is provided, comprising:

[0037] an acquisition module, configured to acquire at least one associated feature of a target task;

[0038] A task execution result determination module is configured to determine the task execution result of the target task under multiple preset execution strategies based on the associated features;

[0039] An execution impact determination module is configured to compare the task execution results under each preset execution strategy and determine the execution impact of each associated feature relative to the target task;

[0040] The target execution strategy determination module is configured to determine the target execution strategy of the target task according to the execution influence of each of the associated features on the target task.

[0041] According to a third aspect of an embodiment of this specification, a computing device is provided, including:

[0042] memory and processor;

[0043] 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 task planning method are implemented.

[0044] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the above-mentioned task planning method are implemented.

[0045] According to a fifth aspect of the embodiments of this specification, a computer program is provided, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned task planning method.

[0046] The task planning method provided in this specification obtains at least one associated feature of a target task; based on each associated feature, determines the task execution result of the target task under multiple preset execution strategies; compares the task execution results under each preset execution strategy to determine the execution impact of each associated feature relative to the target task; and determines the target execution strategy of the target task based on the execution impact of each associated feature relative to the target task. By obtaining at least one associated feature of the target task, the associated features of the target task are abstracted and summarized, not only obtaining the task execution result of each target task, but also determining the execution impact of each associated feature relative to the target task, and then summarizing and guiding the target execution strategy of the target task based on the execution impact, thereby improving the efficiency and accuracy of task planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a flowchart of a task planning method provided by one embodiment of this specification;

[0048] Figure 2A This is a page diagram of a task execution result in a task planning method provided by an embodiment of this specification;

[0049] Figure 2B This is a schematic diagram of the effect of executing the impact degree in a task planning method provided by one embodiment of this specification;

[0050] Figure 2C This is a page diagram of a target execution strategy in a task planning method provided by an embodiment of this specification;

[0051] Figure 2DThis is a page diagram of an associated feature list in a task planning method provided by an embodiment of this specification;

[0052] Figure 2E This is a flowchart of a task planning method provided by an embodiment of this specification;

[0053] Figure 2F This is a flowchart of an iterative process of associated features in a task planning method provided by an embodiment of this specification;

[0054] Figure 2G This is a flowchart of determining a target execution strategy in a task planning method provided by one embodiment of this specification;

[0055] Figure 3 This is a process flow chart of a task planning method provided by one embodiment of this specification;

[0056] Figure 4 This is a schematic diagram of the structure of a task planning device provided by one embodiment of this specification;

[0057] Figure 5 This is a structural block diagram of a computing device provided by one embodiment of this specification. DETAILED DESCRIPTION

[0058] The following description sets forth many specific details to facilitate a thorough understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the scope of this specification. Therefore, this specification is not limited to the specific implementations disclosed below.

[0059] The terms used in one or more embodiments of this specification are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of this specification. The singular forms "a," "the," and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0060] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0061] First, the terms involved in one or more embodiments of this specification are explained.

[0062] The associated feature set, also known as the factor model, is a set of task rules that is highly abstracted from equity. It has a two-layer structure, including a general factor layer and an equity-specific factor layer.

[0063] Measurement engine: Verify the standard workflow of task execution results and efficiently ensure the scientific nature of the results and conclusions.

[0064] Equity measurement: The use of equity is affected by multiple related features (such as different groups of people, different orders, different discount methods, etc.). Equity measurement is to measure which rule-related features the equity is affected by, the degree of influence, and whether it is a positive or negative impact.

[0065] Task execution results: How much incremental revenue can a task execution bring to the platform side (promoting AB plans, promoting orders, promoting purchases, etc.), how much incremental value can it bring to the channel side, whether the subsequent user behavior of active users is affected, whether they will repurchase, etc.

[0066] Then, the task planning method provided in this manual is briefly described.

[0067] As market competition becomes increasingly fierce, equity penetration and marketing methods have become the core strategies and growth points for businesses or service providers to expand markets and promote their products.

[0068] In the prior art, merchants or service providers generally improve their competitiveness by carrying out promotional activities. There are hundreds of various promotional activities, but the only activity effects that merchants or service providers can pay attention to are the growth of new users and the growth of gross merchandise volume (GMV). These macro data cannot scientifically and accurately measure the real effect of promotional activities and determine the influencing factors of promotional activities, and they cannot provide guidance for improving the effectiveness of subsequent promotional activities. For example, a pure A / B testing scheme extracts a portion of regular website traffic users who do not match the discount, and other users who match the discount, and then compares the results to obtain the incremental effect. This conventional comparison scheme is difficult to correspond to the specific "Angry Me" rules, and attribution cannot be found. Moreover, the experiments of each activity have no continuity, and lack scientific reference significance for the next activity.

[0069] Therefore, this specification provides a task planning method, which obtains at least one associated feature of a target task; based on each associated feature, determines the task execution result of the target task under multiple preset execution strategies; compares the task execution results under each preset execution strategy to determine the execution impact of each associated feature relative to the target task; and determines the target execution strategy of the target task based on the execution impact of each associated feature relative to the target task. By obtaining at least one associated feature of the target task, the associated features of the target task are abstracted and summarized, not only obtaining the task execution result of each target task, but also determining the execution impact of each associated feature relative to the target task, and then summarizing and guiding the target execution strategy of the target task based on the execution impact, thereby improving the efficiency and accuracy of task planning.

[0070] In this specification, a task planning method is provided. This specification also relates to a task planning device, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.

[0071] See also Figure 1 , Figure 1 A flowchart of a task planning method provided by an embodiment of this specification is shown, which specifically includes the following steps.

[0072] Step 102: Obtain at least one associated feature of the target task.

[0073] The execution subject of the task planning method can be a computing device with a task planning function, such as a server or terminal with a task planning function.

[0074] Specifically, tasks can be various purposeful activities that people engage in in their daily life, work, and entertainment activities, such as work assigned by superiors, responsibilities undertaken, or a promotional activity, etc. They can also be basic work units in computers; target tasks refer to tasks to be planned; associated features refer to features associated with target tasks, that is, factors that affect the execution of target tasks, such as execution time, execution location, execution order, etc.

[0075] In actual applications, there are many ways to obtain at least one associated feature of the target task. For example, an operator can send a task planning instruction to the execution entity, or send an instruction to obtain at least one associated feature of the target task. Accordingly, after receiving the instruction, the execution entity begins to obtain at least one associated feature of the target task. Alternatively, a server can automatically obtain at least one associated feature of the target task at preset intervals. For example, after a preset period of time, a server with a task planning function automatically obtains at least one associated feature of the target task; or after a preset period of time, a terminal with a task planning function automatically obtains at least one associated feature of the target task. This specification does not impose any restrictions on the method of obtaining at least one associated feature of the target task.

[0076] Exemplarily, if the target task is an object data storage task, then three associated features of the object data storage task are obtained: storage area, data volume, and data type.

[0077] In one or more optional embodiments of this specification, tasks in different fields have different associated features. To improve the completeness and accuracy of the associated features, the associated features can be acquired based on the attribute information of the target task. Specifically, the process of acquiring at least one associated feature of the target task can be as follows:

[0078] Get the attribute information of the target task;

[0079] At least one associated feature of the target task is determined based on the attribute information.

[0080] Specifically, attribute information refers to information related to the attributes of the target task, such as the field information corresponding to the target task, the name of the target task, the technical means corresponding to the target task, the task content of the target task, etc.

[0081] In practical applications, the target task can be analyzed to determine the attribute information of the target task. Then, based on the attribute information of the target task, the associated features related to the attribute information can be determined. For example, the associated features related to the attribute information can be queried from a preset associated feature library, where the associated feature library stores multiple associated features stored in association with the attribute information. Another example is that the attribute information of the target task is displayed through a client for the user to view, and after viewing the attribute information, at least one associated feature of the target task is uploaded through the client. In this way, determining at least one associated feature of the target task solely based on the attribute information of the target task can not only improve the efficiency of obtaining associated features, but also ensure the integrity of the acquired associated features, thereby improving the efficiency and accuracy of task planning based on associated features.

[0082] For example, if the target task is a cargo transport task, then analysis of the cargo transport task can determine that the attribute information of the cargo transport task is vehicle scheduling. Based on vehicle scheduling, the associated features of the cargo transport task can be determined to include: transportation mode, vehicle type, delivery time, etc.

[0083] In one or more optional embodiments of this specification, it is also possible to first obtain task influencing factors on the target task based on the attribute information, and then determine the associated features based on the task influencing factors. In other words, the at least one associated feature of the target task is determined based on the attribute information. The specific implementation process can be as follows:

[0084] Determining task influencing factors of the target task based on the attribute information;

[0085] The task influencing factors are integrated to obtain a correlation feature set, wherein the correlation feature set includes at least one correlation feature.

[0086] Specifically, a task influencing factor refers to anything that affects the execution of the target task, such as the network status of the download task and the size of the downloaded content; and a correlation feature set refers to a collection of correlation features.

[0087] In practical applications, after analyzing the target task and determining its attribute information, task influencing factors for the target task are further obtained based on the attribute information. For example, task influencing factors associated with the attribute information can be retrieved from a preset task influencing factor library, where the library stores multiple task influencing factors associated with the attribute information. Alternatively, the attribute information of the target task can be displayed on a client for the user to view. After viewing the attribute information, the task influencing factors of the target task can be uploaded via the client. After determining the task influencing factors of the target task, the task influencing factors are abstracted, that is, integrated to obtain a set of at least one associated features, i.e., an associated feature set. In this way, determining the task influencing factors of the target task solely based on the attribute information of the target task, and then determining at least one associated feature based on the task influencing factors, not only improves the efficiency of acquiring associated features, but also ensures the completeness and accuracy of the acquired associated features, thereby improving the efficiency and accuracy of task planning based on associated features.

[0088] For example, the target task is a cargo transport task, and the attribute information for the cargo transport task is vehicle scheduling. The attribute information "vehicle scheduling" can be obtained, and the factors affecting the cargo transport task can be determined to include route status, vehicle information, and user needs. These factors are then integrated and abstracted to obtain the associated feature set "transportation mode, vehicle type, delivery time, etc." That is, the associated features of the cargo transport task include: transportation mode, vehicle type, and delivery time.

[0089] Step 104: Based on the associated features, determine the task execution results of the target task under multiple preset execution strategies.

[0090] After obtaining at least one associated feature of the target task, further, task execution results of the target task under multiple preset execution strategies are determined according to each associated feature.

[0091] Specifically, the preset execution strategy refers to the method, steps or manner of executing the target task; the task execution result refers to the result of executing the target task according to a preset execution strategy.

[0092] In practical applications, different preset execution strategies can be set based on the associated features. The target task is then executed according to each preset execution strategy. After execution, the target task's execution results under the multiple preset execution strategies are obtained. For example, two preset execution strategies are set based on the associated features: Preset Execution Strategy 1 and Preset Execution Strategy 2. Then, executing the target task according to Preset Execution Strategy 1 results in Task Execution Result 3, while executing the target task according to Preset Execution Strategy 2 results in Task Execution Result 4.

[0093] It should be noted that one or more preset execution strategies may be set for any one correlation feature, or multiple preset execution strategies may be set for any number of correlation features among multiple correlation features, which is not limited in this specification.

[0094] Since the task execution results may be a comprehensive result from multiple aspects, in reality, only one or several aspects of the task results may be needed. Therefore, task execution indicators can be set for the target task. After obtaining the initial task execution results, the initial task execution results are filtered based on the task execution indicators to obtain the target task execution results. In other words, based on the various associated features, the task execution results of the target task under multiple preset execution strategies are determined. The specific implementation process can be as follows:

[0095] Based on the associated features, configure multiple preset execution strategies and task execution indicators corresponding to the target task;

[0096] Execute each preset execution strategy and obtain the initial task execution results corresponding to each preset execution strategy;

[0097] According to the task execution indicator and the initial task execution result, a target task execution result of the target task under a plurality of preset execution strategies is determined.

[0098] Specifically, a task execution metric refers to a specific aspect of a task's execution parameters, such as task execution rate, task execution duration, and task completion. An initial task execution result refers to the result obtained directly after executing the target task; a target task execution result refers to the portion of the initial task execution result that is relevant to the task execution metric.

[0099] In practical applications, different preset execution strategies and the same task execution indicators can be set according to the associated features. Then, the target task is executed based on multiple preset execution strategies to obtain multiple initial task execution results, wherein the preset execution strategies correspond to the initial task execution results one by one. Furthermore, based on the task execution indicators, the target task execution results corresponding to the task execution indicators are extracted from each initial task execution result. In this way, the initial task execution results are screened based on the task execution indicators to obtain the target task execution results. This not only improves the accuracy and efficiency of obtaining the target task execution results, but also reduces the processing of data irrelevant to the initial task execution results, that is, reduces the amount of data processing, and further improves the efficiency of task planning.

[0100] For example, the target task is selling mobile phones. The associated features of selling mobile phones include price, payment method, and sales location. Preset execution strategies a1 and a2 are determined based on the price, payment method, and sales location. When executing the mobile phone selling task according to preset execution strategy a1, the initial task execution result b1 is: 5 mobile phones sold for a total value of 6,000 yuan, and the sales time is 2 days. When executing the mobile phone selling task according to preset execution strategy a2, the initial task execution result b2 is: 7 mobile phones sold for a total value of 5,000 yuan, and the sales time is 3 days. If the task execution metric is the number of units sold, the target task execution result c1 for the target task under preset execution strategy a1 is: 5 mobile phones sold; and the target task execution result c2 for the target task under preset execution strategy a2 is: 7 mobile phones sold.

[0101] In addition, each associated feature can have multiple configuration parameters. In this case, the preset execution strategy and task execution indicators can be configured based on each configuration parameter. That is, based on each associated feature, multiple preset execution strategies and task execution indicators corresponding to the target task are configured. The specific implementation process can be as follows:

[0102] For any associated feature among the associated features, obtain multiple configuration parameters corresponding to the associated feature;

[0103] According to the multiple configuration parameters under the association feature, multiple preset execution strategies and task execution indicators corresponding to the association feature are configured.

[0104] Specifically, the configuration parameters refer to multiple execution parameters of the associated feature. For example, if the associated feature is country, the configuration parameters may be country A, country B, and country C.

[0105] In practical applications, the preset execution strategy and task execution indicators corresponding to each associated feature can be configured based on the multiple configuration parameters corresponding to that associated feature. This can improve the accuracy of the preset execution strategy, further enabling the rapid and accurate determination of the execution impact of the associated feature, and further improving the efficiency of task planning.

[0106] For example, the target task "Multi-video Download Task" has two associated features: the number of videos downloaded in parallel and the network speed. The number of videos downloaded in parallel has three configuration parameters: 1 and 5, and the network speed has the download speed for ordinary users and the download speed for members. For the associated feature "Number of videos downloaded in parallel," two preset execution strategies can be set: Preset execution strategy n1 uses the download speed of ordinary users and downloads one video in parallel, or uses the download speed of members and downloads one video in parallel; preset execution strategy n2 uses the download speed of ordinary users and downloads five videos in parallel, or uses the download speed of members and downloads five videos in parallel. The task execution indicator is the duration of downloading 50 videos.

[0107] Step 106: Compare the task execution results under each preset execution strategy to determine the execution impact of each associated feature on the target task.

[0108] After determining the task execution results of the target task under multiple preset execution strategies based on the respective associated features, the task execution results under the respective preset execution strategies are further compared to determine the execution impact of each associated feature on the target task.

[0109] Specifically, the execution impact refers to the degree of influence of the associated feature on the execution of the target task, that is, the sensitivity of the associated feature.

[0110] In practical applications, the task execution results under various preset execution strategies can be compared to determine the differences in task execution results under different preset execution strategies, and then the execution impact of the associated features on the target task can be determined based on the differences.

[0111] In one or more optional embodiments of the present specification, the task execution results under each preset execution strategy are compared to determine the execution impact of each associated feature on the target task. The specific implementation process may be as follows:

[0112] Compare the task execution results under each preset execution strategy to determine the task execution rate of each associated feature;

[0113] The execution influence of each associated feature relative to the target task is calculated according to the task execution rate of each associated feature.

[0114] Specifically, the task execution rate refers to the execution rate or completion index of the associated feature relative to the target task.

[0115] In practical applications, the task execution results under various preset execution strategies can be compared to calculate the task execution rate for each associated feature. Furthermore, the execution impact of each associated feature relative to the target task can be calculated. This allows for accurate and rapid calculation of the execution impact of the target task.

[0116] Generally, for any associated feature, two preset execution strategies are set: an experimental preset execution strategy and a control preset execution strategy. Therefore, when calculating the task execution rate for that associated feature, the task execution result corresponding to the experimental preset execution strategy can be subtracted from the task execution result corresponding to the control preset execution strategy. In other words, task execution rate = experimental task execution result - control task execution result, where the experimental task execution result is the task execution result corresponding to the experimental preset execution strategy, and the control task execution result is the task execution result corresponding to the control preset execution strategy.

[0117] In addition, when there are multiple configuration parameters under an associated feature, two preset execution policies can be set for any configuration parameter: an experimental preset execution policy and a control preset execution policy. For example, if an associated feature N has k configuration parameters: n1, n2, ..., nk, the experimental preset execution policy and the control preset execution policy are configured for n1, n2, ..., nk respectively. Then:

[0118] The task execution rate N1 corresponding to the configuration parameter n1 = experimental task execution result n11 - control task execution result n12

[0119] The task execution rate N2 corresponding to the configuration parameter n2 = experimental task execution result n21 - control task execution result n22

[0120] …

[0121] The task execution rate Nk corresponding to the configuration parameter nk = experimental task execution result nk1 - control task execution result nk2

[0122] Furthermore, the execution impact of the associated feature N can be determined by Formula 1.

[0123]

[0124] In formula 1, S 2 represents the execution impact of the associated feature N, k represents the number of configuration parameters, N i Indicates the task execution rate of the i-th configuration parameter.

[0125] For example, assume that in a payment scenario, the result of task execution is an increase in payment conversion rate, where payment conversion rate increase = experimental conversion rate - control conversion rate = number of successful experimental payments / number of experimental payment processes entering the payment process - number of successful control payments / number of control payment processes entering the payment process. If the execution impact of the factor "order type" is shown in Table 1:

[0126] Table 1 Task execution results of experimental preset execution strategy and control preset execution strategy

[0127]

[0128]

[0129] According to Table 1, we can calculate that the activity improvement rate R = 16.3344% - 14.8503% = 1.4841%, and the sensitivity is 1.77, which ranks the highest among all factors. We take the value set [seller drafts, buy immediately] that indicates the positive impact of this factor on the activity effect.

[0130] See also Figure 2A , Figure 2A This is a page diagram of a task execution result in a task planning method provided by an embodiment of the present specification: it mainly shows the task execution result of the preset execution strategy A / B corresponding to the target task of selling items, that is, the preset task execution strategy A / B-task execution result, and the associated features include the value of the item, whether it is anonymous, and the shipping location. The item value is taken as an example for explanation. The item value has three configuration parameters, [100-200), [200-300), and [300-400). For [100-200), the task execution result of the preset task execution strategy A is 10%, the task execution result of the preset task execution strategy B is 7%, and the task execution rate is 3%; for [200-300), the task execution result of the preset task execution strategy A is 9%, the task execution result of the preset task execution strategy B is 6%, and the task execution rate is 3%; for [300-400), the task execution result of the preset task execution strategy A is 5%, the task execution result of the preset task execution strategy B is 5%, and the task execution rate is 0. The total task fulfillment rate can be determined based on the total task fulfillment rate of the item value, anonymity, and shipping location.

[0131] See also Figure 2B , Figure 2BThis is a diagram showing the effect of execution impact in a task planning method provided in one embodiment of this specification: the target task is to sell items, the task indicator is the order success rate, and the target task's associated feature set includes three associated features: item value, anonymity, and shipping location. Item value has three configuration parameters: [100-200), [200-300), and [300-400), with an execution impact of 55; anonymity has two configuration parameters: anonymous and non-anonymous, with an execution impact of 0; and shipping location has three configuration parameters: location A, location B, and location C, with an execution impact of 31.

[0132] Step 108: Determine a target execution strategy for the target task based on the execution impact of each associated feature on the target task.

[0133] After comparing the task execution results under each preset execution strategy and determining the execution impact of each associated feature relative to the target task, further, based on the execution impact of each associated feature relative to the target task, a target execution strategy for the target task is determined.

[0134] In actual applications, after determining the execution impact of each associated feature relative to the target task, further, each associated feature is analyzed according to the execution impact, and the target execution strategy of the target task is determined according to the analysis results, or each associated feature is analyzed according to the execution impact, and multiple preset execution strategies of the target task are again determined according to the analysis results, and so on. If the analysis results meet the preset conditions, the target execution strategy of the target task is determined according to the analysis results.

[0135] Figure 2C This is a schematic diagram of a target execution strategy page in a task planning method provided by one embodiment of this specification: the target execution strategy's execution indicator is "********", and the strategy conclusion is "↑3%", indicating a 3% increase. The item value has three configuration parameters: [100-200), [200-300), and [300-400); anonymity has two configuration parameters: anonymous and non-anonymous; and the shipping location has three configuration parameters: A, B, and C. The strategy configuration is: item value - [200-300), anonymity - anonymous, and shipping location - B.

[0136] In one or more optional embodiments of this specification, each associated feature carries its corresponding feature type. After calculating the execution impact corresponding to each associated feature, the feature type of the associated feature can be adjusted based on the execution impact. Further, based on each associated feature and the feature type of each adjusted associated feature, the target execution strategy of the target task is determined. That is, when the associated feature carries a feature type, the target execution strategy of the target task is determined based on the execution impact of each associated feature relative to the target task. The specific implementation process can be as follows:

[0137] Adjusting the feature type of each associated feature based on the impact of each associated feature on the execution of the target task;

[0138] Re-determining multiple preset execution strategies for the target task based on the associated features and the feature types of the associated features, and continuing to perform the step of determining the task execution results of the target task under the multiple preset execution strategies;

[0139] In a case where a change rate of the execution influence of each associated feature relative to the target task is less than a preset threshold, a target execution strategy for the target task is determined.

[0140] Specifically, the feature type represents the type or category of the associated feature under the target task, such as inert type, explicit type, and implicit type; the change rate refers to the degree of change; and the preset threshold refers to a pre-set value used to measure the change rate.

[0141] In practical applications, after determining the execution impact of each associated feature relative to the target task, for any associated feature, the execution impact of the associated feature can be used to determine the feature type of the associated feature under the execution impact. If the feature type is different from the feature type carried by the associated feature, the feature type carried by the associated feature is adjusted. If they are the same, no adjustment is required. Then all associated features are traversed. Further, based on each associated feature and the feature type of each associated feature, multiple preset execution strategies for the target task are re-determined, and the task execution results of the target task under the multiple preset execution strategies are continued to be determined, and so on, until the rate of change of the execution impact of each associated feature relative to the target task is less than a preset threshold, and then the target execution strategy of the target task is determined based on each associated feature and the feature type of each associated feature. In this way, multiple iterative cycles can make each associated feature and the execution impact of each associated feature tend to be stable, that is, improve the accuracy of the feature type of each associated feature finally determined, and thus improve the efficiency and accuracy of task planning.

[0142] In one or more optional embodiments of this specification, for associated features of different feature types, the feature types need to be adjusted separately. That is, based on the impact of each associated feature on the execution of the target task, the feature type of each associated feature is adjusted. The specific implementation process can be as follows:

[0143] For the associated feature whose feature type is a latent type, if the impact of the associated feature on the execution of the target task is greater than a preset first impact threshold, adjusting the feature type of the associated feature to an explicit type;

[0144] For the associated feature whose feature type is an explicit type, if the impact of the associated feature on the execution of the target task is less than a preset second impact threshold, the feature type of the associated feature is adjusted to an inert type.

[0145] Specifically, the implicit type refers to the type of associated features that will not be used in the configuration of the preset execution strategy. The associated features of the implicit type will not interfere with the task execution results. The associated features that exist in the task and may affect the task execution results will be converted into the explicit type when their execution impact reaches a certain threshold; the explicit type refers to the type of associated features used in the preset execution strategy. The associated features of the explicit type interfere with the task execution results. When their execution impact is low to a certain threshold, they will be converted into the inert type; the inert type refers to the type of associated features that are standard in the preset execution strategy. The execution impact of the associated features of the inert type is constant and can no longer interfere with the activity effect; the first impact threshold refers to a pre-set value used to measure whether the implicit type can be converted into the explicit type; the second impact threshold refers to a pre-set value used to measure whether the explicit type can be converted into the inert type.

[0146] In practical applications, for any implicit type of associated feature, determine whether the impact of the associated feature on the execution of the target task is greater than the first impact threshold. If so, adjust the feature type of the associated feature from implicit to explicit. If not, maintain the feature type of the associated feature as implicit. For any explicit type of associated feature, determine whether the impact of the associated feature on the execution of the target task is less than the second impact threshold. If so, adjust the feature type of the associated feature from explicit to inert. If not, maintain the feature type of the associated feature as explicit.

[0147] In addition, the associated features with small execution impact can be marked as lazy types, and the associated features with large execution impact can be marked as lazy types. The value set of the three associated features with the highest execution impact on the task execution results is taken to recalculate the task execution rate, that is, the new task execution rate = the new experimental task execution result - the control task execution result.

[0148] See also Figure 2D , Figure 2D This is a page diagram of an associated feature list in a task planning method provided by an embodiment of the present specification: the associated feature list includes a label, associated features and feature types, wherein the associated feature with label 1 is a client type, and its feature type is an implicit type; the associated feature with label 2 is whether it is anonymous, and its feature type is an inert type; the associated feature with label 3 is an order type, and its feature type is an explicit type.

[0149] See also Figure 2E , Figure 2E This is a flowchart of a task planning method provided by an embodiment of this specification: first, the rights and interests rules are abstracted to obtain multiple factors, and a factor model is constructed, that is, multiple feature types, such as "interest point copywriting, resource segment, order type", and then the A / B plan and activity effect indicators are configured, such as "payment success rate, order success rate, payment channel penetration rate", that is, multiple preset execution strategies and execution indicators, and multiple factors are input into the measurement engine, and the A / B plan is calculated to obtain the task execution result. Afterwards, the measurement result is determined, and the impact of the factor on the task execution result is determined based on the task execution result, and the effect attribution is found to obtain the effect sequence, that is, the execution influence of the associated feature relative to the target task is determined, such as arranging factor x and factor y. Afterwards, the multiple preset execution strategies of the target task are re-determined based on the execution influence, and so on.

[0150] Figure 2F It is a flowchart of the iteration of associated features in a task planning method provided in an embodiment of this specification; factors are associated features, and factor models are multiple associated features. Through activities, N factors that are highly associated with task effects can be found. This solution divides these factors into layers according to their sensitivity, that is, according to the degree of execution influence. For example, the explicit factor layer, implicit factor layer, and inert factor layer are divided according to high sensitivity, medium sensitivity, and low sensitivity. After multiple rounds of iteration, the value sequence set of the Nth generation of factors can be iteratively evolved. Using this set greatly improves the task effect. At the same time, it can be seen that as the iterative evolution progresses, more and more implicit factors are transformed into explicit factors, and explicit factors are transformed into inert factors. Finally, the value sequence of the gameplay rules of the activity tends to be stable. At this time, the equity marketing plan in a certain scenario will also tend to be stable, and the task effect of the plan will get better and better.

[0151] Figure 2GThis is a flowchart of determining the target execution strategy in a task planning method provided in an embodiment of this specification; in a certain scenario, factors are also associated features, and factor sets are also multiple associated features. Through N generations of equity measurement and factor evolution, a fixed activity plan, that is, an execution strategy or a target execution strategy, can be obtained. For example, through the first execution strategy, a measurement result of 1 is obtained, and through the second execution strategy, a measurement result of 2 is obtained. And so on, the xth execution strategy is determined based on factors 1 and 2 in the factor set to guide the target task to obtain a better execution strategy, that is, the xth execution strategy = F (factor 1 + factor 2). When the sensitivity of each factor is averaged, the execution strategy tends to be stable, and the target execution strategy = C, that is, the sensitivity is averaged and the execution strategy is stable.

[0152] In one or more optional embodiments of the present specification, since the execution impact of the inert type associated features is constant and can no longer interfere with the activity effect, it is only necessary to redefine multiple preset execution strategies for the target task based on the inert type and the explicit type associated features. That is, based on the target associated features in each associated feature, the multiple preset execution strategies for the target task are redetermined, wherein the feature type of the target associated feature is an explicit type or an implicit type. In this way, multiple preset execution strategies are determined only based on the inert type and the explicit type associated features, which reduces the amount of data processing and can thereby improve the efficiency of task planning.

[0153] The task planning method provided in this specification obtains at least one associated feature of a target task; based on each associated feature, determines the task execution result of the target task under multiple preset execution strategies; compares the task execution results under each preset execution strategy to determine the execution impact of each associated feature relative to the target task; and determines the target execution strategy of the target task based on the execution impact of each associated feature relative to the target task. By obtaining at least one associated feature of the target task, the associated features of the target task are abstracted and summarized, not only obtaining the task execution result of each target task, but also determining the execution impact of each associated feature relative to the target task, and then summarizing and guiding the target execution strategy of the target task based on the execution impact, thereby improving the efficiency and accuracy of task planning.

[0154] Attribution can also be used as input for the next target task execution to continue evolution, essentially re-determining multiple preset execution strategies, forming a scientific, closed-loop, and highly reliable growth plan. By acquiring at least one associated feature of the target task and abstractly summarizing its associated features, the equity measurement engine can determine the impact of these features on the execution of the target task. By adjusting highly sensitive rule factors, the next marketing campaign plan can be guided. Through multiple rounds of campaigns and rule factor adjustments, a stable rule factor configuration can be iteratively evolved, resulting in a highly profitable target execution strategy. This effectively addresses the difficulties of equity marketing measurement and the unscientific nature of campaign effectiveness measurement.

[0155] The following combined Figure 3 , taking the application of the task planning method provided in this specification in a promotional activity as an example, the task planning method is further explained. Figure 3 A flowchart of a task planning method according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0156] Step 302: Obtain attribute information of the target promotion activity.

[0157] Step 304: Determine the activity influencing factors of the target promotion activity based on the attribute information.

[0158] Step 306: Integrate the activity influencing factors to obtain a correlation feature set, wherein the correlation feature set includes at least one correlation feature.

[0159] Step 308: For any associated feature among the associated features, obtain multiple configuration parameters corresponding to the associated feature.

[0160] Step 310: According to the multiple configuration parameters under the association feature, configure multiple preset execution strategies and activity execution indicators corresponding to the association feature.

[0161] Step 312: Execute each preset execution strategy to obtain the initial activity execution result corresponding to each preset execution strategy.

[0162] Step 314: Determine target activity execution results of the target promotion activity under multiple preset execution strategies based on the activity execution indicators and the initial activity execution results.

[0163] Step 316: Compare the target activity execution results under each preset execution strategy to determine the activity execution rate of each associated feature.

[0164] Step 318: For an associated feature whose feature type is an implicit type, if the impact of the associated feature on the execution of the target promotion activity is greater than a preset first impact threshold, adjust the feature type of the associated feature to an explicit type.

[0165] Step 320: For an associated feature whose feature type is an explicit type, if the impact of the associated feature on the execution of the target promotion activity is less than a preset second impact threshold, adjust the feature type of the associated feature to an inert type.

[0166] Step 322: Re-determine multiple preset execution strategies for the target promotion activity based on the target associated features in each associated feature, and continue to execute the steps of executing each preset execution strategy, wherein the feature type of the target associated feature is an explicit type or an implicit type.

[0167] Step 324: When the rate of change of each associated feature relative to the execution influence of the target promotion activity is less than a preset threshold, determine a target execution strategy for the target promotion activity.

[0168] The task planning method provided in this specification abstractly summarizes the associated features of the target task by obtaining at least one associated feature of the target task. It not only obtains the task execution results of each target task, but also determines the execution impact of each associated feature relative to the target task, and then summarizes and guides the target execution strategy of the target task based on the execution impact, thereby improving the efficiency and accuracy of task planning.

[0169] Corresponding to the above method embodiment, this specification also provides a task planning device embodiment, Figure 4 FIG1 shows a schematic diagram of the structure of a task planning device provided by an embodiment of this specification. Figure 4 As shown, the device includes:

[0170] An acquisition module 402 is configured to acquire at least one associated feature of a target task;

[0171] The task execution result determination module 404 is configured to determine the task execution result of the target task under multiple preset execution strategies based on the associated features;

[0172] The execution impact determination module 406 is configured to compare the task execution results under each preset execution strategy and determine the execution impact of each associated feature on the target task;

[0173] The target execution strategy determination module 408 is configured to determine the target execution strategy of the target task according to the execution impact of each of the associated features on the target task.

[0174] In one or more optional embodiments of this specification, the acquisition module 402 is further configured to:

[0175] Get the attribute information of the target task;

[0176] At least one associated feature of the target task is determined based on the attribute information.

[0177] In one or more optional embodiments of this specification, the acquisition module 402 is further configured to:

[0178] Determining task influencing factors of the target task based on the attribute information;

[0179] The task influencing factors are integrated to obtain a correlation feature set, wherein the correlation feature set includes at least one correlation feature.

[0180] In one or more optional embodiments of this specification, the task execution result determination module 404 is further configured to:

[0181] Based on the associated features, configure multiple preset execution strategies and task execution indicators corresponding to the target task;

[0182] Execute each preset execution strategy and obtain the initial task execution results corresponding to each preset execution strategy;

[0183] According to the task execution indicator and the initial task execution result, a target task execution result of the target task under a plurality of preset execution strategies is determined.

[0184] In one or more optional embodiments of this specification, the task execution result determination module 404 is further configured to:

[0185] For any associated feature among the associated features, obtain multiple configuration parameters corresponding to the associated feature;

[0186] According to the multiple configuration parameters under the association feature, multiple preset execution strategies and task execution indicators corresponding to the association feature are configured.

[0187] In one or more optional embodiments of this specification, the execution impact determination module 406 is further configured to:

[0188] Compare the task execution results under each preset execution strategy to determine the task execution rate of each associated feature;

[0189] The execution influence of each associated feature relative to the target task is calculated according to the task execution rate of each associated feature.

[0190] In one or more optional embodiments of this specification, the associated feature carries a feature type;

[0191] The target execution strategy determination module 408 is further configured to:

[0192] Adjusting the feature type of each associated feature based on the impact of each associated feature on the execution of the target task;

[0193] Re-determining multiple preset execution strategies for the target task based on the associated features and the feature types of the associated features, and continuing to perform the step of determining the task execution results of the target task under the multiple preset execution strategies;

[0194] In a case where a change rate of the execution influence of each associated feature relative to the target task is less than a preset threshold, a target execution strategy for the target task is determined.

[0195] In one or more optional embodiments of this specification, the target execution strategy determination module 408 is configured to:

[0196] For the associated feature whose feature type is a latent type, if the impact of the associated feature on the execution of the target task is greater than a preset first impact threshold, adjusting the feature type of the associated feature to an explicit type;

[0197] For the associated feature whose feature type is an explicit type, if the impact of the associated feature on the execution of the target task is less than a preset second impact threshold, the feature type of the associated feature is adjusted to an inert type.

[0198] In one or more optional embodiments of this specification, the target execution strategy determination module 408 is configured to:

[0199] A plurality of preset execution strategies of the target task are re-determined according to the target-related features in each of the related features, wherein the feature type of the target-related features is an explicit type or an implicit type.

[0200] The task planning device provided in this specification obtains at least one associated feature of a target task; based on each associated feature, determines the task execution result of the target task under multiple preset execution strategies; compares the task execution results under each preset execution strategy to determine the execution impact of each associated feature relative to the target task; and determines the target execution strategy of the target task based on the execution impact of each associated feature relative to the target task. By obtaining at least one associated feature of the target task, the associated features of the target task are abstracted and summarized, not only obtaining the task execution result of each target task, but also determining the execution impact of each associated feature relative to the target task, and then summarizing and guiding the target execution strategy of the target task based on the execution impact, thereby improving the efficiency and accuracy of task planning.

[0201] The above is a schematic scheme of a task planning device of this embodiment. It should be noted that the technical scheme of the task planning device and the technical scheme of the task planning method described above are of the same concept. For details not described in detail in the technical scheme of the task planning device, please refer to the description of the technical scheme of the task planning method described above.

[0202] Figure 5 FIG2 shows a block diagram of a computing device 500 according to an embodiment of the present disclosure. Components of the computing device 500 include, but are not limited to, a memory 510 and a processor 520. The processor 520 is connected to the memory 510 via a bus 530, and a database 550 is used to store data.

[0203] The computing device 500 also includes an access device 540 that enables the computing device 500 to communicate via one or more networks 560. Examples of such networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 540 may include one or more of any type of network interface (e.g., a network interface card (NIC)) whether wired or wireless, 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) interface, and the like.

[0204] In one embodiment of the present specification, the above components of the computing device 500 and Figure 5 Other components not shown in the figure may also be connected to each other, for example, via a bus. Figure 5 The computing device structure block diagram shown is for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art may add or replace other components as needed.

[0205] Computing device 500 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 computer, etc.), a mobile phone (e.g., a smartphone), a wearable computing device (e.g., a smartwatch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. Computing device 500 can also be a mobile or stationary server.

[0206] The processor 520 is configured to execute the following computer executable instructions, which implement the steps of the above-mentioned task planning method when executed by the processor.

[0207] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical solution of the computing device and the technical solution of the above-mentioned task planning method are of the same concept. For details not described in detail in the technical solution of the computing device, please refer to the description of the technical solution of the above-mentioned task planning method.

[0208] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which implement the steps of the above-mentioned task planning method when executed by a processor.

[0209] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the task planning method described above are of the same concept. For details not described in detail in the technical scheme of the storage medium, please refer to the description of the technical scheme of the task planning method described above.

[0210] An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned task planning method.

[0211] The above is a schematic scheme of a computer program of this embodiment. It should be noted that the technical scheme of the computer program and the technical scheme of the task planning method described above are of the same concept. For details not described in detail in the technical scheme of the computer program, please refer to the description of the technical scheme of the task planning method described above.

[0212] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0213] The computer instructions include computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium may include any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium.

[0214] It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0215] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0216] The preferred embodiments disclosed above are intended only to help illustrate this specification. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made based on the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that those skilled in the art can better understand and utilize this specification. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. A mission planning method, comprising: Obtain at least one relevant feature of the target task; Determining, based on the associated features, task execution results of the target task under multiple preset execution strategies; Comparing the task execution results under each preset execution strategy to determine the execution impact of each associated feature on the target task; According to the execution influence of each associated feature relative to the target task, the target execution strategy of the target task is determined, wherein the determining the target execution strategy of the target task according to the execution influence of each associated feature relative to the target task includes: dividing each associated feature into an explicit factor layer, a latent factor layer and an inert factor layer according to the execution influence of each associated feature relative to the target task; after multiple rounds of iterations, the associated features of the latent factor layer are converted to the explicit factor layer, and the associated features of the explicit factor layer are converted to the inert factor layer, until the associated features and the execution influence tend to be stable, and the target execution strategy of the target task is determined.

2. The method according to claim 1, wherein obtaining at least one associated feature of the target task comprises: Get the attribute information of the target task; At least one associated feature of the target task is determined based on the attribute information.

3. The method according to claim 2, wherein determining at least one associated feature of the target task based on the attribute information comprises: Determining task influencing factors of the target task based on the attribute information; The task influencing factors are integrated to obtain a correlation feature set, wherein the correlation feature set includes at least one correlation feature.

4. The method according to claim 1, wherein determining the task execution results of the target task under multiple preset execution strategies based on the associated features comprises: Based on the associated features, configure multiple preset execution strategies and task execution indicators corresponding to the target task; Execute each preset execution strategy and obtain the initial task execution results corresponding to each preset execution strategy; According to the task execution indicator and the initial task execution result, a target task execution result of the target task under a plurality of preset execution strategies is determined.

5. The method according to claim 4, wherein configuring a plurality of preset execution strategies and task execution indicators corresponding to the target task based on the associated features comprises: For any associated feature among the associated features, obtain multiple configuration parameters corresponding to the associated feature; According to the multiple configuration parameters under the association feature, multiple preset execution strategies and task execution indicators corresponding to the association feature are configured.

6. The method according to any one of claims 1 to 5, wherein comparing the task execution results under each preset execution strategy to determine the execution impact of each associated feature on the target task comprises: Compare the task execution results under each preset execution strategy to determine the task execution rate of each associated feature; The execution influence of each associated feature relative to the target task is calculated according to the task execution rate of each associated feature.

7. The method according to any one of claims 1 to 5, wherein the associated feature carries a feature type; The multi-round iterative process includes: Adjusting the feature type of each associated feature based on the impact of each associated feature on the execution of the target task; Re-determining multiple preset execution strategies for the target task based on the associated features and the feature types of the associated features, and continuing to perform the step of determining the task execution results of the target task under the multiple preset execution strategies; In a case where a change rate of the execution influence of each associated feature relative to the target task is less than a preset threshold, a target execution strategy for the target task is determined.

8. The method according to claim 7, wherein adjusting the feature type of each associated feature based on the execution impact of each associated feature on the target task comprises: For the associated feature whose feature type is a latent type, if the impact of the associated feature on the execution of the target task is greater than a preset first impact threshold, adjusting the feature type of the associated feature to an explicit type; For the associated feature whose feature type is an explicit type, if the impact of the associated feature on the execution of the target task is less than a preset second impact threshold, the feature type of the associated feature is adjusted to an inert type.

9. The method according to claim 8, wherein the re-determining the plurality of preset execution strategies of the target task based on the associated features and the feature types of the associated features comprises: A plurality of preset execution strategies of the target task are re-determined according to the target-related features in each of the related features, wherein the feature type of the target-related features is an explicit type or an implicit type.

10. A mission planning device, comprising: an acquisition module, configured to acquire at least one associated feature of a target task; A task execution result determination module is configured to determine the task execution result of the target task under multiple preset execution strategies based on the associated features; An execution impact determination module is configured to compare the task execution results under each preset execution strategy and determine the execution impact of each associated feature relative to the target task; a target execution strategy determination module configured to determine a target execution strategy for the target task based on the execution impact of each of the associated features relative to the target task; The target execution strategy determination module is further configured to divide the associated features into an explicit factor layer, a latent factor layer and an inert factor layer according to the execution influence of each associated feature relative to the target task; after multiple rounds of iterations, the associated features of the latent factor layer are converted to the explicit factor layer, and the associated features of the explicit factor layer are converted to the inert factor layer, until the associated features and the execution influence tend to be stable, and the target execution strategy of the target task is determined.

11. 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 task planning method described in any one of claims 1 to 9 are implemented.

12. A computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the steps of the task planning method according to any one of claims 1 to 9.

13. A computer program product, characterized in that The method comprises computer instructions which, when executed by a processor, implement the steps of the task planning method according to any one of claims 1 to 9.

Images