Task processing method and device, electronic equipment and storage medium

Abstract

The present disclosure relates to a task processing method and device, electronic equipment and storage medium. The method comprises: obtaining a plurality of users corresponding to a target object in a preset time period; obtaining behavior information of each user in the plurality of users on the target object in the preset time period, the behavior information comprising behavior time information, behavior frequency information and resource consumption information generated by the behavior; determining first association information between the behavior frequency information and the target object, and second association information between the resource consumption information and the target object; classifying the plurality of users according to the behavior time information, the first association information and the second association information, to obtain a plurality of user sets of a preset number; and executing a target task based on the user sets. According to the technical solution provided by the present disclosure, the accuracy of task processing in a vertical category can be improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of Internet application, and particularly relates to a task processing method and device, electronic equipment and storage medium. BACKGROUND

[0002] With the development of Internet application, task processing based on Internet big data is also concerned, for example, precise users are mined for recommendation tasks by statistics of big data information of users to improve recommendation accuracy. In related technologies, RFM (Recency, Frequency, Monetary; time of last consumption, consumption frequency, amount) model is generally used to mine customers for e-commerce to perform task processing, for example, RFM model is used to classify users to perform task processing of all categories, such as recommendation of all categories, but this is not suitable for task processing of vertical categories. SUMMARY

[0003] The present disclosure provides a task processing method, device, electronic equipment and storage medium to at least solve the problem of how to improve the accuracy of task processing in vertical categories in related technologies. The technical solutions of the present disclosure are as follows:

[0004] According to a first aspect of an embodiment of the present disclosure, a task processing method is provided, comprising:

[0005] obtaining a plurality of users corresponding to a target object in a preset time period;

[0006] obtaining behavior information of each user in the plurality of users on the target object in the preset time period, the behavior information comprising behavior time information, behavior frequency information, and resource consumption information generated by the behavior;

[0007] determining first association information between the behavior frequency information and the target object, and second association information between the resource consumption information and the target object, wherein the first association information represents the importance of the behavior frequency information to the user generating the behavior on the target object, and the second association information represents the importance of the resource consumption information to the user generating the behavior on the target object;

[0008] classifying the plurality of users according to the behavior time information, the first association information and the second association information to obtain a preset number of user sets;

[0009] performing a target task based on the user sets.

[0010] In a possible implementation, the step of performing a target task based on the user sets comprises:

[0011] determine weight information corresponding to each of the behavior time information, the first association information and the second association information in each user set, the weight information representing discrete degrees of the respective behavior information;

[0012] determine behavior weighting information of each user according to the behavior time information, the first association information, the second association information and the respective corresponding weight information of each user in each user set;

[0013] perform a target task based on the user set and the behavior weighting information of each user in the user set.

[0014] In a possible implementation, the step of performing a target task based on the user set and the behavior weighting information of each user in the user set comprises:

[0015] obtain target behavior information of the target object;

[0016] based on the target behavior information, filter a target user set matching the target object from the user set of the preset quantity;

[0017] filter a target user from the target user set according to the behavior weighting information of each user in the target user set;

[0018] recommend a virtual resource corresponding to the target object to the target user.

[0019] In a possible implementation, the step of performing a target task based on the user set and the behavior weighting information of each user in the user set comprises:

[0020] sort the behavior weighting information in each user set to obtain a sorting result;

[0021] based on the sorting result, divide users in each user set into multiple levels;

[0022] determine portrait label information of each user based on the level of each user, the portrait label information representing an association degree between each user and the target object.

[0023] In a possible implementation, the step of classifying the multiple users according to the behavior time information, the first association information and the second association information to obtain a user set of a preset quantity comprises:

[0024] respectively obtain a mean value corresponding to each of the behavior time information, the first association information and the second association information;

[0025] determine, based on the respective corresponding mean values, corresponding index information of each user on the behavior time information, the first association information and the second association information respectively;

[0026] classify the plurality of users according to the corresponding index information, to obtain a preset number of user sets.

[0027] In a possible implementation, the step of determining the behavior frequency information and the first association information of the target object, and the resource consumption information and the second association information of the target object comprises:

[0028] obtain a plurality of users corresponding to a plurality of objects in the preset time period;

[0029] determine, based on the plurality of users corresponding to the target object and the plurality of users corresponding to the plurality of objects, heat information of the target object in the plurality of objects;

[0030] obtain multi-object behavior information of each user in the plurality of users corresponding to the target object on the plurality of objects, the multi-object behavior information comprising multi-object behavior frequency information and multi-object resource consumption information;

[0031] determine the first association information according to the behavior frequency information, the multi-object behavior frequency information and the heat information;

[0032] determine the second association information according to the resource consumption information, the multi-object resource consumption information and the heat information.

[0033] In a possible implementation, the step of determining behavior weighting information of each user according to the behavior time information, the first association information, the second association information and the respective corresponding weight information of each user in each user set comprises:

[0034] standardize the behavior time information, the first association information and the second association information of each user in each user set respectively, to obtain standardized behavior time information, standardized first association information and standardized second association information;

[0035] determine behavior weighting information of each user according to the standardized behavior time information, the standardized first association information, the standardized second association information and the respective corresponding weight information.

[0036] According to a second aspect of the embodiments of the present disclosure, a task processing apparatus is provided, comprising:

[0037] a user obtaining module configured to perform obtaining a plurality of users corresponding to a target object in a preset time period;

[0038] The behavior information obtaining module is configured to obtain behavior information of each user in the plurality of users on the target object within the preset time period, the behavior information including behavior time information, behavior frequency information, and resource consumption information generated by the behavior;

[0039] The association information determining module is configured to determine first association information of the behavior frequency information and the target object and second association information of the resource consumption information and the target object, wherein the first association information represents an importance degree of the behavior frequency information for the user to generate the behavior on the target object, and the second association information represents an importance degree of the resource consumption information for the user to generate the behavior on the target object;

[0040] The user set obtaining module is configured to classify the plurality of users according to the behavior time information, the first association information, and the second association information, to obtain a preset number of user sets;

[0041] The task processing module is configured to perform a target task based on the user sets.

[0042] In a possible implementation, the task processing module includes:

[0043] The weight information determining unit is configured to determine weight information corresponding to the behavior time information, the first association information, and the second association information in each user set, wherein the weight information represents a dispersion degree of each behavior information.

[0044] The behavior weighting information determining unit is configured to determine behavior weighting information of each user in each user set according to the behavior time information, the first association information, the second association information, and the corresponding weight information of each user.

[0045] The task processing unit is configured to perform a target task based on the user sets and the behavior weighting information of each user in the user sets.

[0046] In a possible implementation, the task processing unit includes:

[0047] The target behavior information obtaining subunit is configured to obtain target behavior information of the target object.

[0048] The target user set screening subunit is configured to screen a target user set matching the target object from the preset number of user sets based on the target behavior information.

[0049] The target user screening subunit is configured to screen target users from the target user set according to the behavior weighting information of each user in the target user set.

[0050] The first task processing subunit is configured to recommend a virtual resource corresponding to the target object to the target user.

[0051] In a possible implementation, the task processing unit includes:

[0052] The ranking subunit is configured to rank the behavior weighting information in each user set to obtain a ranking result.

[0053] The grade dividing subunit is configured to divide users in each user set into multiple grades based on the ranking result.

[0054] The second task processing subunit is configured to determine portrait label information of each user based on the grade of each user, the portrait label information representing an association degree of each user with the target object.

[0055] In a possible implementation, the user set obtaining module includes:

[0056] The mean value obtaining unit is configured to respectively obtain a mean value corresponding to the behavior time information, the first association information and the second association information.

[0057] The index information obtaining unit is configured to determine corresponding index information of each user on the behavior time information, the first association information and the second association information based on the respective mean values.

[0058] The user set obtaining unit is configured to classify the multiple users according to the corresponding index information to obtain a preset number of user sets.

[0059] In a possible implementation, the association information determining module includes:

[0060] The user obtaining unit is configured to obtain multiple users corresponding to multiple objects in the preset time period.

[0061] The popularity information determining unit is configured to determine popularity information of the target object in the multiple objects based on the multiple users corresponding to the target object and the multiple users corresponding to the multiple objects.

[0062] The multi-object behavior information acquisition unit is configured to acquire multi-object behavior information of a plurality of objects by each user in a plurality of users corresponding to the target object, the multi-object behavior information including multi-object behavior frequency information and multi-object resource consumption information;

[0063] The first association information determination unit is configured to determine the first association information according to the behavior frequency information, the multi-object behavior frequency information, and the heat information.

[0064] The second association information determination unit is configured to determine the second association information according to the resource consumption information, the multi-object resource consumption information, and the heat information.

[0065] In a possible implementation, the behavior weighting information determination unit includes:

[0066] The standardization processing sub-unit is configured to perform standardization processing on the behavior time information corresponding to each user in each user set, the first association information, and the second association information respectively, to obtain standardized behavior time information, standardized first association information, and standardized second association information.

[0067] The behavior weighting information determination sub-unit is configured to determine the behavior weighting information of each user according to the standardized behavior time information, the standardized first association information, the standardized second association information, and the respective corresponding weight information.

[0068] According to a third aspect of the embodiments of the present disclosure, an electronic device is provided, including a processor, a memory for storing instructions executable by the processor, and wherein the processor is configured to execute the instructions to implement the method according to any one of the first aspect.

[0069] According to a fourth aspect of the embodiments of the present disclosure, a computer readable storage medium is provided, when instructions in the computer readable storage medium are executed by a processor of an electronic device, the electronic device can execute the method according to any one of the first aspect of the embodiments of the present disclosure.

[0070] According to a fifth aspect of the embodiments of the present disclosure, a computer program product is provided, including computer instructions, when the computer instructions are executed by a processor, the computer executes the method according to any one of the first aspect of the embodiments of the present disclosure.

[0071] The technical solutions provided by the embodiments of the present disclosure at least bring the following beneficial effects:

[0072] By acquiring a plurality of users corresponding to the target object in a preset time period, the behavior frequency information and the resource consumption information in the behavior information of each user in the plurality of users to the target object in the preset time period are adjusted, that is, the first association information of the behavior frequency information and the target object, and the second association information of the resource consumption information and the target object are determined. The adjusted behavior information can better distinguish the association degree of the user and the target object, so that the classification of the plurality of users based on the behavior time information, the first association information and the second association information is more accurate. Further, the task processing based on the user set can improve the efficiency and accuracy of the task processing.

[0073] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0074] The accompanying drawings incorporated in the specification and forming a part of the specification illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure without imposing undue limitation on the disclosure.

[0075] Figure 1 is a schematic diagram of an application environment according to an exemplary embodiment.

[0076] Figure 2 is a flowchart of a task processing method according to an exemplary embodiment.

[0077] Figure 3 is a flowchart of a method of performing a target task based on a user set according to an exemplary embodiment.

[0078] Figure 4 is a flowchart of a method of performing a target task based on a user set and behavior weighting information of each user in the user set according to an exemplary embodiment.

[0079] Figure 5 is a flowchart of a method of performing a target task based on a user set and behavior weighting information of each user in the user set according to an exemplary embodiment.

[0080] Figure 6 is a flowchart of a method of determining first association information of behavior frequency information and a target object, and second association information of resource consumption information and the target object according to an exemplary embodiment.

[0081] Figure 7 is a flowchart of a method of classifying a plurality of users to obtain a preset number of user sets according to behavior time information, first association information and second association information according to an exemplary embodiment.

[0082] Figure 8 is a task processing device block diagram according to an exemplary embodiment.

[0083] Figure 9 is a block diagram of an electronic device for task processing according to an exemplary embodiment. DETAILED DESCRIPTION

[0084] In order for those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings.

[0085] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The implementation described in the following exemplary embodiments does not represent all implementations consistent with the present disclosure. Rather, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0086] Please refer to Figure 1 , Figure 1 is a schematic diagram of an application environment according to an exemplary embodiment, as Figure 1 shown, the application environment can include a server 01 and a terminal 02.

[0087] In an optional embodiment, the server 01 can be used for task processing. Specifically, the server 01 can be a standalone physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms, etc. Basic cloud computing services.

[0088] In an optional embodiment, the terminal 02 can respond to the result of the task processing, for example, receive a recommended virtual resource corresponding to the target object. Specifically, the terminal 02 can include, but is not limited to, electronic devices such as smartphones, desktop computers, tablets, laptops, smart speakers, digital assistants, augmented reality (AR) / virtual reality (VR) devices, smart wearable devices, and the like. Optionally, the operating system running on the electronic device can include, but is not limited to, Android, IOS, Linux, Windows, and the like.

[0089] In addition, it should be noted that, Figure 1 The above is only one application environment of the image processing method provided by the present disclosure.

[0090] In the embodiments of the present disclosure, the server 01 and the terminal 02 described above can be connected directly or indirectly through wired or wireless communication, which is not limited in the present application.

[0091] It should be noted that the following figures show a possible sequence of steps, which actually does not have to be strictly followed. Some steps can be performed in parallel without being dependent on each other. The user information (including but not limited to user device information, user personal information, user behavior information, etc.) and data (including but not limited to data for display, training data, etc.) involved in the present disclosure are all information and data authorized by the user or authorized by all parties.

[0092] Figure 2 is a flowchart of a task processing method according to an exemplary embodiment. As Figure 2 shown, it can include the following steps.

[0093] In step S201, a plurality of users corresponding to a target object in a preset time period are obtained.

[0094] In the embodiments of the present disclosure, the plurality of users corresponding to the target object can refer to users performing a preset behavior on the target object. The preset behavior can be any one of a purchase behavior, a collection behavior, or the like; the object can refer to an object that can be performed on the preset behavior, such as mobile phones, milk powder, e-books, and the like, and the target object can be any one of these categories. The preset time period can be a time period of a preset time period from the current time, and the present disclosure does not limit the preset time period, which can be 6 months or 3 months. In one embodiment, the user obtains a plurality of users corresponding to the target object in the preset time period through a user account identifier, which refers to obtaining a plurality of user accounts corresponding to the target object in the preset time period.

[0095] In one example, a plurality of users who have purchased milk powder within 6 months from the current time can be acquired, i.e., a plurality of users corresponding to the milk powder category within a preset time period are acquired.

[0096] In step S203, behavior information of each user in the plurality of users on the target object within the preset time period is acquired, and the behavior information can include behavior time information, behavior frequency information, and resource consumption information generated by the behavior.

[0097] In one example, the behavior information of each user in the plurality of users on the target object within the preset time period can be acquired based on the RFM model. In this case, the behavior time information can refer to the time information closest to the current time in the time information of the user purchasing the target object, such as 2 days (purchased the target object 2 days ago). The behavior frequency information can refer to the number of times the user purchases the target object within the preset time period, such as 3 times; and the resource consumption information generated by the behavior can refer to the amount of money consumed by the user in purchasing the target object within the preset time period, such as 1000 yuan. Herein, this is only an example and does not limit the present disclosure.

[0098] In step S205, the behavior frequency information and the first association information of the target object, and the resource consumption information and the second association information of the target object are determined.

[0099] The first association information can represent the importance of the behavior frequency information to the user generating the above behavior on the target object, and the second association information can represent the importance of the resource consumption information to the user generating the above behavior on the target object.

[0100] In actual application, an e-commerce platform generally positions a corresponding user group for a certain category, so that the promotion of the certain category can be carried out for the user group. Based on this, users interested in the category can be screened from the frequency information of the user purchasing the category and the amount of money consumed in purchasing the category, such as the higher the purchase frequency of the user and / or the more the amount of money consumed, the more interested the user can be in the category, and the user can be a high-value user of the category.

[0101] However, due to promotion activities in the e-commerce platform, a certain category, such as milk, may be promoted within the preset time period, resulting in a large number of users in the e-commerce platform purchasing the milk, and a part of the large number of users may not be high-value users of the milk category, i.e., not users who are really interested in the milk category. In order to more accurately screen out high-value users of the milk category, the behavior frequency and resource consumption of the user can be adjusted to offset the deviation between the behavior information of the user and the interest of the user caused by the promotion. Based on this, the behavior frequency information and the resource consumption information can be adjusted to reflect the real interest of the user.

[0102] Based on the above analysis, in one example, the target object can obtain the discount information in a preset time period, such as the number of discounts, the strength of discounts, etc. If the target object has discount information in the preset time period, it can be considered that some of the above-mentioned users have generated the preset behavior, such as the purchase behavior, due to the stimulation of the discount information. Based on this, in order to obtain more accurate behavior frequency information and resource consumption information, when the target object has discount information in the preset time period, a weight value can be added to the behavior frequency information and the resource consumption information, respectively, and the weight value can be a value between 0 and 1, such as the more the number of discounts, the greater the strength of the discounts, and the smaller the weight value. In this way, the purchase frequency and the purchase amount due to the discount information can be balanced, so that the target frequency information obtained by multiplying the frequency information by the corresponding weight value, and the target resource consumption information obtained by multiplying the resource consumption information by the corresponding weight value, can express the more real interest of the user in the target object. Therefore, the target frequency information can be used as the first association information, and the target resource consumption information can be used as the second association information.

[0103] In step S207, the plurality of users are classified according to the behavior time information, the first association information, and the second association information, to obtain a preset number of user sets.

[0104] In actual application, the plurality of users can be classified according to the behavior time information, the first association information and the second association information adjusted based on the above-mentioned behavior frequency information and resource consumption information, such as obtaining a preset time threshold, a frequency threshold and a resource consumption threshold, and dividing the users whose behavior time information, first association information and second association information are respectively higher than the corresponding threshold into a user set; the users whose behavior time information, first association information and second association information are respectively lower than the corresponding threshold are divided into a user set, so that two user sets can be obtained. The present disclosure does not limit the preset number, the preset time threshold, the frequency threshold and the resource consumption threshold, and does not limit the classification method, as long as the user sets after classification can be effectively used for task processing.

[0105] In step S209, the target task is executed based on the user set.

[0106] In the embodiments of the present disclosure, the target task can be executed based on the user set. For example, the user is labeled with a portrait tag, and the target object is recommended to the user.

[0107] The user set here can be regarded as a coarse classification of users. For example, the preset time period is 6 months from the current time, the behavior time information of the users in a user set is 5 months ago, the behavior frequency information is less than or equal to 2 times, and the resource consumption is greater than 2000 yuan. It can be considered that the users in the user set are periodic users. The periodic users here can refer to users who consume at the time of promotion. Based on this, when the target object is promoted, all or part of the users in the user set can be recommended.

[0108] Optionally, when recommending to part of the users in the user set, the part of the users can be filtered based on the behavior time information, the first association information and the second association information of the users in the user set, so that the part of the users in the user set can be recommended.

[0109] For labeling the portrait tag of a user, a set tag can be labeled for each user set. For example, the set tag of a user set can be "periodic user of the target object". Correspondingly, the set tag can be used as the portrait tag of the user in the corresponding user set, from which the interest of the user in the target object can be known.

[0110] By obtaining a plurality of users corresponding to the target object in a preset time period, adjusting the behavior frequency information and the resource consumption information in the behavior information of each user in the plurality of users in the preset time period, that is, determining the first association information of the behavior frequency information and the target object, and the second association information of the resource consumption information and the target object, the adjusted behavior information can better distinguish the degree of association between the user and the target object, so that the classification of the plurality of users based on the behavior time information, the first association information and the second association information is more accurate. Further, the efficiency and accuracy of the task processing based on the user set can be improved.

[0111] Figure 3 is a method flowchart for performing a target task based on a user set according to an example embodiment. As shown in Figure 3 In a possible implementation, the step S209 can include:

[0112] In step S301, the weight information corresponding to the behavior time information, the first association information and the second association information in each user set is determined. The weight information can represent the dispersion degree of each behavior information.

[0113] In an example, the weight information corresponding to the behavior time information of different users in a user set can be the same, the weight information corresponding to the first association information of different users can be the same, and the weight information corresponding to the second association information of different users can be the same.

[0114] In actual applications, in order to better distinguish the value of a user in a user set to a target object, three dimensions in the behavior information of the user can be analyzed. If the three dimensions are simply superimposed, the user cannot be effectively distinguished. Based on this, the three dimensions can be sorted to represent the influence degree of different dimensions on distinguishing the user. For example, the dimension with a large influence degree on distinguishing the user can be set to have a higher weight. In an example, the influence degree of each dimension on distinguishing the user can be represented by the information dispersion degree of each dimension. For example, the dispersion degree can be calculated using a coefficient of variation. The formula (1) of the coefficient of variation C·V can be as follows:

[0115] C·V=(standard deviation SD / average value Mean)×100% (1)

[0116] Taking the behavior time information as an example, it is assumed that a user set includes 5 users, and the preset time period is 6 months from the current time. The behavior time information of the 5 users is 8, 7, 30, 50, and 5 days respectively. The corresponding average value Mean=(8+7+30+50+5) / 5=20; the standard deviation SD=5.6. Thus, C·V=(1538 / 20)×100%=76.9% can be obtained. μ can be the average value, which is 20 here; U i The behavior time information of the i-th user can be determined. Based on the same method, the corresponding weight information of the first association information and the second association information can be determined respectively.

[0117] The dispersion degree of each behavior information can also be represented by the variance and the standard deviation of each behavior information, which is not limited in the present disclosure.

[0118] In step S303, the behavior weighted information of each user is determined according to the behavior time information, the first association information, the second association information, and the corresponding weight information of each user in each user set.

[0119] In an example, the behavior weighted information J of each user can be obtained according to the following formula (2):

[0120] J=C·V 1 ×R+C·V 2 ×F_t+C·V 3 ×M_t (2)

[0121] Wherein, R is the behavior time information of a user, C·V 1 is the weight information corresponding to the behavior time information in the user set of the user; F_t is the first association information of a user, C·V 2 is the weight information corresponding to the first association information in the user set of the user; M_t is the second association information of a user, C·V3 is the weight information corresponding to the second association information in the user set of the one user.

[0122] In a possible implementation, the step S303 can include:

[0123] The behavior time information, the first association information and the second association information corresponding to each user in each user set are standardized respectively to obtain standardized behavior time information, standardized first association information and standardized second association information; and the behavior weighting information of each user can be determined according to the standardized behavior time information, the standardized first association information, the standardized second relationship information and the weight information corresponding to each.

[0124] In actual application, when calculating the behavior weighting information of each user, the behavior time information, the first association information and the second association information corresponding to each user in each user set can be standardized respectively, and then the behavior weighting information of each user can be determined according to the standardized behavior time information, the standardized first association information, the standardized second relationship information and the weight information corresponding to each. The standardization processing here can be based on Min-Max standardization, Z-Score standardization and the like, which is not limited in the present disclosure. By standardizing the behavior time information, the first association information and the second association information, the behavior time information, the first association information and the second association information can be converted into dimensionless pure values, so that the behavior weighting information is more accurate.

[0125] In step S305, the target task is executed based on the user set and the behavior weighting information of each user in the user set.

[0126] In actual application, the target user set can be selected from the preset number of user sets based on the target task, and the target user can be selected from the target user set to execute the target task.

[0127] By taking the dispersion degree of each behavior information as the weight information corresponding to each behavior information, the weight information corresponding to the behavior information with large dispersion degree can be higher, so that the user can be distinguished more effectively, and the execution accuracy of the target task can be improved.

[0128] Figure 4 is a method flow chart for executing a target task based on a user set and behavior weighting information of each user in the user set according to an example embodiment. As shown in Figure 4 In a possible implementation, the above step S305 can include:

[0129] In step S401, target behavior information of a target object is obtained.

[0130] In step S403, based on the target behavior information, a target user set matching the target object is filtered from the preset number of user sets;

[0131] In step S405, according to the behavior weighting information of each user in the target user set, a target user is filtered from the target user set.

[0132] In step S407, a virtual resource corresponding to the target object is recommended to the target user.

[0133] In the embodiments of the present specification, the target task can be a recommendation task of the target object. Based on this, the target behavior information of the target object can be obtained, which can represent the purpose of recommendation, for example, promotion of the target object. In one example, the target behavior information of the target object can be behavior time information far from the current, low behavior frequency, and high resource consumption, that is, when the target behavior information is behavior time information far from the current, low behavior frequency, and high resource consumption, it can represent that the purpose of recommendation is promotion. Since the user set is classified based on the behavior time information, the first association information and the second association information, the behavior information of the users in one user set to the target object can be relatively consistent, and therefore, based on the target behavior information, a target user set matching the target behavior information, that is, a target user set matching the target object, can be filtered from the preset number of user sets.

[0134] In another example, a corresponding relationship between the recommendation purpose and the target behavior information can be set in advance, where the target behavior information can include target time information, target first association information and target second association information, so as to directly match the behavior time information, the first association information and the second association information corresponding to the preset number of user sets, and filter a target user set matching the target object.

[0135] Further, each user in the target user set can be filtered according to the behavior weighting information of the target user set, and the target user can be filtered from the target user set. The virtual resource corresponding to the target object can be recommended to the target user. For example, a user with high behavior weighting information can be filtered from the target user set as a target user, so that the virtual resource can be recommended to the target user, for example, a coupon for milk powder can be recommended to the target user.

[0136] Through this rough screening and accurate screening method of first filtering the target user set and then filtering the target user from the target user set, the screening efficiency can be improved, and the recommendation accuracy can be improved.

[0137] Figure 5is a method flowchart for performing a target task based on a user set and behavior weighting information of each user in the user set according to an exemplary embodiment. As shown in Figure 5 In a possible implementation, the step S305 can include the following steps.

[0138] In step S501, the behavior weighting information in each user set is sorted to obtain a sorting result.

[0139] In step S503, based on the sorting result, the users in each user set are divided into multiple levels.

[0140] In step S505, based on the level of each user, portrait label information of each user is determined, which can represent the degree of association of each user with the target object.

[0141] In the embodiments of the present disclosure, the behavior weighting information in each user set can be sorted to obtain a sorting result, and based on the sorting result, the users in each user set can be divided into multiple levels, for example, the users in each user set can be divided into three level sub-sets, which can include high, medium and low levels, and the level can represent the degree of association with the target object. Thus, based on the level of each user, the portrait label information of each user can be determined, for example, if the level of user A is high, the portrait label information of user A can be determined as "high degree of association with the target object", and taking the target object as a milk powder category as an example, the portrait label information of user A can be "high degree of association with the milk powder category" or "milk powder category / high", which is not limited in the present disclosure. Further, based on the determined portrait label information, each user can be labeled with the portrait label information associated with the target object.

[0142] By classifying the users through the behavior weighting information and determining the portrait label information, each user can have portrait label information associated with the target object, which facilitates the accurate execution of the target task.

[0143] Figure 6 is a method flowchart for performing a target task based on a user set and behavior weighting information of each user in the user set according to an exemplary embodiment. As shown in Figure 6 In a possible implementation, the step S305 can include the following steps.

[0144] In step S601, a plurality of users corresponding to a plurality of objects in a preset time period are obtained.

[0145] In an embodiment of the present specification, a plurality of users performing a preset behavior on any of a plurality of objects in a preset time period can be obtained, for example, all users purchasing any category in an e-commerce platform in a preset time period can be obtained. It should be noted that the plurality of users corresponding to the plurality of objects can be users after deduplication.

[0146] In step S603, based on the plurality of users corresponding to the target object and the plurality of users corresponding to the plurality of objects, the heat information of the target object in the plurality of objects is determined.

[0147] In one example, the heat information W_IDF can be determined based on the IDF in the TFIDF (term frequency-inverse document frequency), for example, the heat information can be determined based on the following formula (3):

[0148]

[0149] Wherein, U1 is the number of the plurality of users corresponding to the plurality of objects, and U2 is the number of the plurality of users corresponding to the target object.

[0150] In step S605, the multi-object behavior information of each user in the plurality of users corresponding to the target object to the plurality of objects is obtained, which can include multi-object behavior frequency information and multi-object resource consumption information.

[0151] In an embodiment of the present specification, the multi-object behavior information of each user in the plurality of users corresponding to the target object to the plurality of objects can be obtained, for example, the information of each user in the plurality of users corresponding to the target object performing a preset behavior on the plurality of objects can be obtained as multi-object behavior information, for example, the purchase frequency information and resource consumption information of each user in the plurality of users corresponding to the target object to all categories.

[0152] In step S607, the first association information is determined according to the behavior frequency information, the multi-object behavior frequency information and the heat information.

[0153] In one example, the first association information F_t can be determined based on the TFIDF, for example, F_t can be determined based on the following formula (4):

[0154]

[0155] Wherein, F_t is the first association information of one user; F is the behavior frequency information of the one user; F_a is the multi-object behavior frequency information of the one user; and W_IDF is the heat information.

[0156] In step S609, the second association information is determined according to the resource consumption information, the multi-object resource consumption information and the hotness information.

[0157] In one example, the second association information M_t can be determined based on TFIDF, for example, M_t can be determined based on the following formula (5):

[0158]

[0159] Wherein, M_t is the second association information of one user; M is the resource consumption information of the one user; M_a is the multi-object resource consumption information of the one user; W_IDF is the hotness information.

[0160] By using the hotness information of the target object in the plurality of objects and the multi-object behavior information of the user on the plurality of objects, the behavior frequency information and the resource consumption information of each user are adjusted, that is, by combining the TFIDF and the RFM model, the first association information and the second association information can better represent the importance of the behavior frequency information and the resource consumption information to the user's behavior on the target object, so that the first association information and the second association information can be more effectively used for task processing.

[0161] Figure 7 Fig. 7 is a flow chart of a method for classifying a plurality of users to obtain a preset number of user sets according to behavior time information, first association information and second association information according to an example embodiment. As shown in Fig. 7, the step S207 can include: Figure 7

[0162] In step S701, the mean values corresponding to the behavior time information, the first association information and the second association information respectively are obtained;

[0163] In step S703, the index information corresponding to the behavior time information, the first association information and the second association information respectively of each user is determined based on the mean values corresponding thereto respectively;

[0164] In step S705, the plurality of users are classified according to the corresponding index information to obtain a preset number of user sets.

[0165] ​As an example, it is assumed that the mean values of the behavior time information, the first association information and the second association information of a user set are a1, a2 and a3 respectively. Based on this, each behavior information can be divided into two index information based on the respective corresponding mean values. For example, a1 or more can be taken as high time index information a11, and less than a1 can be taken as low time index information a12; a2 or more can be taken as high frequency index information a21, and less than a1 can be taken as low frequency index information a22; a3 or more can be taken as high resource consumption index information a31, and less than a1 can be taken as low resource consumption index information a32. In this way, six index information a11, a12; a21, a22; a31, a32 can be obtained.

[0166] Further, the behavior time information, the first association information and the second association information of each user can be compared with the respective corresponding mean values to determine the corresponding index information of each user on the behavior time information, the first association information and the second association information respectively. For example, the corresponding index information of user A on the behavior time information, the first association information and the second association information is a11, a22 and a31 respectively. Based on this, users with the same index information can be taken as a user set to realize the classification of multiple users.

[0167] Alternatively, the six index information a11, a12; a21, a22; a31, a32 can be combined to obtain eight combinations as shown in Table 1, wherein one combination can correspond to one user set. Thus, the behavior time information, the first association information and the second association information of each user are compared with the respective corresponding mean values, and each user is divided into the corresponding user set to realize the classification of multiple users.

[0168] Table 1

[0169] Combination / User Set a11, a21, a31 a11, a21, a32 a11, a22, a31 a11, a22, a32 a12, a21, a31 a12, a21, a32 a12, a22, a31 a12, a22, a32

[0170] As shown in Table 1, the index information corresponding to the behavior information of three dimensions is included in each combination, so that each user set can be consistent on the index information corresponding to each behavior information, and the user set classified in this way is also relatively fine, which can be better used for the execution of the target task.

[0171] Figure 8 is a block diagram of a task processing device according to an example embodiment. Referring to Figure 8 The device can include:

[0172] The user acquisition module 801 is configured to acquire a plurality of users corresponding to a target object in a preset time period.

[0173] The behavior information obtaining module 803 is configured to obtain behavior information of each user in the plurality of users on the target object within a preset time period. The behavior information can include behavior time information, behavior frequency information, and resource consumption information generated by the behavior.

[0174] The association information determining module 805 is configured to determine first association information of the behavior frequency information and the target object and second association information of the resource consumption information and the target object. The first association information represents the importance of the behavior frequency information to the user generating the behavior on the target object. The second association information represents the importance of the resource consumption information to the user generating the behavior on the target object.

[0175] The user set obtaining module 807 is configured to classify the plurality of users according to the behavior time information, the first association information, and the second association information, to obtain a preset number of user sets.

[0176] The task processing module 809 is configured to perform the target task based on the user sets.

[0177] By obtaining the plurality of users corresponding to the target object within the preset time period, the behavior frequency information and the resource consumption information in the behavior information of each user in the plurality of users on the target object within the preset time period are adjusted, that is, the first association information of the behavior frequency information and the target object and the second association information of the resource consumption information and the target object are determined. The adjusted behavior information can better distinguish the association degree of the user and the target object, so that the classification of the plurality of users based on the behavior time information, the first association information, and the second association information is more accurate. The task processing based on the user set can improve the efficiency and accuracy of the task processing.

[0178] In a possible implementation, the task processing module 809 can include:

[0179] The weight information determining unit is configured to determine weight information corresponding to the behavior time information, the first association information, and the second association information in each user set. The weight information represents the dispersion degree of each behavior information.

[0180] The behavior weighting information determining unit is configured to determine behavior weighting information of each user according to the behavior time information, the first association information, the second association information, and the weight information corresponding to each user in each user set.

[0181] The task processing unit is configured to perform the target task based on the user sets and the behavior weighting information of each user in the user sets.

[0182] In a possible implementation, the task processing unit can include:

[0183] The target behavior information acquisition sub-unit is configured to acquire target behavior information of the target object.

[0184] The target user set screening sub-unit is configured to screen a target user set matched with the target object from a preset number of user sets based on the target behavior information.

[0185] The target user screening sub-unit is configured to screen a target user from the target user set according to behavior weighting information of each user in the target user set.

[0186] The first task processing sub-unit is configured to recommend a virtual resource corresponding to the target object to the target user.

[0187] In a possible implementation, the task processing unit can include:

[0188] The sorting sub-unit is configured to sort the behavior weighting information in each user set to obtain a sorting result.

[0189] The grade dividing sub-unit is configured to divide the users in each user set into a plurality of grades based on the sorting result.

[0190] The second task processing sub-unit is configured to determine portrait tag information of each user based on the grade of each user, the portrait tag information representing an association degree of each user with the target object.

[0191] In a possible implementation, the user set acquisition module 805 can include:

[0192] The mean value acquisition unit is configured to acquire a mean value of the behavior time information, the first association information and the second association information respectively.

[0193] The index information acquisition unit is configured to determine index information corresponding to each user respectively on the behavior time information, the first association information and the second association information based on the respective mean values.

[0194] The user set acquisition unit is configured to classify a plurality of users according to the corresponding index information to obtain a preset number of user sets.

[0195] In a possible implementation, the association information determination module can include:

[0196] The user acquisition unit is configured to acquire a plurality of users corresponding to a plurality of objects in a preset time period.

[0197] The heat information determination unit is configured to determine heat information of the target object in the plurality of objects based on a plurality of users corresponding to the target object and a plurality of users corresponding to the plurality of objects;

[0198] The multi-object behavior information acquisition unit is configured to acquire multi-object behavior information of the plurality of objects by each user in the plurality of users corresponding to the target object, which can include multi-object behavior frequency information and multi-object resource consumption information;

[0199] The first association information determination unit is configured to determine first association information according to the behavior frequency information, the multi-object behavior frequency information and the heat information;

[0200] The second association information determination unit is configured to determine second association information according to the resource consumption information, the multi-object resource consumption information and the heat information.

[0201] In a possible implementation, the behavior weighting information determination unit can include:

[0202] The standardization processing sub-unit is configured to respectively perform standardization processing on the behavior time information, the first association information and the second association information corresponding to each user in each user set to obtain standardized behavior time information, standardized first association information and standardized second association information;

[0203] The behavior weighting information determination sub-unit is configured to determine the behavior weighting information of each user according to the standardized behavior time information, the standardized first association information, the standardized second association information and the respective corresponding weight information.

[0204] As to the apparatus in the above-mentioned embodiments, the specific manners in which various modules perform operations have been described in detail in the embodiments of the method, and will not be described in detail here.

[0205] Figure 9 is a block diagram of an electronic device for task processing according to an example embodiment. The electronic device can be a server, and its internal structure diagram can be as shown in Figure 9 The electronic device includes a processor, a memory and a network interface connected through a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The network interface of the electronic device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement a task processing method.

[0206] Those skilled in the art can understand that Figure 9 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present disclosure, and does not constitute a limitation on the electronic device to which the scheme of the present disclosure is applied. The specific electronic device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0207] In an example embodiment, an electronic device is also provided, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the task processing method in the embodiments of the present disclosure.

[0208] In an example embodiment, a computer readable storage medium is also provided, which, when the instructions in the computer readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform the task processing method in the embodiments of the present disclosure. The computer readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0209] In an example embodiment, a computer program product containing instructions is also provided, which, when running on a computer, enables the computer to perform the task processing method in the embodiments of the present disclosure.

[0210] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium and, when executed, can include the processes of the above-mentioned embodiments of the methods. Any reference to memory, storage, databases, or other media in the embodiments provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0211] Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features disclosed herein. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

[0212] It should be understood that the present disclosure is not limited to the precise structures as herein described and illustrated in the drawings, and that various modifications and changes can be made without departing from its scope. The scope of the present disclosure is limited only by the claims that follow.

Claims

1. A task processing method characterized by, The method comprises: acquiring a plurality of users corresponding to a target object in a preset time period; acquiring behavior information of each user in the plurality of users on the target object in the preset time period, the behavior information comprising behavior time information, behavior frequency information, and resource consumption information generated by the behavior; acquiring a plurality of users corresponding to a plurality of objects in the preset time period; determining, based on the plurality of users corresponding to the target object and the plurality of users corresponding to the plurality of objects, heat information of the target object in the plurality of objects; acquiring multi-object behavior information of each user in the plurality of users corresponding to the target object on the plurality of objects, the multi-object behavior information comprising multi-object behavior frequency information and multi-object resource consumption information; determining first association information according to the behavior frequency information, the multi-object behavior frequency information, and the heat information; determining second association information according to the resource consumption information, the multi-object resource consumption information, and the heat information, wherein the first association information represents the importance of the behavior frequency information to the behavior of the user on the target object, and the second association information represents the importance of the resource consumption information to the behavior of the user on the target object; classifying the plurality of users according to the behavior time information, the first association information, and the second association information to obtain a preset number of user sets; executing a target task based on the user sets.

2. The task processing method according to claim 1, characterized by, The step of executing the target task based on the user sets comprises: determining weight information corresponding to the behavior time information, the first association information, and the second association information in each user set, wherein the weight information represents the dispersion degree of each behavior information; determining behavior weighting information of each user according to the behavior time information, the first association information, the second association information, and the corresponding weight information of each user in each user set; executing the target task based on the user sets and the behavior weighting information of each user in the user sets.

3. The task processing method according to claim 2, characterized by, The step of executing the target task based on the user sets and the behavior weighting information of each user in the user sets comprises: acquiring target behavior information of the target object; screening, based on the target behavior information, a target user set matching the target object from the preset number of user sets; screening a target user from the target user set according to the behavior weighting information of each user in the target user set; recommending virtual resources corresponding to the target object to the target user.

4. The task processing method according to claim 2, characterized by, The step of executing the target task based on the user sets and the behavior weighting information of each user in the user sets comprises: sorting the behavior weighting information in each user set to obtain a sorting result; dividing the users in each user set into a plurality of levels based on the sorting result; determining portrait label information of each user based on the level of each user, wherein the portrait label information represents the association degree of each user with the target object.

5. The task processing method of claim 1, wherein, The step of classifying the plurality of users according to the behavior time information, the first association information, and the second association information to obtain a preset number of user sets comprises: respectively obtaining a mean value corresponding to each of the behavior time information, the first association information, and the second association information; determining, based on the respective mean values, corresponding index information of each user on the behavior time information, the first association information, and the second association information; classifying the plurality of users according to the corresponding index information to obtain a preset number of user sets.

6. The task processing method according to claim 2, wherein The step of determining the behavior weighting information of each user according to the behavior time information, the first association information, the second association information, and the respective corresponding weight information of each user in each user set comprises: respectively performing standardization processing on the behavior time information, the first association information, and the second association information corresponding to each user in each user set to obtain standardized behavior time information, standardized first association information, and standardized second association information; determining the behavior weighting information of each user according to the standardized behavior time information, the standardized first association information, the standardized second association information, and the respective corresponding weight information.

7. A task processing apparatus characterized by comprising: Comprise: A user acquisition module configured to perform acquiring a plurality of users corresponding to a target object within a preset time period; A behavior information acquisition module configured to perform acquiring behavior information of each user in the plurality of users on the target object within the preset time period, the behavior information comprising behavior time information, behavior frequency information, and resource consumption information generated by the behavior; An association information determination module configured to perform determining first association information of the behavior frequency information and the target object, and second association information of the resource consumption information and the target object, wherein the first association information represents the importance of the behavior frequency information for the user to generate the behavior on the target object, and the second association information represents the importance of the resource consumption information for the user to generate the behavior on the target object; A user set acquisition module configured to perform classifying the plurality of users according to the behavior time information, the first association information, and the second association information to obtain a preset number of user sets; A task processing module configured to perform executing a target task based on the user sets; The association information determination module comprises: A user acquisition unit configured to perform acquiring a plurality of users corresponding to a plurality of objects within the preset time period; A popularity information determination unit configured to perform determining popularity information of the target object in the plurality of objects based on the plurality of users corresponding to the target object and the plurality of users corresponding to the plurality of objects; A multi-object behavior information acquisition unit configured to perform acquiring multi-object behavior information of each user in the plurality of users corresponding to the target object on the plurality of objects, the multi-object behavior information comprising multi-object behavior frequency information and multi-object resource consumption information; The first association information determination unit is configured to determine the first association information according to the behavior frequency information, the multi-object behavior frequency information, and the hotness information. The second association information determination unit is configured to determine the second association information according to the resource consumption information, the multi-object resource consumption information, and the hotness information.

8. The task processing apparatus according to claim 7, characterized by The task processing module comprises: The weight information determination unit is configured to determine weight information corresponding to the behavior time information, the first association information, and the second association information in each user set, wherein the weight information represents the dispersion degree of each behavior information. The behavior weighting information determination unit is configured to determine behavior weighting information of each user according to the behavior time information, the first association information, the second association information, and the corresponding weight information of each user in each user set. The task processing unit is configured to perform a target task based on the user set and the behavior weighting information of each user in the user set.

9. The task processing apparatus according to claim 8, characterized by The task processing unit comprises: The target behavior information acquisition subunit is configured to acquire target behavior information of the target object. The target user set screening subunit is configured to screen a target user set matching the target object from the preset number of user sets based on the target behavior information. The target user screening subunit is configured to screen a target user from the target user set according to the behavior weighting information of each user in the target user set. The first task processing subunit is configured to recommend a virtual resource corresponding to the target object to the target user.

10. The task processing apparatus according to claim 8, characterized by The task processing unit comprises: The sorting subunit is configured to sort the behavior weighting information in each user set to obtain a sorting result. The level division subunit is configured to divide users in each user set into multiple levels based on the sorting result. The second task processing subunit is configured to determine portrait label information of each user based on the level of each user, wherein the portrait label information represents the association degree between each user and the target object.

11. The task processing apparatus according to claim 7, characterized by The user set acquisition module comprises: The mean value acquisition unit is configured to acquire mean values corresponding to the behavior time information, the first association information, and the second association information, respectively. The index information acquisition unit is configured to determine index information corresponding to the behavior time information, the first association information, and the second association information of each user based on the corresponding mean values. The user set acquisition unit is configured to classify the multiple users according to the corresponding index information to obtain a preset number of user sets.

12. The task processing apparatus according to claim 8, characterized by The behavior weighting information determination unit comprises: The standardized processing subunit is configured to perform standardized processing on the behavior time information, the first association information and the second association information corresponding to each user in each user set respectively, to obtain standardized behavior time information, standardized first association information and standardized second association information. The behavior weighting information determination subunit is configured to determine the behavior weighting information of each user according to the standardized behavior time information, the standardized first association information, the standardized second association information and the respective corresponding weight information.

13. An electronic device, comprising: Comprise: A processor; A memory for storing instructions executable by the processor; Wherein the processor is configured to execute the instructions to implement the task processing method of any one of claims 1 to 6.

14. A computer-readable storage medium, characterized in that, When the instructions in the computer readable storage medium are executed by the processor of the electronic device, the electronic device can execute the task processing method of any one of claims 1 to 6.

15. A computer program product comprising computer instructions, characterized in that, The computer instructions are executed by the processor to implement the task processing method of any one of claims 1 to 6.

Images