Data processing method and device, equipment, storage medium and product

Abstract

The embodiment of the invention provides a data processing method and device, equipment, a storage medium and a product, and the method comprises the steps: determining a plurality of target impact factors of a target product for the target product, and enabling the target impact factors to be actions and / or product states which affect the order quantity of the target product; according to the multiple target influence factors, a target task for the target product is determined, the target task comprises at least one subtask and an execution sequence of the at least one subtask, and the target task is indicated by the target influence factors; and recommending the target task to prompt to execute the at least one sub-task according to the execution sequence, so that the accurate target task can be provided for the shop for the target product, the shop is prompted to execute the target task, and the product information of the target product is efficiently recommended.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular, to a data processing method, apparatus, device, storage medium, and product. Background Art

[0002] In the field of e-commerce, product information is recommended to users so that they can purchase the corresponding products online. Currently, this is done by analyzing the user's historical behavior data, finding product information of other products similar to the target product and recommending it to the user, or finding other users similar to the user and recommending the target product to other customers.

[0003] The above method has the problem of being unable to efficiently recommend product information. Summary of the invention

[0004] The embodiments of the present disclosure provide a data processing method, apparatus, device, computer-readable storage medium, and product, which are used to solve the technical problem that the prior art cannot efficiently recommend product information.

[0005] In a first aspect, an embodiment of the present disclosure provides a data processing method, including:

[0006] For a target product, multiple target influencing factors of the target product are determined, where the target influencing factors are actions and / or product states that affect the order volume of the target product;

[0007] Determining a target task for a target product according to a plurality of target impact factors, the target task comprising: at least one subtask and an execution order of at least one subtask, the target task being indicated by the target impact factor;

[0008] The target task is recommended to prompt execution of at least one subtask in the execution order.

[0009] In a second aspect, an embodiment of the present disclosure provides a data processing device, including:

[0010] A first determination unit is used to determine, for a target product, a plurality of target influencing factors of the target product, where the target influencing factors are actions and / or product states that affect the order quantity of the target product;

[0011] A second determining unit is used to determine a target task for a target product according to a plurality of target impact factors, wherein the target task includes at least one subtask and an execution order of at least one subtask, and the target task is indicated by the target impact factor;

[0012] The recommendation unit is used to recommend a target task to prompt the user to execute at least one subtask in an execution order.

[0013] In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor and a memory;

[0014] Memory stores computer-executable instructions;

[0015] The processor executes the computer-executable instructions stored in the memory, so that at least one processor executes the data processing method of the first aspect and various possible designs of the first aspect as described above.

[0016] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the data processing method as described in the first aspect and various possible designs of the first aspect are implemented.

[0017] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the data processing method as described in the first aspect and various possible designs of the first aspect.

[0018] The data processing method, apparatus, device, storage medium and product provided in this embodiment include: determining multiple target influencing factors of the target product for the target product, where the target influencing factors are actions and / or product status that affect the order volume of the target product; determining a target task for the target product based on the multiple target influencing factors, where the target task includes: at least one subtask and the execution order of at least one subtask, and the target task is indicated by the target influencing factor; recommending the target task to prompt the execution of at least one subtask in the execution order. The present disclosure can provide accurate target tasks to stores for target products to prompt the stores to execute the target tasks and thus achieve efficient recommendation of product information of the target products. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0020] Figure 1 An example diagram of an application scenario of a data processing method provided by an embodiment of the present disclosure;

[0021] Figure 2 A flow chart of a data processing method provided by an embodiment of the present disclosure;

[0022] Figure 3 A flow chart of a prediction model training method provided by an embodiment of the present disclosure;

[0023] Figure 4 A schematic diagram of a sample construction provided by an embodiment of the present disclosure;

[0024] Figure 5 A schematic diagram of the structure of a data processing device provided in an embodiment of the present disclosure;

[0025] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0027] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the target users in an appropriate manner in accordance with relevant laws and regulations, and the target users' authorization should be obtained.

[0028] It is understandable that the above notification and the process of obtaining authorization of the target user are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0029] It should be noted that the data processing method, device, equipment, storage medium and product provided by the present disclosure can be applied to the recommendation of any product.

[0030] In the related art, one method is to recommend product information based on the user's historical behavior data. Another method is to use a deep learning model to capture the connection between users and products. The deep learning model can process a large number of data features. Another method is to analyze the characteristics of the product, such as the product's description, label, category, etc., and then match these characteristics with the user's interests and preferences. This method is more suitable for recommending new products or long-tail products because it does not rely on the user's historical behavior data. The above methods all have the problem of not being able to efficiently recommend product information.

[0031] In order to solve the technical problem, the present disclosure provides a data processing method, apparatus, device, computer-readable storage medium and product, which determines the target influencing factor that affects the order volume of the target product, determines the target task for the target product according to the target influencing factor, and then provides the store with accurate target task to prompt the store to perform the target task and thereby realize efficient recommendation of product information of the target product.

[0032] The data processing method provided by the embodiment of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0033] Figure 1 This is an example diagram of an application scenario of a data processing method provided by an embodiment of the present disclosure. Figure 1 The figure shows a store page, which is displayed to store users. Store users can upload product cards on the store page. The product card includes: the main product image and product text information. Then the store operator obtains the product features of the corresponding product based on the product card, and then recommends the target task to the store. The store operator can perform multiple subtasks in sequence to increase the order volume of the product.

[0034] Figure 2 A flowchart of a data processing method provided in an embodiment of the present disclosure, the data processing method may include the following steps:

[0035] S201. For a target product, determine multiple target influencing factors of the target product.

[0036] Among them, the target influencing factors are actions and / or product states that affect the order volume of the target product. In the embodiment of the present disclosure, actions refer to some dynamic behaviors of merchants towards the target product, and product states are a continuous online state of the product. For example, the target influencing factors include: binding a short video and maintaining a 7-day no-reason return, where binding a short video is an action and maintaining a 7-day no-reason return is a product state.

[0037] In an embodiment of the present disclosure, determining multiple target impact factors of a target product includes: obtaining target product features of the target product; inputting the target product features into a pre-trained prediction model for processing to obtain multiple target impact factors.

[0038] The target product features include the current price feature of the target product, the store selling ability feature, the user rights feature, the store feature to which the target product belongs, the review feature of the target product, and at least one of other features. Specifically, the price feature includes: whether it is the lowest price or the price stability of the target product. The user rights feature includes: at least one of: extremely fast refund, delivery speed, after-sales guarantee, and genuine product guarantee.

[0039] Furthermore, the prediction model is a pre-trained causal inference model, and the target product features are input into the pre-trained prediction model for processing to obtain multiple target influencing factors.

[0040] It can be understood that on the store operator side, if the operator needs to increase the order volume of the target product, the target product can be selected into the pool. The products in the pool indicate that they need to be processed by the present disclosure to recommend the target task.

[0041] S202: Determine a target task for a target product based on multiple target influencing factors.

[0042] The target task includes: at least one subtask and at least one execution order of the subtask, and the target task is indicated by the target impact factor.

[0043] It can be understood that the target task is based on multiple target impact factors, wherein a subtask can be generated based on at least the target impact factor.

[0044] In the disclosed embodiment, the correspondence between the target impact factor and the subtask can be preset. For example: the target impact factor includes: binding a short video and maintaining a 7-day no-reason return policy, then the target task can include: 2 subtasks, subtask 1 is: binding a short video to the target product, and subtask 2 is: setting the target product to maintain a 7-day no-reason return policy. Among them, the execution order of subtask 1 can also be set to 1, and the execution order of subtask 2 can be set to 2. Or the execution order of subtask 2 can be set to 1, and the execution order of subtask 1 can be set to 2.

[0045] In the present disclosure, at least one target influencing factor can be selected from multiple target influencing factors to generate a target task. In addition, multiple target tasks can be generated based on multiple target influencing factors, and each target task has a corresponding predicted order quantity. Among them, the predicted order quantity of the configured target task can be the same as the predicted order quantity output by the prediction model, or the predicted order quantity of the configured target task is less than the predicted order quantity output by the prediction model. It can be understood that if the target task is determined based on all the target influencing factors among multiple target influencing factors, the predicted order quantity of the target task is the same as the predicted order quantity output by the prediction model. If the target task is determined based on some of the target influencing factors among multiple target influencing factors, the predicted order quantity of the target task is less than the predicted order quantity output by the prediction model.

[0046] Specifically, product features are input into a pre-trained prediction model for processing, and a predicted order volume is obtained. The target task of the target product is determined based on multiple target influencing factors, including: determining the target task of the target product based on multiple target influencing factors and the predicted order volume, and the target task also indicates the predicted order volume corresponding to executing the target task.

[0047] For example, the predicted order volume is 20. The predicted order volume can be understood as the predicted daily order volume, weekly order volume, or monthly order volume of the target product.

[0048] S203: recommending a target task to prompt execution of at least one subtask in an execution order.

[0049] In one embodiment, the recommended target task includes: multiple subtasks and the execution order of the subtasks, so that the store operation staff can execute these subtasks in the execution order. For example, the multiple subtasks and the execution order are: (1) Subtask 1: suggest changing the price; (2) Subtask 2: suggest joining some activities; (3) Subtask 3: suggest cooperating with product recommendation staff; (4) Subtask 4: suggest placing advertisements.

[0050] In another embodiment, the recommended target task includes: multiple subtasks, the execution order of the subtasks, and the predicted order volume, so that the store operation personnel can execute these subtasks in the execution order, and the store operation personnel can clearly know the order volume that can be achieved by executing the subtasks. For example: one of the target tasks 1 is to sequentially execute the configuration of store coupons and the number of store positive reviews (the predicted order volume is 0-10 orders); target task 2 is to sequentially execute maintaining the lowest price outside the site, placing product card advertisements, and adjusting the high quality of product titles (the predicted order volume is 10-100 orders); target task 3 is to sequentially execute accumulating product reviews, adding selected scenes, and adding short video bindings (the predicted order volume is 100-500 orders). Target task 4 is to sequentially increase seasonal products, maintain the quality of product detail pages, and participate in flash sales (the predicted order volume is 500-1000 orders).

[0051] In summary, in the embodiments of the present disclosure, the target influencing factors that affect the order volume of the target product can be accurately determined through the prediction model, and then the target influencing factors can be applied to the determination of the target task to recommend the target task to the store operators, so that the store operators can increase the order volume of the target product after executing the target task.

[0052] Figure 3 A flowchart of a prediction model training method provided in an embodiment of the present disclosure, the prediction model training method includes the following steps:

[0053] S301, obtaining multiple samples.

[0054] The samples include: sample product characteristics, sample influencing factors and sample order volumes of sample products.

[0055] In the disclosed embodiment, the sample product characteristics include: price characteristics of the sample product, activity participation level characteristics, store characteristics of the sample product, recent exposure trend characteristics, recent sales trend characteristics, comment characteristics, user rights characteristics and at least one of other characteristics.

[0056] Specifically, the price characteristics include: whether it is the lowest price and price stability. If the price of a product is the lowest price in this store, then the product is "lowest price", otherwise the product is "non-lowest price". If the price of a product does not change within a preset period of time (such as 3 months), then it can be determined that the price stability of the product is high, otherwise, it can be determined that the price stability of the product is low.

[0057] The activity participation level characteristics include: the number of store activity registrations. For example, the number of store activity registrations is 0, 1, or more.

[0058] The store characteristics include: at least one of the main shelf characteristics, store product conditions, store ratings, store membership numbers, and store business activity. Among them, the store product conditions include: the number of online products in the store, the order volume, and the order volume ranking of the same product in the same store.

[0059] Other features include: whether it is a new product, the quality of product text information, the number of product recommenders, whether it is a pre-sale, and whether it is a seasonal product. For example, if a product has just been launched, it is a new product. The quality of product text information refers to whether the main image of the product is clear and whether the text introducing the product is standardized. If the product is mainly used in a certain season, it is a seasonal product, for example, down jackets are mainly used in winter, and sun protection clothes are mainly used in summer.

[0060] In the embodiment of the present disclosure, the sample impact factor is an impact factor of the sample product, which may be the actions performed by the store on the sample product within a preset time period (such as within 2 weeks) and the product status maintained by the sample product.

[0061] For example, actions include: binding a video or live broadcast room, changing prices, participating in activities, improving the quality of product promotion content, enabling after-sales protection, investing in advertising, etc.

[0062] In the embodiments of the present disclosure, the action may also include other contents, and the product status may also include other contents, which are not limited here.

[0063] In the embodiment of the present disclosure, the sample order quantity may be the order quantity of the sample product within a preset time period.

[0064] The multiple samples include multiple positive samples and multiple negative samples, the sample order volume of the positive samples is greater than or equal to a first threshold, the sample order volume of the negative samples is less than a second threshold, and the first threshold is greater than the second threshold.

[0065] In the embodiment of the present disclosure, for example, the first threshold is 100 and the second threshold is 50. Then, products with an order volume greater than 100 within 2 weeks can be selected as positive sample products, and products with an order volume less than 50 can be selected as negative sample products.

[0066] For example, the sample product features of one negative sample are: high price stability, quick refund for undelivered products, after-sales guarantee, large number of valid product reviews, and high quality of product text information. The sample order volume is 10. The sample influencing factors include: opening after-sales guarantee and improving the quality of product promotion content.

[0067] The sample product features of one of the positive samples are: high price stability, high store order volume, high store rating, many store members, and after-sales guarantee. The sample order volume is 100. The sample influencing factors include: binding video or live broadcast room, price change, and participation in activities.

[0068] Furthermore, the sample is constructed by: obtaining sample product characteristics of the sample product in the first period; determining the sample impact factor of the sample product in the second period; obtaining the order volume generated by the sample product using the sample impact factor, the second period is after the first period; constructing the sample according to the sample characteristics, sample impact factor and order volume. Both positive samples and negative samples can be constructed in this way.

[0069] In the embodiments of the present disclosure, refer to Figure 4 , obtain sample product features in the first period, obtain sample impact factors in the second period, and obtain order volume in the third period. The third period can be the order volume generated based on the sample impact factors. For example, if an action is performed on the sample product at time T, and no other actions are performed after time T, then the third period is calculated from time T.

[0070] In one embodiment, for each sample, determining the sample impact factor of the sample product in the second time period includes: obtaining multiple first impact factors of the sample product in the second time period; determining the coverage rate of each first impact factor in multiple positive samples or multiple negative samples; and determining, among the multiple first impact factors, the first impact factor with a third threshold before the coverage rate is sorted from high to low as the sample impact factor. In this embodiment, the first impact factor is an impact factor of an action or an impact factor of a product state.

[0071] In another embodiment, for each sample, a sample influence factor of the sample product in the second time period is determined, including: obtaining multiple first influence factors of the sample product in the second time period; determining the coverage rate of each first influence factor in multiple positive samples or multiple negative samples; classifying the multiple first influence factors to obtain first influence factors belonging to actions and first influence factors belonging to product status; for the first influence factors belonging to actions, determining the first influence factor of the fourth threshold before the coverage rate is sorted from high to low as the sample influence factor; for the first influence factors belonging to product status, determining the first influence factor of the fifth threshold before the coverage rate is sorted from high to low as the sample influence factor.

[0072] It can be understood that if the sample is a positive sample, the coverage rate of the first influencing factor in multiple positive samples is determined, and if the sample is a negative sample, the coverage rate of the first influencing factor in multiple negative samples is determined.

[0073] In addition, the third threshold is preset, such as 3. In the embodiment of the present disclosure, the coverage ranking may be performed by action and product status respectively.

[0074] In the embodiment of the present disclosure, the multiple first influencing factors can be understood as all the influencing factors used by the sample product in the second period. The coverage rate refers to the ratio of the number of positive samples including the first influencing factor to the number of multiple positive samples, or the coverage rate refers to the ratio of the number of negative samples including the first influencing factor to the number of multiple negative samples.

[0075] In the embodiments of the present disclosure, the PSM technology in the statistical model is used to count the influencing factors of the action, and the coverage and coverage ranking of the influencing factors (actions) are obtained. The DML technology in the statistical model is used to count the influencing factors of the product status, and the coverage and coverage ranking of the influencing factors (status) are obtained. Among them, PSM (Propensity Score Matching) is a statistical technique that reduces selection bias when estimating causal effects by matching individuals in the treatment group and the control group with similar propensity scores. DML (Double Machine Learning) is a machine learning method that combines traditional regression analysis and machine learning techniques and can be used to process high-dimensional, nonlinear and non-parametric data. In the embodiments of the present disclosure, the coverage of specific statistical influencing factors is not limited.

[0076] In the embodiment of the present application, it can be understood that the higher the coverage rate, the higher the significance of the influencing factor, and the greater the positive impact on the order volume of the product. Among them, if only the first influencing factor of the action is selected as the target influencing factor, and the third threshold is 3, the first influencing factor of the top three (including the third) of the "action" ranking is selected as the sample influencing factor. If only the first influencing factor of the product status is selected as the target influencing factor, and the third threshold is 3, the first influencing factor of the top three (including the third) of the "product status" ranking is selected as the sample influencing factor. If the first influencing factor of the action is selected, the first influencing factor of the product status is also selected as the sample influencing factor, wherein, if the fourth threshold is 3 and the fifth threshold is 4, the first influencing factor of the top three (including the third) of the "action" ranking and the first influencing factor of the top four (including the fourth) of the "product status" ranking are selected as sample influencing factors.

[0077] S302, taking sample product features as inputs of the prediction model, sample influencing factors and sample order quantities as labels of the prediction model, training the prediction model to obtain a trained prediction model.

[0078] The specific training process is as follows: inputting sample product features into the prediction model for processing, outputting multiple prediction influencing factors and the predicted order quantity of each prediction influencing shadow, comparing the loss values ​​of multiple prediction influencing factors and sample influencing factors, and comparing the loss values ​​of sample order quantity and predicted order quantity, using the loss values ​​to adjust the model parameters of the prediction model, using multiple samples to train the prediction model, and obtaining a trained prediction model when the prediction model meets the preset convergence conditions.

[0079] The present disclosure also includes: testing the trained prediction model. For example, for the target product in the above embodiment, after executing the target task, if the difference between the actual order quantity and the predicted order quantity of the target product is greater than a threshold, the model parameters of the prediction model are adjusted using the target product characteristics, target influencing factors and actual order quantity.

[0080] The present disclosure constructs positive samples and negative samples to train the prediction model, and then tests the trained prediction model. After the prediction model meets the convergence condition, a trained prediction model is obtained. Further, the trained prediction model is applied to the prediction of the target impact factor and the predicted order volume of the target product of the actual store.

[0081] Previously, store operators mainly increased product order volume by participating in channel registration and platform promotions. These methods have high requirements for the products themselves, resulting in a limited range of products that can participate. The present disclosure is applicable to various products. In addition, in the application of the embodiments of the present disclosure, in some recommendation scenarios, store operators can obtain transparent suggestions for increasing product order volume. This "white box" suggestion mechanism breaks the limitations of the target participation in channel registration and platform promotions, allowing the store's products to have more opportunities to receive support and incentives, thereby expanding the scale of participation of the store's products.

[0082] Furthermore, the disclosure recommends the target task and the predicted order volume to the store, which can be displayed on the store page, enhancing the transparency of the data. This transparent display not only allows store operators to more clearly understand the order volume that can be achieved by executing the target task, but also greatly improves the store's willingness and enthusiasm to execute the target task.

[0083] In summary, by deeply analyzing the influencing factors that can increase the order volume of products, the present disclosure can help store operators better understand which influencing factors are most likely to increase the order volume of products.

[0084] Figure 5 The following is a schematic diagram of the structure of a data processing device provided in an embodiment of the present disclosure. The data processing device 50 may include the following units:

[0085] A first determining unit 51 is used to determine, for a target product, a plurality of target influencing factors of the target product, where the target influencing factors are actions and / or product states that affect the order quantity of the target product;

[0086] A second determining unit 52 is used to determine a target task for a target product according to a plurality of target impact factors, wherein the target task includes at least one subtask and an execution order of at least one subtask, and the target task is indicated by the target impact factor;

[0087] The recommendation unit 53 is used to recommend the target task to prompt the user to execute at least one subtask in an execution order.

[0088] In some embodiments, the first determination unit 51 is specifically used to obtain target product features of the target product; input the target product features into a pre-trained prediction model for processing to obtain multiple target impact factors.

[0089] In some embodiments, when product features are input into a pre-trained prediction model for processing, a predicted order quantity is also obtained. The second determination unit 52 is specifically used to: determine the target task of the target product based on multiple target influencing factors and the predicted order quantity. The target task also indicates the predicted order quantity corresponding to the execution of the target task.

[0090] In some embodiments, a training unit (not shown) is also included, which is used to train the prediction model in the following manner to obtain multiple samples, where the samples include: sample product characteristics, sample influence factors and sample order quantities of sample products; using the sample product characteristics as the input of the prediction model, the sample influence factors and the sample order quantity as the labels of the prediction model, training the prediction model, and obtaining a trained prediction model.

[0091] In some embodiments, the multiple samples include multiple positive samples and multiple negative samples, the sample order volume of the positive samples is greater than or equal to a first threshold, the sample order volume of the negative samples is less than a second threshold, and the first threshold is greater than the second threshold.

[0092] In some embodiments, it also includes: a sample construction unit (not shown), which is used to obtain sample product characteristics of the sample product in a first time period; determine the sample influence factor of the sample product in a second time period; obtain the order volume generated by the sample product using the sample influence factor, the second time period is after the first time period; and construct a sample based on the sample product characteristics, sample influence factor and order volume.

[0093] In some embodiments, when the sample construction unit determines the sample impact factor of the sample product in the second time period for each sample, it is specifically used to: obtain multiple first impact factors of the sample product in the second time period; determine the coverage rate of each first impact factor in multiple positive samples or multiple negative samples; among the multiple first impact factors, determine the first impact factor with the coverage rate sorted from high to low before the third threshold as the sample impact factor.

[0094] In some embodiments, when the sample construction unit determines the sample influence factor of the sample product in the second time period for each sample, it is specifically used to: obtain multiple first influence factors of the sample product in the second time period; determine the coverage of each first influence factor in multiple positive samples or multiple negative samples; classify the multiple first influence factors to obtain the first influence factors belonging to the action and the first influence factors belonging to the product status; for the first influence factors belonging to the action, determine the first influence factor of the fourth threshold before the coverage is sorted from high to low as the sample influence factor; for the first influence factors belonging to the product status, determine the first influence factor of the fifth threshold before the coverage is sorted from high to low as the sample influence factor.

[0095] The device or apparatus provided in this embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be repeated here.

[0096] In order to implement the above embodiments, the embodiments of the present disclosure further provide a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, a data processing method as described in any of the above embodiments is implemented.

[0097] In order to implement the above embodiments, the embodiments of the present disclosure further provide a computer program product, including a computer program, which implements the data processing method of any of the above embodiments when executed by a processor.

[0098] In order to implement the above embodiment, the present disclosure also provides an electronic device, including: a processor and a memory;

[0099] Memory stores computer-executable instructions;

[0100] The processor executes the computer execution instructions stored in the memory, so that the processor executes the data processing method as described in any of the above embodiments.

[0101] Figure 6 The electronic device 60 is a schematic diagram of the structure of the electronic device provided in the embodiment of the present disclosure, and the electronic device 60 may be a terminal device or a server. The terminal device may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (Portable Android Devices, PADs), portable multimedia players (Portable Media Players, PMPs), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0102] like Figure 6 As shown, the electronic device 60 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 61, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 62 or a program loaded from a storage device 68 to a random access memory (RAM) 63. Various programs and data required for the operation of the electronic device 60 are also stored in the RAM 63. The processing device 61, the ROM 62, and the RAM 63 are connected to each other via a bus 64. An input / output (I / O) interface 65 is also connected to the bus 64.

[0103] Typically, the following devices may be connected to the I / O interface 65: input devices 66 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 67 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 68 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 69. The communication device 69 may allow the electronic device 60 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 6 The electronic device 60 is shown with various devices, but it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have instead.

[0104] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 69, or installed from the storage device 68, or installed from the ROM 62. When the computer program is executed by the processing device 61, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0105] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0106] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0107] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0108] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the target user computer, partially on the target user computer, as a separate software package, partially on the target user computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the target user computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0109] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0110] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a unit does not limit the unit itself in some cases. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses".

[0111] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0112] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0113] In a first aspect, according to one or more embodiments of the present disclosure, there is provided a data processing method, comprising: determining, for a target product, multiple target influencing factors of the target product, the target influencing factors being actions and / or product statuses that affect the order quantity of the target product; determining, based on the multiple target influencing factors, a target task for the target product, the target task comprising: at least one subtask and an execution order of at least one subtask, the target task being indicated by the target influencing factor; and recommending the target task to prompt execution of at least one subtask in the execution order.

[0114] According to one or more embodiments of the present disclosure, determining multiple target impact factors of a target product includes: obtaining target product features of the target product; inputting the target product features into a pre-trained prediction model for processing to obtain multiple target impact factors.

[0115] According to one or more embodiments of the present disclosure, product features are input into a pre-trained prediction model for processing, and a predicted order volume is obtained. The target task of the target product is determined based on multiple target influencing factors, including: determining the target task of the target product based on multiple target influencing factors and the predicted order volume, and the target task also indicates the predicted order volume corresponding to executing the target task.

[0116] According to one or more embodiments of the present disclosure, the prediction model is trained in the following manner: obtaining multiple samples, the samples including: sample product features, sample influencing factors and sample order quantities of sample products; using the sample product features as inputs to the prediction model, the sample influencing factors and the sample order quantities as labels of the prediction model, training the prediction model, and obtaining a trained prediction model.

[0117] According to one or more embodiments of the present disclosure, the multiple samples include multiple positive samples and multiple negative samples, the sample order volume of the positive samples is greater than or equal to a first threshold, the sample order volume of the negative samples is less than a second threshold, and the first threshold is greater than the second threshold.

[0118] According to one or more embodiments of the present disclosure, it also includes: the sample is constructed in the following manner: obtaining sample product characteristics of the sample product in a first time period; determining the sample influence factor of the sample product in a second time period; obtaining the order volume generated by the sample product using the sample influence factor, the second time period is after the first time period; constructing the sample according to the sample product characteristics, the sample influence factor and the order volume.

[0119] According to one or more embodiments of the present disclosure, for each sample, a sample influence factor of the sample product in the second time period is determined, including: obtaining multiple first influence factors of the sample product in the second time period; determining the coverage rate of each first influence factor in multiple positive samples or multiple negative samples; among the multiple first influence factors, determining the first influence factor before the third threshold value in the order of coverage from high to bottom as the sample influence factor.

[0120] According to one or more embodiments of the present disclosure, for each sample, a sample influence factor of the sample product in the second time period is determined, including: obtaining multiple first influence factors of the sample product in the second time period; determining the coverage of each first influence factor in multiple positive samples or multiple negative samples; classifying the multiple first influence factors to obtain first influence factors belonging to actions and first influence factors belonging to product status; for the first influence factors belonging to actions, determining the first influence factor of the fourth threshold before the coverage is sorted from high to low as the sample influence factor; for the first influence factors belonging to product status, determining the first influence factor of the fifth threshold before the coverage is sorted from high to low as the sample influence factor.

[0121] In a second aspect, according to one or more embodiments of the present disclosure, there is provided a data processing device, comprising:

[0122] A first determination unit is used to determine, for a target product, a plurality of target influencing factors of the target product, where the target influencing factors are actions and / or product states that affect the order quantity of the target product;

[0123] A second determining unit is used to determine a target task for a target product according to a plurality of target impact factors, wherein the target task includes at least one subtask and an execution order of at least one subtask, and the target task is indicated by the target impact factor;

[0124] The recommendation unit is used to recommend a target task to prompt the user to execute at least one subtask in an execution order.

[0125] In a third aspect, according to one or more embodiments of the present disclosure, there is provided an electronic device, comprising: at least one processor and a memory;

[0126] Memory stores computer-executable instructions;

[0127] At least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the data processing method of the first aspect and various possible designs of the first aspect as described above.

[0128] In a fourth aspect, according to one or more embodiments of the present disclosure, a computer-readable storage medium is provided, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the data processing method as described in the first aspect and various possible designs of the first aspect are implemented.

[0129] In a fifth aspect, according to one or more embodiments of the present disclosure, a computer program product is provided, including a computer program, which, when executed by a processor, implements the data processing method of the first aspect and various possible designs of the first aspect.

[0130] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0131] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0132] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A data processing method, characterized in that: include: For a target product, determining a plurality of target influencing factors of the target product, wherein the target influencing factors are actions and / or product states that affect the order quantity of the target product; Determining a target task for the target product according to the multiple target impact factors, the target task comprising: at least one subtask and an execution order of the at least one subtask, the target task being indicated by the target impact factor; The target task is recommended to prompt execution of the at least one subtask in the execution order.

2. The data processing method according to claim 1, characterized in that: The determining of a plurality of target impact factors of the target product comprises: Acquire target product features of the target product; The target product features are input into a pre-trained prediction model for processing to obtain the multiple target influencing factors.

3. The data processing method according to claim 2, characterized in that: The step of inputting the product features into a pre-trained prediction model for processing and obtaining a predicted order quantity, and determining the target task of the target product based on the multiple target influencing factors, includes: determining the target task of the target product based on the multiple target influencing factors and the predicted order quantity, and the target task also indicates the predicted order quantity corresponding to executing the target task.

4. The data processing method according to claim 3, characterized in that: The prediction model is trained in the following way: Acquire multiple samples, the samples including: sample product characteristics, sample influencing factors, and sample order quantities of sample products; The prediction model is trained using the sample product features as inputs of the prediction model, the sample influencing factors and the sample order quantities as labels of the prediction model, and a trained prediction model is obtained.

5. The data processing method according to claim 4, characterized in that: The multiple samples include multiple positive samples and multiple negative samples, the sample order volume of the positive samples is greater than or equal to a first threshold, the sample order volume of the negative samples is less than a second threshold, and the first threshold is greater than the second threshold.

6. The data processing method according to claim 5, characterized in that: The sample is constructed in the following way: Obtaining sample product characteristics of the sample product in the first period; Determine the sample impact factor of the sample product in the second period; Obtaining the order volume of the sample product generated by adopting the sample influencing factor, wherein the second period is after the first period; The sample is constructed according to the sample characteristics, the sample influencing factors and the order volume.

7. The data processing method according to claim 6, characterized in that: For each sample, determining the sample impact factor of the sample product in the second time period includes: Obtaining a plurality of first impact factors of the sample product in the second time period; Determine the coverage rate of each first impact factor in the multiple positive samples or the multiple negative samples; Among the multiple first impact factors, determine the first impact factor of the third threshold before sorting the coverage from high to low as the sample impact factor.

8. The data processing method according to claim 6, characterized in that: For each sample, determining the sample impact factor of the sample product in the second time period includes: Obtaining a plurality of first impact factors of the sample product in the second time period; Determine the coverage rate of each first impact factor in the multiple positive samples or the multiple negative samples; Classifying the multiple first influencing factors to obtain a first influencing factor belonging to an action and a first influencing factor belonging to a product state; For the first influencing factor belonging to the action, determine the first influencing factor of the fourth threshold before the coverage is sorted from high to low as the sample influencing factor; For the first influencing factor belonging to the product status, determine the first influencing factor before the fifth threshold in the order of coverage from high to low as the sample influencing factor.

9. A data processing device, characterized in that: include: A first determining unit is used to determine, for a target product, a plurality of target influencing factors of the target product, wherein the target influencing factors are actions and / or product states that affect the order quantity of the target product; A second determining unit is configured to determine a target task for the target product according to the multiple target impact factors, the target task comprising: at least one subtask and an execution order of the at least one subtask, the target task being indicated by the target impact factor; The recommendation unit is used to recommend the target task to prompt the at least one subtask to be executed in the execution order.

10. An electronic device, characterized in that: include: Processor and memory; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the data processing method according to any one of claims 1 to 9.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the processor executes the computer-executable instructions, the data processing method according to any one of claims 1 to 9 is implemented.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the data processing method according to any one of claims 1 to 9 is implemented.

Images