Information processing method and device

Resource allocation and task division through simulation resource configuration information, the problem of user behavior data prediction is solved, and efficient prediction is achieved in the context of rich and diverse information services, which is suitable for a variety of scenarios.

CN118644282BActive Publication Date: 2024-11-19RAJAX NETWORK &TECHNOLOGY (SHANGHAI) CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411126737.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-15
Publication Date
2024-11-19
Estimated Expiration
2044-08-15

AI Technical Summary

Technical Problem

It is difficult for the prior art to effectively predict user behavior data, such as click behavior, subscription services and purchasing goods, especially in the context of rich and diverse information services, how to accurately predict based on the user's allocated resources has become an urgent problem.

Method used

Resource allocation is performed by simulation resource configuration information, resource allocation results and target user information are determined, and target task list is generated, distributed tasks are divided according to task processing status and simulated to predict the behavioral data of target users.

Benefits of technology

It realizes the effective prediction of the target user's behavior data based on the simulation resource configuration information, which has high applicability and accuracy, and is suitable for a variety of information processing scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118644282B_ABST
    Figure CN118644282B_ABST
Patent Text Reader

Abstract

The embodiment of the present invention discloses an information processing method and device, which performs resource allocation according to simulation resource configuration information to determine the resource allocation result, the resource allocation result includes target user information and resource allocation information, and then determines a target task list according to the target user information and the resource allocation information, the target task list includes at least one target task, and then determines multiple distributed tasks according to the processing state of the target task, and then performs simulation on the multiple distributed tasks to determine the behavior data of the target user. Therefore, the behavior data of the target user can be effectively predicted according to the simulation resource configuration information, and the method has high applicability.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to an information processing method and device. Background Art

[0002] With the development and progress of information technology, industries such as express delivery, catering, and entertainment have also developed rapidly, resulting in more and more types of information services (such as displaying product information, short video information, cloud service information, etc.), which has greatly enriched and facilitated people's lives. At the same time, in order to facilitate the provision of information services to users, it is usually necessary to predict user behavior data (such as click behavior, subscription services, purchase of goods, etc.) based on the user's allocated resources (such as product exposure, consumer coupons, merchant recommended locations, trial periods, etc.). Therefore, how to effectively predict user behavior data based on the user's allocated resources has become an urgent problem to be solved. Summary of the invention

[0003] In view of this, the embodiments of the present invention provide an information processing method and device, which can effectively predict the behavior data of the target user according to the simulation resource configuration information, and has high applicability.

[0004] In a first aspect, an embodiment of the present invention provides an information processing method, the method comprising:

[0005] Perform resource allocation according to the simulated resource configuration information to determine a resource allocation result, wherein the resource allocation result includes target user information and resource allocation information, wherein the simulated resource configuration information is used to characterize a strategy for performing resource allocation, and the resource allocation information is used to characterize allocated resources for the corresponding target user;

[0006] Determine a target task list according to the target user information and the resource allocation information, wherein the target task list includes at least one target task, and the target task is used to simulate and predict the behavior data of the target user;

[0007] Determining a plurality of distributed tasks according to the processing state of the target task, each of the distributed tasks is used to simulate and predict sub-data of the behavior data of the target user;

[0008] The simulation of the multiple distributed tasks is performed to determine the behavior data of the target user.

[0009] In a second aspect, an embodiment of the present invention provides an information processing device, the device comprising:

[0010] A resource allocation unit, configured to perform resource allocation according to the simulated resource configuration information to determine a resource allocation result, wherein the resource allocation result includes target user information and resource allocation information, wherein the simulated resource configuration information is used to characterize a strategy for performing resource allocation, and the resource allocation information is used to characterize allocated resources for the corresponding target user;

[0011] A task list determining unit, configured to determine a target task list according to the target user information and the resource allocation information, wherein the target task list includes at least one target task, and the target task is used to simulate and predict the behavior data of the target user;

[0012] A distributed task determination unit, configured to determine a plurality of distributed tasks according to a processing state of the target task, each of the distributed tasks being used to simulate and predict sub-data of the behavior data of the target user;

[0013] The task execution unit is used to execute the simulation of multiple distributed tasks to determine the behavior data of the target user.

[0014] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer program instructions, wherein the computer program instructions implement the method described in the first aspect when executed by a processor.

[0015] In a fourth aspect, an embodiment of the present invention provides an electronic device, the device comprising:

[0016] a memory for storing one or more computer program instructions;

[0017] A processor, wherein the one or more computer program instructions are executed by the processor to implement the method according to the first aspect.

[0018] The embodiment of the present invention determines the resource allocation result by performing resource allocation according to the simulation resource configuration information, the resource allocation result includes the target user information and the resource allocation information, and then determines the target task list according to the target user information and the resource allocation information, the target task list includes at least one target task, and then determines multiple distributed tasks according to the processing state of the target task, and then performs simulation on the multiple distributed tasks to determine the behavior data of the target user. Therefore, the behavior data of the target user can be effectively predicted according to the simulation resource configuration information, and the application is relatively high. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0020] Figure 1is a flow chart of an information processing method according to an embodiment of the present invention;

[0021] Figure 2 is a flow chart of a method for determining resource allocation results in an embodiment of the present invention;

[0022] Figure 3 is a flow chart of a method for determining multiple distributed tasks in an embodiment of the present invention;

[0023] Figure 4 is a flow chart of a method for determining multiple distributed tasks in an embodiment of the present invention;

[0024] Figure 5 is a schematic diagram of a predicted data distribution curve and a detected data distribution curve in an embodiment of the present invention;

[0025] Figure 6 is a data flow diagram of the information processing method according to an embodiment of the present invention;

[0026] Figure 7 is a schematic diagram of an information processing device according to an embodiment of the present invention;

[0027] Figure 8 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The present application is described below based on embodiments, but the present application is not limited to these embodiments. In the detailed description of the present application below, some specific details are described in detail. It is possible for those skilled in the art to fully understand the present application without the description of these details. In order to avoid confusing the essence of the present application, known methods, processes, flows, components and circuits are not described in detail.

[0029] In addition, persons of ordinary skill in the art will appreciate that the drawings provided herein are for illustration purposes and are not necessarily drawn to scale.

[0030] Unless the context clearly requires otherwise, the words "include", "comprising" and similar words throughout the application should be interpreted as including rather than exclusive or exhaustive; that is, the meaning is "including but not limited to".

[0031] In the description of this application, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, the meaning of "plurality" is two or more.

[0032] The solutions described in this specification and in the examples, if they involve the processing of personal information, will be processed on the premise of having a legal basis (such as obtaining the consent of the subject of personal information, or being necessary for the performance of a contract, etc.), and will only be processed within the scope of regulations or agreements. If a user refuses to process personal information other than the necessary information for basic functions, it will not affect the user's use of basic functions.

[0033] In this embodiment, the information processing method can be applied to the scenario of purchasing orders, then the allocated resources of the target user can be consumption coupons, and the predicted behavior data of the target user can be the number of purchased orders. It should be understood that the information processing method involved in the embodiment of the present invention can also be applied to various other types of scenarios that require information processing. For example, the information processing method can be applied to the scenario of browsing goods, then the allocated resources of the target user can be the exposure of the goods (such as the frequency and duration of exposure), and the predicted behavior data of the target user can be the number of clicks on the goods. For another example, the information processing method can be applied to the scenario of subscription services, then the allocated resources of the target user can be the trial period of cloud services (cloud services such as network resources based on cloud computing systems (such as gateway devices and switches, etc.)), and the predicted behavior data of the target user can be the number of subscriptions to the cloud service. For another example, the information processing method can be applied to the scenario of short video information recommendation, then the allocated resources of the target user can be the recommended position of the short video on the recommendation page, and the predicted behavior data of the target user can be the number of views and comments of the video.

[0034] In this embodiment, in order to effectively predict the user's behavior data based on the user's allocated resources, this embodiment determines the resource allocation result by performing resource allocation based on the simulated resource configuration information, and then determines the target task list based on the target user information and resource allocation information included in the resource allocation result, and then determines multiple distributed tasks based on the processing status of the target task in the target task list, and performs simulation on multiple distributed tasks to determine the target user's behavior data. In this way, the user's behavior data can be effectively predicted and has high applicability. Specifically, the information processing method of this embodiment can refer to Figure 1 .

[0035] Figure 1 is a flow chart of the information processing method according to an embodiment of the present invention. Figure 1 As shown, the information processing process of this embodiment includes the following steps:

[0036] Step S100: Perform resource allocation according to the simulation resource configuration information to determine a resource allocation result, where the resource allocation result includes target user information and resource allocation information.

[0037] In this embodiment, resource allocation can be performed according to preset simulation resource configuration information to determine the resource allocation result. The resource allocation result includes target user information and resource allocation information. The simulation resource configuration information is used to characterize the strategy for performing resource allocation, and the resource allocation information is used to characterize the allocated resources of the corresponding target user. In other words, in order to determine the effective allocation of resources, the simulation resource configuration information (that is, the resource allocation strategy) can be preset to simulate resource allocation according to the resource allocation strategy to determine the target user information and the corresponding allocated resources.

[0038] In this embodiment, considering that different resource allocation strategies may have an impact on the predicted behavior data, in view of this situation, this embodiment can pre-simulate different resource allocation strategies and obtain detection behavior data, and then determine the simulation resource configuration information according to the resource allocation strategy that may have an impact on the detection behavior data. Among them, the detection behavior data is the user behavior data obtained through online resource allocation. That is to say, the online system can use different simulated resource allocation strategies to conduct resource allocation experiments on online resources to collect corresponding user behavior data, and then determine the simulation resource configuration information according to the user behavior data. Among them, the online resources are similar to the allocated resources of the above-mentioned target users, and the online resources are different in different application scenarios. Online resources include consumption coupons, exposure, trial period of cloud services, and recommended locations. The detection behavior data is similar to the behavior data of the predicted target user. The detection behavior data in different application scenarios include the number of purchased orders, the number of clicks on the goods, the number of subscriptions to the cloud service, the number of video views, the number of comments, etc. For example, the detection behavior data is the number of completed orders, and different amounts of consumption coupons can be issued to the target user in the online resource allocation system to determine the different completed orders of the target user.

[0039] In the following description, it is taken as an example that the allocated resources of the target user can be consumption coupons and the predicted behavior data of the target user can be the number of purchased orders (ie, the number of completed orders).

[0040] For example, the online system is a service platform (such as a takeaway platform, an express delivery platform, a shopping platform, etc.), which can be deployed on an electronic device (such as a server, a computer, etc.) with functions such as data transmission, data processing, and data storage. The service platform can display goods to users, and users can receive consumer coupons and place orders on the service platform. Online resources are consumer coupons of different amounts, and the detection behavior data can be the number of completed orders by users. By obtaining the order information purchased by the user, it can be determined that the allocation of consumer coupons to users at different times may have an impact on the number of completed orders of the user. Specifically, the time period of the order purchased by the user is from 8 pm to 9 pm, indicating that the user is relatively free from 8 pm to 9 pm, and consumer coupons can be allocated to the user. For users who are relatively busy from 8 am to 9 am, consumer coupons may not be allocated to the user. Therefore, it can be determined that time information may have an impact on the user's behavior data, and the resource allocation strategy can be adjusted according to the time information to determine the simulation resource configuration information.

[0041] In this embodiment, the simulation resource configuration information includes location information, time information, user characteristics, etc. Among them, the location information includes the location of the business district (i.e., commercial area), the city location, the geographic coordinates, etc. In other words, different location information may have an impact on the user's behavior data. For example, the user's location information indicates that the user is within the business district, so a consumption voucher can be allocated to the user. For another example, the user's location information indicates that the user is crossing the road, so a consumption voucher should not be allocated to the user. Among them, user characteristics include age, gender, occupation, etc. In other words, different user characteristics may have an impact on the user's behavior data. For example, based on the user's young age, it can be indicated that the user may be interested in toy products, and a consumption voucher for toy products can be allocated to the user. Among them, the time information can be different moments, different time periods, etc.

[0042] In this embodiment, the above-mentioned collection of detection behavior data to determine the simulation resource configuration information, that is, determining the simulation resource configuration information based on the behavior data obtained by simulating resource allocation in the online system is used as an example for explanation. It should be understood that the simulation resource configuration information can also be customized according to needs, for example, the simulation resource configuration information can be customized according to product characteristics (for example, product price, evaluation, color, etc.), merchant characteristics (for example, merchant rating, number of goods sold), etc. (that is, adjusting the strategy of simulated resource allocation). Correspondingly, this implementation is explained by taking the simulation resource configuration information including location information, time information and user characteristics as an example. It should be understood that the simulation resource configuration information can also include the above-mentioned customized resource allocation strategies such as product characteristics and merchant characteristics.

[0043] In this embodiment, the resource allocation result can be determined by the resource allocation system, wherein the resource allocation system can be deployed on the above-mentioned service platform. The resource allocation system can be determined according to the above-mentioned application scenario. For example, the resource allocation system can be a consumer voucher allocation system, a commodity exposure system, a network cloud service system, a video recommendation system, etc. In other words, the resource allocation is simulated by the online system of the service platform according to the simulated resource configuration information to determine the resource allocation result.

[0044] Optionally, the resource allocation system may also be determined by a pre-trained neural network model, such as a convolutional neural network (CNN), a recurrent neural network (RNN), a long short-term memory network (LSTM), and the like.

[0045] In this embodiment, the simulation resource configuration information can be simulated to generate a simulation request, and then the simulation request carrying the simulation resource configuration information is sent to the resource allocation system. After the resource allocation system receives the simulation request, the resource allocation system determines the target user information that matches the simulation resource configuration information. For example, the target user information of the corresponding location area is determined according to the location information. For another example, the target user information that meets the user characteristics is determined.

[0046] Furthermore, the resource allocation system determines the resource allocation information of the target user according to the preset resource allocation method, and determines the resource allocation result according to the target user information and the corresponding resource allocation information. Among them, the resource allocation method can be customized according to the needs, such as the issuance method of consumption coupons of different amounts, the method of receiving consumption coupons, the display method, etc. Correspondingly, the resource allocation information is used to characterize the allocated resources of the corresponding target user, and the resource allocation information includes consumption coupons of different amounts, the conditions for receiving consumption coupons, and different consumption coupon display pages (such as page color, brightness, etc.). In the following description, the resource allocation information including consumption coupons of different amounts is used for explanation.

[0047] Optionally, the resource allocation system determines the target user information from the registered user information of the service platform according to the simulation resource configuration information. The resource allocation system may also send information acquisition requests to the terminals of multiple candidate users, and then determine the target user information that matches the simulation resource configuration information from the candidate user information fed back by each user. The target user information may include a variety of feature information of the target user, such as age, gender, occupation, user location, account information, target user ID (Identity document), serial number of the target user's terminal, etc. The target user information may include user features in the simulation resource configuration information.

[0048] In this embodiment, the resource allocation system is used as an example to illustrate the resource allocation result. It should be understood that the resource allocation result can also be customized according to the simulation resource configuration information. For example, the user allocates corresponding resources to the target user according to the simulation resource configuration information.

[0049] Step S200: determining a target task list according to target user information and resource allocation information, wherein the target task list includes at least one target task.

[0050] In this embodiment, a target task list can be determined based on the target user information and the resource allocation information. The target task list includes at least one target task, and the target task is used to simulate and predict the behavior data of the target user. Specifically, the flowchart of the method for determining the target task list in this embodiment can be referred to Figure 2 .

[0051] Figure 2 is a flow chart of a method for determining resource allocation results in an embodiment of the present invention. Figure 2 As shown, the process of determining the resource allocation result in this embodiment includes the following steps:

[0052] S210: Determine a candidate task list according to target user information and resource allocation information, where the candidate task list includes multiple candidate tasks.

[0053] In this embodiment, multiple candidate tasks are generated according to the target user information and the resource allocation information, and then a candidate task list is determined according to the multiple candidate tasks, wherein each candidate task is used to simulate candidate data for predicting the target user's behavior.

[0054] Optionally, the resource allocation information includes consumer vouchers of different amounts. A candidate task can be determined based on the target user information and a consumer voucher of a certain amount. Similarly, multiple candidate tasks can be determined based on the target user information and consumer vouchers of different amounts, based on multiple candidate task lists. In the following description, the resource allocation information including consumer vouchers of different amounts is used as an example. It should be understood that the resource allocation information may also include a consumer voucher display page, full reduction information, etc.

[0055] In this embodiment, in order to effectively perform task simulation, the priority and task processing time corresponding to each candidate task can be set when generating each candidate task. The task processing time represents the timestamp of starting task processing.

[0056] Optionally, you can also customize task parameters such as the task processing time length of each candidate task.

[0057] S220: Obtain target tasks that meet predetermined conditions from multiple candidate tasks, and determine a target task list, wherein the predetermined conditions include priority and task processing time.

[0058] In this embodiment, the candidate task with the highest priority and corresponding to the task processing time closest to the current timestamp may be determined as the target task, and the target task list may be determined based on the target task.

[0059] Optionally, a predetermined number of candidate tasks may be determined as multiple target tasks, and a target task list may be determined based on the multiple target tasks. For example, the candidate tasks with the first, second, and third priorities may be determined as multiple target tasks. In other words, the target task list may include one or more target tasks.

[0060] Optionally, considering that there are a large number of candidate tasks, target tasks that meet predetermined conditions may be obtained from a plurality of candidate tasks at predetermined time intervals to determine a target task list.

[0061] In this embodiment, the predetermined conditions including priority and task processing time are taken as an example for explanation. It should be understood that the predetermined conditions may also include custom conditions such as the task processing time length being less than a time length threshold.

[0062] Step S300: determining a plurality of distributed tasks according to the processing status of the target task, each distributed task being used to simulate and predict sub-data of the behavior data of the target user.

[0063] In this embodiment, each target task in the target task list has a corresponding processing status, and the processing status can be to be scheduled, in process, or suspended. The target task can be obtained from the target task list, and then the processing status of the target task can be detected, and then multiple distributed tasks can be determined for simulation based on the processing status of the target task. Among them, each distributed task is used to simulate and predict the sub-data of the target user's behavior data. Specifically, if it is detected that the processing status of the target task is to be scheduled, step S300 includes steps S311-S313, which can be referred to Figure 3 .

[0064] Figure 3 It is a flowchart of a method for determining multiple distributed tasks in an embodiment of the present invention. Figure 3 As shown, the process of determining multiple distributed tasks in this embodiment includes the following steps:

[0065] Step S311: The processing status of the target task is pending, and the total number of pages of the target task is determined.

[0066] In this embodiment, it is detected that the processing status of the target task is pending, indicating that the target task has not yet been divided into multiple distributed tasks. The total number of pages of the target task can be determined first, and then the target task can be divided into multiple distributed tasks according to the total number of pages. Specifically, considering that the target user information includes age, gender, location information, time information (such as the time when the target user receives the consumption voucher, the time when the consumption voucher is allocated, etc.), occupation and other types of feature information, in order to simplify the complexity of information processing, so as to simulate and predict the behavior data of the target user, this embodiment can determine the total number of pages of the target task through various methods such as preset paging information and establishing a feature matrix.

[0067] In an optional implementation, the target matrix can be determined by the target task, and then the total number of pages can be determined based on the target matrix. Specifically, the target user feature matrix can be determined based on the target user information, and the resource feature matrix can be determined based on the resource allocation information. Then, the total number of pages of the target matrix can be determined based on the number of pages corresponding to the target user feature matrix and the resource feature matrix.

[0068] Optionally, the target user information may include multiple feature information corresponding to multiple users, and multiple feature matrices may be determined based on the multiple feature information, and the target user feature matrix may be determined based on the multiple feature matrices. In other words, the target user feature matrix may include matrices of features corresponding to one or more users. In the following description, the target user feature matrix may include a matrix of features corresponding to one user as an example for explanation.

[0069] In another optional implementation, the total number of pages of the target task can be determined by preset paging information. The paging information may include the data size of each page (the data size refers to a predetermined byte or predetermined data bit, etc.), and the total number of pages of the target task can be determined by calculating the data size of the target task and the data size of each page. The data size of each page may be the same or different. The paging information may also include the page number of each page.

[0070] Optionally, data corresponding to a certain feature in the target user information may be assigned a page, that is, a certain page records certain feature data (eg, age, occupation, etc.) of the target user.

[0071] In this embodiment, the total number of pages of the target task is determined by establishing a feature matrix through preset paging information. It should be understood that the total number of pages of the target task can also be determined by the user by customizing paging according to needs.

[0072] Step S312: Divide the target task into multiple distributed tasks according to the total number of pages.

[0073] In this embodiment, the target task can be divided into multiple distributed tasks according to the total number of pages in various ways.

[0074] Optionally, the target task can be divided into multiple distributed tasks according to the type of characteristic information in the target user information and the total number of pages of the target task. For example, the target user characteristic matrix can be divided into multiple sub-matrices according to the age, occupation, time information, location information, etc. of the target user, and a distributed task can be determined according to any sub-matrix and the resource characteristic matrix. Similarly, the target task can be divided into multiple distributed tasks according to multiple types of characteristic information in the target user information and the total number of pages of the target task.

[0075] Optionally, the target user information may include multiple feature information corresponding to multiple users, and the target task may be divided into multiple distributed tasks according to the feature information corresponding to each user and the total number of pages of the target task. For example, a distributed task may be determined according to a feature matrix of a certain user and a resource feature matrix.

[0076] Optionally, the target task may be divided into multiple distributed tasks according to the total number of pages of the target task and preset paging information (such as the data size and page number of each page).

[0077] In this embodiment, a correspondence relationship between a target task and multiple distributed tasks can be established. For example, the unique identifiers corresponding to the target task and multiple distributed tasks can be determined, and then a mapping relationship between the unique identifier corresponding to the target task and the unique identifiers corresponding to the multiple distributed tasks can be established.

[0078] Step S313: Change the processing status of the target task from pending to being processed.

[0079] In this embodiment, since the target task is divided into multiple distributed tasks, the processing status of the target task can be changed from pending to processing, and then the multiple distributed tasks can be simulated to determine the behavior data of the target user. Further, the processing status of each distributed task can be marked as pending simulation to wait for subsequent simulation.

[0080] In this embodiment, the current time can be obtained in real time. If it is detected that the current time does not match the preset time, the processing status of the target task is set to suspended processing. That is to say, considering that coupons need to be allocated to a large number of users in certain time periods, resulting in a large number of target tasks that need to be simulated, in order to reduce simulation failures and improve simulation efficiency, it can be detected whether the current time matches the preset time. If the current time does not match the preset time, the processing status of the target task can be set to suspended processing, and multiple distributed tasks corresponding to the target task with a processing status of suspended processing can be set to a suspended state. For example, the preset time is 8 to 11 a.m. and 2 to 5 p.m. If the current time is 12 o'clock, the processing status of the target task can be set to suspended processing, and the simulation of the distributed tasks corresponding to the target task is suspended.

[0081] Optionally, the task completion time can also be determined according to the task processing time of the target task (that is, the timestamp of starting task processing) and the task processing duration. If the task completion time does not match the preset time, the current time matches the preset time, and the time interval between the current time and the preset time is less than the time threshold, the processing status of the target task is set to suspended processing. In other words, if the target task cannot be completed within the preset time, the target task can be set to suspended processing in advance. For example, the time threshold is 10 minutes, the preset time is 8:00 to 11:00 a.m. and 2:00 to 5:00 p.m., if the current time is 10:55 and the completion time of the target task is 12:20, although the current time matches the preset time, the task completion time does not match the preset time, and the time interval between the current time and the preset time is 5 minutes less than the time threshold of 10 minutes, the target task can be set to suspended processing. In other words, if the target task list includes multiple target tasks, the processing status of the multiple target tasks may include pending, processing, and suspended processing. The processing status of each target task may be the same or different. Correspondingly, if the task completion time matches the preset time and the current time matches the preset time, or the current time matches the preset time and the task completion time does not match the preset time, and the time interval between the current time and the preset time is greater than or equal to the time threshold, the processing status of the target task is set to being processed. In the following description, the current time does not match the preset time, and the processing status of the target task is set to being suspended. The current time matches the preset time and the processing status of the target task is set to being processed as an example for explanation.

[0082] In this embodiment, if it is detected that the processing status of the target task is suspended, step S300 includes steps S321 to S325, which can refer to Figure 4 .

[0083] Figure 4 is a flow chart of a method for determining multiple distributed tasks in an embodiment of the present invention. Figure 4 As shown, the process of determining multiple distributed tasks in this embodiment includes:

[0084] Step S321: The processing status of the target task is suspended, and the current time is obtained.

[0085] In this embodiment, if the processing status of the target task is suspended processing, the current time is obtained.

[0086] Step S322: determine whether the current time matches the preset time.

[0087] In this embodiment, if the current time matches the preset time, step S323 is executed. If the current time does not match the preset time, step S325 is executed.

[0088] Step S323: Determine multiple tasks in a paused state corresponding to the target task during the simulation as multiple distributed tasks.

[0089] In this embodiment, since the multiple distributed tasks corresponding to the target task are set to a paused state, the multiple tasks corresponding to the target task in the simulation process that are in a paused state can be determined as multiple distributed tasks to continue the simulation.

[0090] Step S324: Change the processing status of the target task from suspended processing to processing.

[0091] Step S325, suspend execution of the target task.

[0092] In this embodiment, since the current time does not match the preset time, the execution of the target task is suspended.

[0093] In this embodiment, if it is detected that the processing status of the target task is processing, multiple tasks in a failed state corresponding to the target task in the simulation process are determined as multiple distributed tasks. Specifically, each distributed task has a corresponding simulation state during the simulation process, and the simulation state includes a completed state, an operating state, a failed state, etc. Among them, the completed state indicates that the corresponding distributed task simulation is completed, the operating state indicates that the corresponding distributed task is in the simulation process, and the failed state indicates that the corresponding distributed task simulation fails. Considering that there may be a distributed task simulation failure, for the target task whose processing status is processing, multiple tasks in a failed state can be determined as multiple distributed tasks to re-simulate.

[0094] In this embodiment, if the simulation status of all distributed tasks corresponding to the target task is in the completed status, it means that the simulation of the target task is completed, and the processing status of the target task can be set to simulation completed.

[0095] Step S400: simulating multiple distributed tasks to determine the behavior data of the target user.

[0096] In this embodiment, multiple distributed tasks are simulated to determine the behavior data of the target user. Specifically, multiple distributed tasks can be simulated to predict multiple sub-data of the target user's behavior data (such as the number of completed orders, click-through rate, etc.), and then weighted calculation is performed according to the preset weight value corresponding to each sub-data to obtain the behavior data of the target user. Among them, the preset weight value corresponding to each sub-data can be customized, or it can be determined according to the type of feature information corresponding to the distributed task. For example, the preset weight value of the sub-data corresponding to the age feature of the target user in the distributed task simulation is 0.2.

[0097] In this embodiment, multiple distributed tasks may be simulated in a variety of ways.

[0098] Optionally, multiple distributed tasks may be simulated separately using a pre-trained neural network model, such as a convolutional neural network, a recurrent neural network, a long short-term memory network, or the like.

[0099] Optionally, multiple nodes in a distributed cluster may be called to simulate multiple distributed tasks respectively. The nodes in the distributed cluster may be servers, and the servers may be deployed with pre-trained neural network models.

[0100] Optionally, a preset algorithm of a cloud platform may be called to simulate multiple distributed tasks respectively. The cloud platform may be, for example, TPP (The Personalization Platform).

[0101] In this embodiment, based on the correspondence between the predetermined time period and the simulation rate, the target simulation rate of multiple distributed tasks is determined according to the current time. For example, the simulation rate corresponding to 8 am to 10 am, that is, the query rate per second (QPS) is 200. If the current time is 9 am, the corresponding simulation rate is 200 QPS.

[0102] In this embodiment, after the behavior data of the target user is determined by simulation, a predicted data distribution curve is determined based on the predicted behavior data of the target user, and a detection data distribution curve is determined based on the detection behavior data, and then the predicted data distribution curve and the detection data distribution curve are presented in a comparative manner to facilitate the determination of the target resource allocation strategy. Among them, the target resource allocation strategy can be determined by weighted calculation, average value calculation, and optimal solution calculation based on the predicted data distribution curve and the detection data distribution curve. The target resource allocation strategy is similar to the simulation resource configuration information. The target resource allocation strategy represents the target strategy for resource allocation. The target resource allocation strategy may include time information, location information, user characteristics, etc. For example, the target resource allocation strategy allocates consumption coupons to target users at a certain location at a certain time. For example, the behavior data of the target user is the number of purchased orders (that is, the number of completed orders), and the resource allocation information, that is, the allocated resources of the target user is the amount of consumption coupons, then the predicted data distribution curve and the detection data distribution curve can refer to Figure 5 .

[0103] Figure 5 Schematic diagram of the predicted data distribution curve and the detected data distribution curve in the embodiment of the present invention. Figure 5 In the example, the predicted data distribution curve and the detected data distribution curve are presented in a comparative manner to facilitate the determination of the target resource allocation strategy.

[0104] The embodiment of the present invention determines the resource allocation result by performing resource allocation according to the simulation resource configuration information, the resource allocation result includes the target user information and the resource allocation information, and then determines the target task list according to the target user information and the resource allocation information, the target task list includes at least one target task, and then determines multiple distributed tasks according to the processing state of the target task, and then performs simulation on the multiple distributed tasks to determine the behavior data of the target user. Therefore, the behavior data of the target user can be effectively predicted according to the simulation resource configuration information, and the application is relatively high.

[0105] Figure 6 : is a data flow diagram of the information processing method of an embodiment of the present invention. Figure 6 As shown, firstly, resource allocation is performed according to the simulation resource configuration information 210 to determine the resource allocation result 220, and the resource allocation result 220 includes the target user information and the resource allocation information. The simulation resource configuration information 210 is used to characterize the strategy for resource allocation, and the resource allocation information is used to characterize the allocated resources of the corresponding target user. Then, a candidate task list 230 is determined according to the target user information and the resource allocation information, and the candidate task list 230 includes multiple candidate tasks 231, 232, 233 and 234. Further, a target task 241 that meets a predetermined condition is obtained from the multiple candidate tasks to determine the target task list 240. Then, multiple distributed tasks 250 are determined according to the processing status of the target task, and the multiple distributed tasks 250 include 251, 252, 253 and 254. Finally, the multiple distributed tasks 250 are simulated to determine the behavior data 260 of the target user.

[0106] The embodiment of the present invention determines the resource allocation result by performing resource allocation according to the simulation resource configuration information, the resource allocation result includes the target user information and the resource allocation information, and then determines the target task list according to the target user information and the resource allocation information, the target task list includes at least one target task, and then determines multiple distributed tasks according to the processing state of the target task, and then performs simulation on the multiple distributed tasks to determine the behavior data of the target user. Therefore, the behavior data of the target user can be effectively predicted according to the simulation resource configuration information, and the application is relatively high.

[0107] Figure 7 Schematic diagram of an information processing device according to an embodiment of the present invention. Figure 7 As shown, the information processing apparatus of this embodiment includes a resource allocation unit 310 , a task list determination unit 320 , a distributed task determination unit 330 and a task execution unit 340 .

[0108] The resource allocation unit 310 is configured to perform resource allocation according to the simulation resource configuration information to determine the resource allocation result, and the resource allocation result includes target user information and resource allocation information, wherein the simulation resource configuration information is used to characterize the resource allocation strategy, and the resource allocation information is used to characterize the allocated resources of the corresponding target user.

[0109] The task list determining unit 320 is configured to determine a target task list according to the target user information and the resource allocation information. The target task list includes at least one target task, and the target task is used to simulate and predict the behavior data of the target user.

[0110] The distributed task determination unit 330 is configured to determine a plurality of distributed tasks according to the processing state of the target task, each distributed task being used to simulate and predict sub-data of the behavior data of the target user.

[0111] The task execution unit 340 is configured to execute simulation of a plurality of distributed tasks to determine the behavior data of the target user.

[0112] The embodiment of the present invention determines the resource allocation result by performing resource allocation according to the simulation resource configuration information, the resource allocation result includes the target user information and the resource allocation information, and then determines the target task list according to the target user information and the resource allocation information, the target task list includes at least one target task, and then determines multiple distributed tasks according to the processing state of the target task, and then performs simulation on the multiple distributed tasks to determine the behavior data of the target user. Therefore, the behavior data of the target user can be effectively predicted according to the simulation resource configuration information, and the application is relatively high.

[0113] Figure 8 4 is a schematic diagram of an electronic device according to an embodiment of the present invention. In this embodiment, the electronic device 400 includes a server, a terminal, etc. Figure 8 As shown, the electronic device 400 includes: at least one processor 410; and a memory 420 connected to the at least one processor 410 for communication; and a communication component 430 connected to the scanning device for communication, and the communication component 430 receives and sends data under the control of the processor 410; wherein the memory 420 stores instructions that can be executed by at least one processor 410, and the instructions are executed by at least one processor 410 to implement the above-mentioned information processing method.

[0114] Specifically, the electronic device includes: one or more processors 410 and a memory 420, Figure 8 A processor 410 is taken as an example. The processor 410 and the memory 420 may be connected via a bus or other means. Figure 8The example of the bus connection is taken as an example. The memory 420 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules. The processor 410 executes various functional applications and data processing of the device by running the non-volatile software programs, instructions and modules stored in the memory 420, that is, realizing the above-mentioned information processing method.

[0115] The memory 420 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and applications required for at least one function; the data storage area may store a list of options, etc. In addition, the memory 420 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 420 may optionally include a memory remotely arranged relative to the processor 410, and these remote memories may be connected to an external device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0116] One or more modules are stored in the memory 420, and when executed by one or more processors 410, the information processing method in any of the above method embodiments is executed.

[0117] The above-mentioned product can execute the method provided in the embodiment of the present application, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in this embodiment, please refer to the method provided in the embodiment of the present application.

[0118] The embodiment of the present invention determines the resource allocation result by performing resource allocation according to the simulation resource configuration information, the resource allocation result includes the target user information and the resource allocation information, and then determines the target task list according to the target user information and the resource allocation information, the target task list includes at least one target task, and then determines multiple distributed tasks according to the processing state of the target task, and then performs simulation on the multiple distributed tasks to determine the behavior data of the target user. Therefore, the behavior data of the target user can be effectively predicted according to the simulation resource configuration information, and the application is relatively high.

[0119] Another embodiment of the present invention relates to a non-volatile storage medium for storing a computer-readable program, wherein the computer-readable program is used for a computer to execute part or all of the above method embodiments.

[0120] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0121] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An information processing method, characterized in that: The method comprises: Perform resource allocation according to the simulated resource configuration information to determine a resource allocation result, wherein the resource allocation result includes target user information and resource allocation information, wherein the simulated resource configuration information is used to characterize a strategy for performing resource allocation, and the resource allocation information is used to characterize allocated resources for the corresponding target user; Determine a target task list according to the target user information and the resource allocation information, wherein the target task list includes at least one target task, and the target task is used to simulate and predict the behavior data of the target user; Determining a plurality of distributed tasks according to the processing state of the target task, each of the distributed tasks is used to simulate and predict sub-data of the behavior data of the target user; Simulating the plurality of distributed tasks to determine behavior data of the target user; Wherein, simulating the plurality of distributed tasks to determine the behavior data of the target user includes: Simulating the multiple distributed tasks respectively to predict multiple sub-data of the target user's behavior data; and The behavior data of the target user is obtained by performing weighted calculation according to the preset weight value corresponding to each sub-data.

2. The method according to claim 1, characterized in that The performing resource allocation according to the simulation resource configuration information to determine the resource allocation result comprises: A simulation request carrying the simulation resource configuration information is sent to a resource allocation system to request the resource allocation system to determine the target user information that matches the simulation resource configuration information, and determine the resource allocation information of the target user according to a preset resource allocation method, wherein the simulation resource configuration information includes at least one of location information, time information or user characteristics.

3. The method according to claim 1, characterized in that Determining the target task list according to the target user information and the resource allocation information includes: Determine a candidate task list according to the target user information and the resource allocation information, wherein the candidate task list includes a plurality of candidate tasks; The target tasks satisfying predetermined conditions are obtained from the multiple candidate tasks, and the target task list is determined, wherein the predetermined conditions include priority and task processing time.

4. The method according to claim 1, characterized in that: The determining of a plurality of distributed tasks according to the processing status of the target task comprises: In response to the processing status of the target task being to be processed, determining a total number of pages of the target task; Dividing the target task into the plurality of distributed tasks according to the total number of pages; The processing status of the target task is changed from pending to being processed.

5. The method according to claim 1, characterized in that: The determining of a plurality of distributed tasks according to the processing status of the target task comprises: In response to the processing status of the target task being in processing, a plurality of tasks corresponding to the target task in a failed state during the simulation process are determined as the plurality of distributed tasks.

6. The method according to claim 1, characterized in that The determining of a plurality of distributed tasks according to the processing status of the target task comprises: In response to the processing status of the target task being suspended, obtaining the current time; In response to the current time matching the preset time, determining a plurality of tasks in a paused state corresponding to the target task in the simulation process as the plurality of distributed tasks; The processing status of the target task is changed from suspended processing to processing.

7. The method according to claim 1, characterized in that The method further comprises: Get the current time; In response to the current time not matching the preset time, the processing state of the target task is set to suspended processing.

8. The method according to claim 1, characterized in that The method further comprises: Determining a predicted data distribution curve according to the predicted behavior data of the target user; Determining a detection data distribution curve according to the detection behavior data, wherein the detection behavior data is user behavior data obtained by performing an experiment on allocating online resources by using different simulated resource allocation strategies in an online system; The predicted data distribution curve and the detected data distribution curve are presented in a comparative manner to facilitate determination of a target resource allocation strategy.

9. A computer-readable storage medium storing computer program instructions, characterized in that: The computer program instructions implement the method according to any one of claims 1 to 8 when executed by a processor.

10. An electronic device, characterized in that: The device comprises: a memory for storing one or more computer program instructions; A processor, wherein the one or more computer program instructions are executed by the processor to implement the method according to any one of claims 1 to 8.

Citation Information

Patent Citations

  • Information pushing method and device

    CN114610996A

  • Task allocation method and device, equipment and storage medium

    CN114816690A

  • Cloud server resource allocation method and device, equipment and medium

    CN117640541A

  • Inter-domain shift recommendation system based on interest and preference of user

    JP2024021038A

  • Load balancing based on user behavior prediction

    US20170264679A1