Information processing method, electronic device, and computer program

Abstract

To provide an information processing method which promotes targeted product adjustment, and can improve whole efficiency or benefit.SOLUTION: In an information processing method, an electronic device acquires product information on a plurality of products (210), applies the product information to a data processing model and thereby determines a causal relation concerning an output amount (220), and determines at least one target product affecting the total output amount of the plurality of products among the plurality of products on the basis of the determined causal relation (230).SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] TECHNICAL FIELD Embodiments of the present disclosure relate to the field of data processing, and more particularly, to methods, electronic devices and computer-readable storage media for processing information. [Background technology]

[0002] With the rapid development of information technology, the scale of data is also growing rapidly. Under such a background and trend, more and more attention is being paid to how to use technologies such as machine learning to process information more effectively. For example, an entity that needs to process (e.g., design, produce, or sell) multiple types of products may wish to make trade-offs among multiple types of products and maximize efficiency or profits by making better use of various information about the products. Summary of the Invention [Problem to be solved by the invention]

[0003] In an embodiment of the present disclosure, an information processing solution is provided. [Means for solving the problem]

[0004] In a first aspect of the present disclosure, an information processing method is provided. The method includes obtaining product information for a plurality of products, the product information including at least an output amount and a target attribute of each product in the plurality of products in a certain period of time. The output amount indicates the number of the corresponding product outputted to the outside in a certain period of time. The method further includes applying the product information to a data processing model to determine a causal relationship associated with the output amount. The causal relationship indicates at least a dependency of the output amount of each product in the plurality of products on a target attribute of each of the plurality of products. The method further includes determining at least one target product from the plurality of products that affects the total output amount of the plurality of products based on the causal relationship.

[0005] In a second aspect of the present disclosure, an electronic device is provided. The electronic device includes a processor and a memory coupled to the processor and having instructions stored thereon, the electronic device performing operations when the instructions are executed by the processor. The operations include obtaining product information for the plurality of products, the product information including at least an output amount and a target attribute of each product in the plurality of products in a certain period of time. The output amount indicates a number of the corresponding product outputted to the outside in a certain period of time. The operations further include applying the product information to a data processing model to determine a causal relationship associated with the output amount. The causal relationship indicates at least a dependency of the output amount of each product in the plurality of products on the target attribute of each of the plurality of products. The operations further include determining at least one target product from the plurality of products that affects a total output amount of the plurality of products based on the causal relationship.

[0006] In a third aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of the first aspect of the present disclosure.

[0007] The Summary of the Invention is intended to present a selection of concepts in a simplified manner, which are further described in the following embodiments. The description in the Summary of the Invention is not intended to identify key or key features of the disclosure, nor is it intended to limit the scope of the disclosure. [Brief description of the drawings]

[0008] The above and other objects, features and advantages of the present disclosure will become more apparent from the following detailed description of exemplary embodiments of the present disclosure in conjunction with the drawings. In the exemplary embodiments of the present disclosure, the same reference numerals essentially indicate the same elements.

[0009] [Figure 1] FIG. 1 is a schematic diagram of an exemplary environment in which several embodiments of the present disclosure can be implemented. [Diagram 2]1 is a flowchart of a product analysis process according to some embodiments of the present disclosure. [Diagram 3] FIG. 1 is a simplified block diagram of product analysis and adjustment according to some embodiments of the present disclosure. [Figure 4] 1 is a table illustrating examples of causal relationships according to some embodiments of the present disclosure. [Diagram 5] 1 is a flowchart of a product reconciliation process according to some embodiments of the present disclosure. [Figure 6A] 1 is a flowchart of a process for determining adjustment information according to some embodiments of the present disclosure. [Figure 6B] 11 is a flowchart of another process for determining adjustment information according to some embodiments of the present disclosure. [Figure 7] FIG. 1 is a block diagram of an example device in which embodiments of the present disclosure may be implemented. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] The principles of the present disclosure will now be described with reference to some exemplary embodiments shown in the drawings. Although the drawings depict preferred embodiments of the present disclosure, it should be understood that these embodiments are merely intended to enable those skilled in the art to better understand and realize the present disclosure, and are not intended to limit the scope of the present disclosure in any manner.

[0011] As used herein, the term "comprises" and variations thereof refer to the open "including, but not limited to." Unless otherwise specified, the term "or" refers to "and / or" and the term "based on" refers to "based at least in part on." The terms "one exemplary embodiment" and "one embodiment" refer to "at least one exemplary embodiment." The term "another embodiment" refers to "at least one other embodiment." The terms "first," "second," etc. can refer to different or the same object. Other explicit and implicit definitions may be included in the following text.

[0012] The term "causation" as used herein can refer to a relationship between one or more factors (causes) and an event or result (effect). Any factor that influences an event or result is a cause of that event or result.

[0013] As used herein, the term "attribute" of a product may refer to a property that is specific to a product or that a product has in a given context, such as, but not limited to, size, color, price, material, etc. The term "target attribute" refers to one or more attributes that are considered or of interest in learning or determining causal relationships.

[0014] The term "output amount" used in the text may be the number of products output to the outside within a certain period of time. For example, the "output amount" may represent the sales amount of products, the amount of customized orders, the production amount, etc. according to different application scenarios. The term "total output amount" may refer to a type of amount, and the amount is used to indicate a situation in which multiple types or multiple products are output to the outside within a certain period of time. For example, the "total output amount" may represent the total sales amount, total sales revenue (or total sales profit), total customized order amount, total customized order amount, total production amount, etc. of multiple types or multiple products within a certain period of time according to different application scenarios.

[0015] The term "handle" as used herein may refer to one or more of designing, producing, selling, etc. of a product. A product handling entity may be an entity that performs corresponding processing on a product, such as a selling entity, a designing entity, etc. Similarly, an entity that places a customization order for a product with a designing entity may be referred to as a customization ordering entity, and an entity that purchases a product from a selling entity may be referred to as a purchasing entity.

[0016] As mentioned above, an entity that processes (e.g., designs, produces, or sells) multiple types of products simultaneously may wish to make trade-offs among multiple types of products and maximize efficiency or profits by better utilizing various information about the products. By way of example only, an entity that sells multiple types of products simultaneously (e.g., a retail market) may wish to develop a product pricing strategy or product selection strategy, etc., based on the sales status of the products. An entity that designs multiple types of products simultaneously may wish to develop a strategy for product modification (e.g., size, color change) based on the status of product customization orders or ordering.

[0017] To meet these demands, the general solutions usually use simulation modeling methods to obtain a forecast model for the output amount or total output amount, and then determine the attributes of multiple products based on the forecast model. However, these general solutions are based only on mathematical models and do not consider the inherent relationship or influence between the multiple products and their attributes.

[0018] The inventors of the present application have found that in activities such as product design, production, and sales, some attributes of a product, such as size, color, price, etc., generally affect the popularity of the product or the degree of demand for the product by users, and thus affect the output volume of the product. In addition, there are also situations in which different products, particularly different products of the same type, affect each other. For example, for two types of products of the same type, the size, price, etc. of one type of product affect the popularity of the other product.

[0019] Therefore, the inventor of the present application has found that in order to increase the total output of multiple types or multiple products, it is necessary to consider which factors affect the output of the products and the influence manner of these factors. Based on the determined influence factors and influence manner, a core product in the multiple products can be further determined. Then, a corresponding strategy can be specified to increase the total output. For example, the inventor of the present application has found that in order to increase the overall sales, the product sales entity needs to understand what are the important factors that affect the sales volume of the products and how they affect it, so as to determine the core value product, and then formulate a corresponding strategy to increase the overall sales.

[0020] According to an embodiment of the present disclosure, a solution for product analysis and product adjustment is provided. In the solution, the causal relationship on the output volume of the product can be determined by processing product information including data from various sources and utilizing an automated causal relationship learning technique. The causal relationship represents which factors affect the output volume of the product. Then, a core product or an important product in the multiple products can be determined based on the causal relationship. For example, the core product or the important product can be a product that has a relatively large impact on the total output volume of the multiple products. Furthermore, the causal relationship can be utilized to determine or provide an adjustment mode or strategy for the core product or the important product to enhance and thus maximize the overall efficiency or profit of processing the multiple products. According to an embodiment of the present disclosure, the core product or the important product can be determined to adjust the product in a more targeted manner to effectively enhance the processing efficiency or profit of the product.

[0021] Hereinafter, the embodiments of the present disclosure will be described in detail with reference to the drawings. Fig. 1 shows a schematic diagram of an example environment 100 in which multiple embodiments of the present disclosure can be implemented. In the example environment 100, a computing device 102 processes product information 110 related to multiple products to determine causal relationships 103 related to output quantities of the products and target product information 104 related to at least one target product.

[0022] The product information includes at least the output amount and the target attribute of each product in a certain period of time for a plurality of products. In FIG. 1, the column 111 of the exemplary product information 110 represents different products, the column 112 represents the output amount, and the column 113 represents the target attribute. In the exemplary product information, the output amount (specifically, the value of the output amount) and the target attribute (specifically, the value of the target attribute) of the products A to E are shown. The certain period of time can be any length of time that is considered or statistics are performed, such as one day, one week, one month, one quarter, one year, etc. Although the product information 110 is shown in a table format, this is merely an example and is not intended to be limiting.

[0023] Also, in the example of FIG. 1, each product corresponds to only one output amount, but in some embodiments, the output amount can be further subdivided. For example, when the same product is associated with multiple product processing entities, the output amount of one product (e.g., product A) can be subdivided into output amounts corresponding to the multiple product processing entities, respectively. For example, when product A is sold by multiple sales entities, output amount 1 can be subdivided to include the sales amount sold by each of the multiple sales entities. Also, for example, when product A is customized and ordered by multiple entities, output amount 1 can be subdivided to include the amount customized and ordered by each of the multiple entities.

[0024] As an example, the output amount may be the sales amount of products A to E in a certain period of time, the target attribute may be the price of products A to E in the certain period of time, and the corresponding total output amount (not shown) may be the total sales amount of products A to E in the certain period of time. This example may also be referred to as a product sales example in the following text. As another example, the output amount may be the customization order amount or order amount of products A to E in a certain period of time, the target attribute may be the size of products A to E (e.g., the width, height, etc. of beds), and the corresponding total output amount (not shown) may be the total customization order amount or order amount of products A to E in a certain period of time. This other example may also be referred to as a product design example in the following text.

[0025] In the text, the term "multiple products" may refer to products of different types, products of the same type but different specifications, or a combination thereof. As an example only, product A may be a double bed, product B may be a double bed of a different size than product A, product C may be a single bed, product D may be a closet, product E may be a TV stand, etc. It should also be understood that although only five products A-E are shown in FIG. 1, this is for illustrative purposes only and is not intended to be limiting. According to embodiments of the present disclosure, more or fewer products may be included. In addition, in some embodiments, the product information 110 may further include other information other than the output amount and the target attribute, such as historical output status, geographic location information, etc. These will be described later.

[0026] The causal relationships 103 may represent or describe factors that affect the output volume of each of the products A-E. Such factors include at least the target attributes of the products A-E. The target product information 104 may represent at least one target product that affects the total output volume of the plurality of products A-E, where example target products are product A and product C. In some embodiments, the target product is determined by the computing device 102 based on the causal relationships 103.

[0027] The computing device 106 can obtain the causal relationship 103 and the target product information 104 to determine adjustment information 105 for the target products A and C. The adjustment information 105 can include at least adjustment modes for the target attributes of the target products A and C, such as changes to the attribute values ​​of the target attributes. The adjustment information 105 can further include changes in the total output volume corresponding to the adjustment modes. In the above product design example, the adjustment information 105 can include size changes for the target products A and C, and can further include changes in the predicted total customized order volume caused by the changes.

[0028] Computing devices 102 and 106 may be any suitable computing device, such as, for example, a fixed computing device, or a portable computing device, such as a mobile phone, a tablet PC, etc. Additionally, while computing devices 102 and 106 are shown as separate in FIG. 1, it should be understood that in some embodiments, computing devices 102 and 106 may be the same computing device, or operations or modules described separately in the following text with reference to computing devices 102 and 106 may be implemented in the same physical device.

[0029] Please refer now to Figure 2, which illustrates a flow chart of a product analysis process 200 according to some embodiments of the present disclosure. The process 200 may be implemented by the computing device 102 of Figure 1. For ease of discussion, the process 200 will be described in conjunction with Figure 1.

[0030] In block 210, the computing device 102 acquires product information 110 regarding a plurality of products A to E. The product information 110 includes at least the output amount (e.g., column 112) and the target attribute (e.g., column 113) of each of the plurality of products A to E within a certain period of time. The output amount indicates the number of corresponding products that are output to the outside within the certain period of time. In the product sales example, the product information 110 may include at least the weekly sales amount and price of each of the products A to E. In the product design example, the product information 110 may include at least the feature size and the weekly customization order amount of each of the products A to E.

[0031] In some embodiments, the product information 110 may further include other attribute information other than the target attribute. For example, if the target attribute is price, the other attribute information may include the corresponding product type (e.g., bedding, kitchenware), characteristic size (length, width, height), color, etc. For further example, if the target attribute is size, the other attribute information may include the corresponding product type (e.g., bedding, kitchenware), price, color, etc.

[0032] In some embodiments, the product information 110 may further include historical information regarding the plurality of products A-E, such as a historical target attribute and / or a historical output volume during the period prior to the period for each product in the plurality of products A-E. For example, for product sales examples, when a product analysis is performed on a weekly basis, the historical information may include the prices and sales volumes of the plurality of products A-E during the previous one, two, or three weeks.

[0033] In some embodiments, the product information 110 may further include location information associated with each product in the plurality of products A-E. For example, such location information may indicate a location of an entity that processes the corresponding product and / or may indicate a location of an entity that receives the output product. In a product sales instantiation, the location information may include a geographic location where a sales entity (e.g., a retail market) of the corresponding product is located, such as the size of the city (e.g., first-tier city), the specific location of the market (e.g., urban or suburban). In a product design instantiation, the location may include a geographic location where an entity (e.g., an individual, a product sales entity) that orders or customizes the corresponding product is located, and / or a geographic location where a design entity of the corresponding product is located, etc.

[0034] In some embodiments, the product information 110 may further include information on operations (which may also be referred to as auxiliary operations) for at least some of the products A to E. Such operations are intended to promote the output of the products to the outside. In the product design example, such information may include whether one or more of the products A to E are actively promoted, such as whether they are listed at the front of the product manual, whether product advertisements are inserted, etc. In the product sales example, such information may include whether one or more of the products A to E are promoted (e.g., discounted), whether there are promotional posters at the sales location, etc.

[0035] Please refer to Fig. 3. Fig. 3 shows a simplified block diagram of product analysis and adjustment according to some embodiments of the present disclosure. The operation of obtaining product information described with reference to block 210 can be performed, for example, by a data collection module 301. For example, the data collection module 301 can fetch or read at least a portion of the product information 110 from a database of a product processing entity.

[0036] Please continue to refer to FIG. 2. In block 220, the computing device 102 applies the product information 110 to the data processing model to determine the causal relationship 103 regarding the output amount. The causal relationship 103 regarding the output amount indicates at least the dependency of the output amount of each of the multiple products A to E on the target attribute of each of the multiple products A to E. The data processing model may be any suitable model based on a causal relationship (linear / non-linear) learning technique. The data processing model may be any suitable model capable of determining the causal relationship using the product information 110.

[0037] The causal relationship 103 may indicate one or more factors (which may also be referred to as critical factors) that affect the output volume of the product and the manner of their influence. The one or more factors may include at least the target attribute of the product. If the product information 110 includes other information, the one or more factors may further include factors other than the target attribute, such as historical output status, geographic location, etc.

[0038] In some embodiments, the computing device 102 may perform pre-processing on the product information 110 for application to the data processing model. The pre-processing on the product information 110 may include text processing, feature engineering, or a combination thereof. Text processing and feature engineering are each described below with reference to FIG. 3.

[0039] The text processing module 302 can be used to process the text information in the product information 110 to obtain a corresponding quantitative representation or characteristic representation. For example, the above-mentioned location information and information on auxiliary operations are usually provided in text format. The text processing module 302 can obtain a quantified characteristic representation for the product processing entity based on the location information, such as which type of entity one or more product processing entities belong to (e.g., an indication of the size of the entity). In product sales examples, such a characteristic representation can indicate whether one or more product processing entities are first-tier city stores, second-tier city stores, etc. The text processing module 302 can determine a characteristic representation based on the information on auxiliary operations. The characteristic representation represents whether one or more products have been promoted in output within the certain period (e.g., one week), and the degree and scale of the promotion. In product sales examples, such a characteristic representation can represent whether one or more products have been promoted in the week, the degree and scale of the promotion, etc.

[0040] The feature engineering module 303 performs data analysis on the product information 110 or the quantified product information 110 to discover new features having physical meaning. In an embodiment where the product information 110 includes historical information on multiple products A-E, the feature engineering module 303 can generate time series features. The time series features can indicate or describe delay characteristics of the product output. For example, in a product design example, the time series features can include product customization order amount / size in the last week, product customization order amount / size in the week before last, etc. Also, for example, in a product sales example, the time series features can include product sales amount / price in the last week, product sales amount / price in the week before last, etc.

[0041] When the product information 110 includes a historical output amount, the feature engineering module 303 can mark a period characteristic of the certain period based on a comparison between the historical output amount and the output amount of the certain period (i.e., the considered period). The period characteristic can indicate whether the certain period is a peak period for outputting products to the outside. For example, if the output amount of the product exceeding a certain ratio in the certain period is greater than the historical output amount, the certain period can be marked as a peak period. For example, the feature engineering module 303 can perform special period marking. Such special periods can include, for example, periods corresponding to public holidays (e.g., Golden Week for National Day), special periods related to product processing entities (e.g., anniversary celebrations of sales entities), etc. In such an embodiment, the causal relationship learning module 304 can determine the period dependency of the output amount of each product in the plurality of products A to E based on the marked period characteristic. For example, see column 409 of table 400 described below.

[0042] When the product information 110 includes location information, the feature engineering module 303 can cluster the multiple geographic locations indicated by the location information based on the output volume of at least some of the multiple products A to E. Through the clustering, a clustering mark associated with the processing entity of the product can be obtained. For example, the feature engineering module 303 can cluster based on the information of the products among the multiple products A to E that have an output volume higher than a threshold or a high output volume ranking. In the product sales example, clustering can be performed on the sales entity. The clustering result can indicate whether the sales entity belongs to a first type of store (e.g., corresponding to a new store), a second type of store (e.g., corresponding to a special store such as a flagship store), etc. In the product design example, clustering can be performed on the customized order entity. The clustering result can indicate whether the customized order entity belongs to a first type of entity (e.g., corresponding to an individual), a second type of entity (e.g., corresponding to an organization, etc.), etc. In this embodiment, the causal relationship learning module 304 can determine the location dependency of the output quantity of at least some of the products A to E based on the clustering result. For example, see columns 406 and 407 of table 400 described below.

[0043] The causal relationship learning module 304 uses any suitable causal relationship learning technique to determine the causal relationships 103 for the output quantity of the product based on the product information 110 or the pre-processed product information 110. The causal relationships 103 can indicate the important factors that affect the output quantity of the product and the manner in which they affect it.

[0044] 4 illustrates a table 400 depicting example causal relationships according to some embodiments of the present disclosure. Table 400 is illustrative only and is not intended to be limiting. Causal relationships 103 may show fewer or more dependencies than those shown in table 400. Causal relationships 103 may also show dependencies in other formats other than a table.

[0045] In some embodiments, the causal relationship 103 may include only columns 401-405 of table 400, for example. Columns 401-405 indicate the dependency of the output volume of the product on the target attribute of the product. If the product information 110 includes historical output volumes, the causal relationship 103 may additionally include columns 406, 407, etc. If the product information 110 includes location information and / or performs feature engineering processing (as described above with reference to feature engineering module 303) on the location information, the causal relationship 103 may additionally include column 408, which indicates the dependency of the output volume of the product on related entities (e.g., processing entities, customized order entities). If feature extraction is performed on the historical output volumes in the product information 110, the causal relationship 103 may additionally include column 409. Column 409 indicates the dependency of the output volume of the product on whether the certain period considered is a peak period (e.g., National Day Golden Week).

[0046] In table 400, a non-blank element indicates that the corresponding output quantity depends on the corresponding factor (referred to as a significant factor). An element that is a numerical value (e.g., element 411) can indicate that the corresponding "factor" has a linear effect on the "result", and an element that is a formula (e.g., element 412) can indicate that the corresponding "factor" has a non-linear effect on the "result". For example, for the output quantity of product A, the significant factors include the target attribute of product A, the target attribute of product B, the target attribute of product A in the last week, and whether the related entity is a first-class entity or not. The target attribute of product A (e.g., price) has a linear effect on the output quantity of product A, that is, every time the target attribute changes by 1, the output quantity changes by -0.5, while the target attribute of product B has a non-linear effect on the output quantity of product A, and the influence relationship is F_21(), which represents a non-linear relationship. Other elements in table 400 have similar meanings and will not be described in detail here. Additionally, a blank element in table 400 indicates that the corresponding output quantity does not depend on the corresponding element; for example, the output quantity of product A does not depend on the target attribute of product C.

[0047] 2, in block 230, the computing device 102 determines, from among the multiple products A to E, at least one target product that affects the total output amount of the multiple products A to E based on the causal relationship 103. For example, in the example of FIG. 1, product A and product C are determined as target products. The target product can be regarded as a core value product whose target attribute has a certain effect on the output amount of multiple other products.

[0048] Determining at least one target product from among the multiple products A to E can be based on one or more criteria. In some embodiments, such criteria can include whether the ratio of the output amount (and / or output measure) of the product to the total output amount exceeds a threshold ratio. The products whose ratio exceeds the threshold ratio can be selected as candidates for the target product.

[0049] Alternatively or additionally, in some embodiments, such criteria may further include whether the number of other products whose output amount depends on the target attribute of a certain product in the multiple products A to E exceeds a threshold number, in other words, whether the number of other products affected by the target attribute of a certain product exceeds a threshold number. Products whose number exceeds the threshold number may be selected as candidates for the target product. In the example of FIG. 4, the other products affected by the target attribute of product A include product B, product D, and product E.

[0050] 3 in the computing device 102 can determine, for a product, some products, or each product among the multiple products A to E, the number of other products whose output amount depends on the target attribute of the product based on the dependency indicated by the causal relationship 103. If the number exceeds a threshold number, the target product determination module 305 can determine the product as a candidate product in the set of candidate products.

[0051] Alternatively or additionally, in some embodiments, such criteria may further include whether a change in total output volume due to a predetermined change in the target attribute of the product exceeds a threshold change. A product whose change in total output volume exceeds the threshold change may be selected as a candidate target product. In product sales examples, the criteria may include whether a change in total sales volume of the multiple products A to E when a product is reduced in price or discounted (e.g., 10% off) exceeds a threshold change. In product design examples, the criteria may include whether a change in total customization order volume of the multiple products A to E when a product's size is changed by a certain percentage (e.g., 10%) exceeds a threshold change. The target product determination module 305 may determine or predict a change in total output volume using the causal relationship 103 output by the causal relationship learning module 304.

[0052] For example, the target product determination module 305 can determine, for a product, some products, or each product among the multiple products A to E, a change in the total output amount caused by a predetermined change in the target attribute of the product based on the dependency indicated by the causal relationship 103. If the change in the total output amount exceeds a threshold change, the product can be determined as a candidate product in the set of candidate products.

[0053] The above multiple criteria can be used alone or in combination. When used in combination, the target product determination module 305 can use the multiple criteria in parallel. For example, the target product determination module 305 can apply each of the above multiple criteria to determine a set of multiple candidate products, and then determine a candidate product in the intersection of the sets of the multiple candidate products as the target product. When used in combination, the target product determination module 305 can selectively use the multiple criteria in sequence. For example, the target product determination module 305 can first apply one criterion to remove one or more products that do not satisfy the criterion from among the multiple products A to E, and then apply another criterion to the remaining products to determine the target product.

[0054] For illustrative purposes only, in the product sales example, a product that accounts for a high proportion of product sales (e.g., higher than 5%), whose product price affects the sales volume of other products (e.g., more than 10 types), and whose total sales increase is large after the product price is discounted (e.g., 10% off) (e.g., becomes the top 3 or exceeds a threshold) can be considered as a target product or a core value product. It should also be understood that the specific values ​​of discounts and size changes listed in the above description are merely illustrative and are not intended to be limiting, and any suitable discounts and size changes are included within the scope of the present disclosure.

[0055] In some embodiments, the computing device 102 can provide information about at least one target product to an entity associated with the plurality of products A-E. The information about the at least one target product can include which product or products the target product is, and can further include other information, such as, for example, how many or which other products are affected by a target attribute of the target product, a change in total output volume due to a predetermined change in a target attribute of the target product, etc. The entity associated with the plurality of products A-E can include a processing entity of the plurality of products A-E, such as a sales entity, a design entity, etc.

[0056] Above, several embodiments of analyzing products by performing information processing have been described with reference to Figs. 1 to 4. In these embodiments, a core product or an important product in a plurality of products can be determined by processing product information including different source data and utilizing an automated causal learning technique. Information on the core product or important product can be provided to a product processing entity as a guide or reference. For example, the product processing entity can improve and even maximize efficiency or profit by formulating or adjusting a strategy based on the information on the core product or important product. For example, in a product design example, the product design entity can invest more costs in the size design aspect of the core product or important product. Also, for example, in a product sales example, the product sales entity can increase total sales by adjusting the price of the core product or important product.

[0057] In some embodiments of the present disclosure, the information processing may adjust target attributes of the product. Figure 5 illustrates a flow chart of a product adjustment process 500 according to some embodiments of the present disclosure. The process 500 may be implemented by the computing device 106 of Figure 1. For ease of discussion, the process 500 will be described in conjunction with Figure 1 and additionally in conjunction with Figure 3.

[0058] In block 510, the computing device 106 obtains a causal relationship 103 regarding the output amount of the multiple products A to E. The causal relationship 103 indicates at least the dependency of the output amount of each product in the multiple products A to E on the target attribute of each of the multiple products A to E, and the output amount indicates the number of the corresponding product output to the outside within a certain period of time. The causal relationship described here is the same as that described with respect to the process 200 described above, and therefore will not be discussed in detail.

[0059] In some embodiments, the computing device 106 can receive the causal relationship 103 regarding the output quantities of the multiple products A-E from another device (e.g., the computing device 102) or a data source. For example, the adjustment information determination module 306 implemented in the computing device 106 can receive the causal relationship 103 from the causal relationship learning module 304. In some embodiments, the computing device 106 can determine the causal relationship by performing the process 200 described above.

[0060] In block 520, the computing device 106 determines at least one target product from among the plurality of products A to E that affects the total output quantity of the plurality of products A to E. The target product may be considered as a core product or an important product whose target attributes have a certain influence on the output quantity of the plurality of other products, as described above with respect to the process 200.

[0061] In some embodiments, the computing device 106 may determine at least one target product as described above with reference to block 230. For example, the computing device 106 may determine the target product using one or more of the criteria described above with reference to block 230.

[0062] In some embodiments, the computing device 106 can determine the target product based on information other than causality. For example, the computing device 106 can determine the target product based only on whether the ratio of the output amount of the product to the total output amount exceeds a threshold ratio. In some embodiments, the computing device 106 can receive a determination of the target product for the plurality of products A-E, for example from the computing device 102.

[0063] In block 530, the computing device 106 determines adjustment information 105 for the target attributes of at least one of the target products A and C based on the causal relationship 103. For the example in FIG. 1, the adjustment information 105 may include at least an adjustment mode for the target attributes of the target products A and C, such as a change to the attribute value of the target attribute. The adjustment information 105 may further include a change in the total output amount corresponding to the adjustment mode. In a product design example, the adjustment information 105 may include a change to the size of the target products A and C, and may further include a change in the predicted total customization order amount caused by the change. In a product sales example, the adjustment information 105 may include a change to the price of the target products A and C (e.g., how much discount each is), and may further include a change in the predicted total sales amount caused by the change.

[0064] In some embodiments, the computing device 106 (e.g., the adjustment information providing module 307) provides the adjustment information 105 to the object associated with the plurality of products A-E, so that the associated object can apply the adjustment indicated by the adjustment information 105 to at least one target product, such as adjusting the size of the target product, discounting the target product, etc. In some embodiments, the computing device 106 can further obtain an adjusted output amount of each product in the plurality of products A-E after the adjustment is applied. The computing device 106 can apply the adjusted output amount to a data processing model (e.g., the causal relationship learning model described in the process 200) to update the causal relationship or further correct the causal relationship model. For example, the adjustment information providing module 307 can obtain the adjusted output amount from the associated object and communicate the adjusted output amount to the data collection module 301 for updating the causal relationship.

[0065] In block 530, the computing device 106 can determine the adjustment information 105 in a number of ways. In some embodiments, the computing device 106 can compare different adjustment modes (which can also be referred to as strategies) for at least one target product. See FIG. 6A. FIG. 6A shows a flowchart of a process 601 for determining adjustment information according to some embodiments of the present disclosure. The process 601 can be considered as one specific implementation of block 530.

[0066] In block 610, the computing device 106 (e.g., the adjustment information determination module 306) obtains a plurality of adjustment modes or strategies for at least one target product. Each adjustment mode in the plurality of adjustment modes includes a change to a target attribute of at least one target product. For example, one adjustment mode in the plurality of adjustment modes can include which change is made to the target attribute of target product A, such as a percentage decrease or increase in size, a percentage decrease or increase in price, etc., while leaving the target attribute of target product B unchanged. Another adjustment mode in the plurality of adjustment modes can include what change is made to the target attributes of target products A and B, respectively. Yet another adjustment mode in the plurality of adjustment modes can include what change is made to the target attribute of target product B, while leaving the target attribute of target product A unchanged.

[0067] In some embodiments, the computing device 106 can provide information about at least one target product to a subject associated with a plurality of products A-E, and obtain at least a portion of the plurality of adjustment modes from the associated subject. The information about the at least one target product and the associated subject are as described above with reference to Fig. 2. The adjustment modes obtained from the associated subject can be one or more strategies formulated by the associated subject based on the information about the target product.

[0068] Alternatively or additionally, in some embodiments, the computing device 106 can autonomously determine one or more adjustment modes for the target products. For example, the computing device 106 can combine different modifications (or no changes) to the target attributes with different arrangements of the target products to generate one or more adjustment modes. For example, in a product sale example, different modifications can include no price change, a 10% discount, a 20% discount, etc.

[0069] In block 620, the computing device 106 may determine, as at least a part of the adjustment information 105, a number of predicted values ​​of the change in the total output caused by the change based on the dependencies indicated by the causal relationships 103. Each predicted value corresponds to one adjustment mode of the plurality of adjustment modes. The computing device 106 utilizes the learned causal relationships to predict the change in the total output under different adjustment modes or strategies to obtain an optimal strategy and a corresponding value (absolute or relative) of the total output.

[0070] For example, in the product sales example, the multiple adjustment modes or strategies may include adjustment mode 1, in which target product A is discounted by 10% and target product B is left unchanged, adjustment mode 2, in which target product A is discounted by 20% and target product B is left unchanged, and adjustment mode 3, in which both target products A and B are discounted by 10%. Using the causal relationships 103, it may be determined that adjustment mode 1 increases total sales by 80,000, adjustment mode 2 increases total sales by 78,000, and adjustment mode 3 increases total sales by 73,000. The computing device 102 may provide the predicted total output change corresponding to the different adjustment modes or strategies to an associated target, such as a product sales entity or a product design entity, as at least a part of the adjustment information 105. It should be understood that the above-mentioned adjustment modes and the modifications (e.g., specific discounts) included therein are merely exemplary and are not intended to be limiting.

[0071] In some embodiments, in block 630, the computing device 106 may select an adjustment mode to apply to the at least one target product from among a plurality of adjustment modes based on the plurality of predicted values. For example, the computing device 106 may determine the adjustment model that has the largest forward change in total output amount as the adjustment mode to apply. For the above example, the computing device 106 may select adjustment mode 1 as the adjustment mode to apply.

[0072] In block 530, in some embodiments, the computing device 106 can determine the adjustment mode and generate adjustment information through optimization learning. See FIG. 6B. FIG. 6B shows a flowchart of another process 602 for determining adjustment information according to some embodiments of the present disclosure. The process 602 can be regarded as one specific implementation of block 530.

[0073] In block 660, the computing device 106 determines a change in the total output amount that changes based on the target attributes of at least one of the target products A and C based on the causal relationships 103. For example, the computing device 106 further learns a prediction formula for the output amount of the at least one target using the learned causal relationships 103. Furthermore, a formula for the change in the total output amount with the target attributes of the target products A and C as arguments can be obtained.

[0074] In block 670, the computing device 106 may determine changes to the target attributes of at least one of the target products A and C by maximizing the change in the total output volume as at least a part of the adjustment information 105. For example, the computing device 106 may determine an adjustment mode, such as an optimal size combination or an optimal list price combination, that maximizes efficiency or profit by maximizing the change in the total output volume expressed by an equation for the change in the total output volume under a given constraint.

[0075] Above, the process of adjusting information of target attributes of target products has been described with reference to Figures 5, 6A and 6B. In such an embodiment, the causal relationship can be utilized to formulate a corresponding strategy for core or important products, thereby improving and thus maximizing the overall efficiency or profit of processing multiple products.

[0076] Although the processes 200 and 500 are described above with reference to Figures 2 and 5, respectively, it should be understood that in some embodiments, the processes 200 and 500 may be combined into a single process.

[0077] 7 shows a block schematic diagram of an exemplary device 700 capable of implementing embodiments of the present disclosure. As shown in the figure, the device 700 includes a central processing unit (CPU) 701. The CPU 701 can perform various appropriate operations and processes based on computer program instructions stored in a read-only memory (ROM) 702 or loaded from a storage unit 708 into a random access memory (RAM) 703. The RAM 703 can further store various programs and data required for the operation of the device 700. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) port 705 is also connected to the bus 704.

[0078] A number of components in the device 700 are connected to an I / O port 705. The components include an input unit 706 such as a keyboard, a mouse, etc., an output unit 707 such as various types of displays, speakers, etc., a storage unit 708 such as a magnetic disk, an optical disk, etc., and a communication unit 709 such as a network interface card, a modem, a wireless communication transceiver, etc. The communication unit 709 enables the device 700 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0079] The processing unit 701 executes each of the methods and processes described above, such as any one of the processes 200, 500, 601, 602. For example, in some embodiments, any one of the processes 200, 500, 601, 602 may be implemented as a computer software program or computer program product, tangibly stored in a device-readable medium, such as the storage unit 708. In some embodiments, a part or all of the computer program may be loaded and / or installed in the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the CPU 701, one or more steps of any one of the processes 200, 500, 601, 602 described above may be executed. Alternatively, in other embodiments, the CPU 701 may be arranged to execute any one of the processes 200, 500, 601, 602 in any other suitable manner (e.g., using firmware).

[0080] According to some embodiments of the present disclosure, a computer readable medium is provided having stored thereon a computer program which, when executed by a device, implements the methods of the present disclosure.

[0081] It should be understood by those skilled in the art that the steps of the method of the present disclosure described above can be implemented by a general-purpose computing device, and can be centralized in a single computing device or distributed across a network of multiple computing devices. Optionally, the steps of the method of the present disclosure can be implemented by a computing device-executable program code, and thus can be stored in a storage device and executed by a computing device, or can be formed as individual integrated circuit modules, or multiple modules or steps can be formed as a single integrated circuit module. Thus, the present disclosure is not limited to any particular combination of hardware and software.

[0082] It should be understood that, although the above detailed description refers to multiple units or sub-units of a device, such division is merely exemplary and non-mandatory. In fact, according to the embodiments of the present disclosure, features and functions of two or more units described above may be embodied in one unit. Conversely, features and functions of one unit described above may be further divided to be embodied in multiple units.

[0083] The above description is merely a preferred embodiment of the present disclosure, and does not limit the present disclosure. Those skilled in the art may have various modifications and changes to the present disclosure. Any amendments, equivalent replacements, improvements, etc. made within the spirit and principle of the present disclosure should be included within the protection scope of the present disclosure.

Claims

1. Obtaining product information for a plurality of products, the product information including at least an output amount and a target attribute of each product in a certain period of time; applying the product information to a data processing model to determine causal relationships with respect to the output quantities; determining at least one target product from among the plurality of products that affects a total output amount of the plurality of products based on the causal relationship; Equipped with The output amount indicates the number of corresponding products output to the outside within the certain period, the causal relationship indicates at least a dependency of the output quantity of each product in the plurality of products on the target attribute of each of the plurality of products; Information processing methods.

2. Determining the at least one target product includes: determining a change in a total output amount due to a predetermined change in the target attribute of a first product of the plurality of products based on the dependency; determining the first product as a candidate product in a set of candidate products based on determining that the change in the total output amount exceeds the change threshold; determining said at least one target product from among said set of candidate products; The information processing method according to claim 1 , comprising:

3. Determining the at least one target product from among the set of candidate products includes: selecting a candidate product from the set of candidate products, the candidate product having a ratio of the output volume to the total output volume exceeding a ratio threshold, as a target product. The information processing method according to claim 2 .

4. The product information further comprises: a historical target attribute and / or a historical output volume for each product in the plurality of products prior to the period of time; location information associated with each product in the plurality of products; Operational information for at least some of the products in the plurality of products; and At least one other attribute of each product in the plurality of products other than the target attribute. and the operation is for facilitating the external output of at least some of the products; The information processing method according to claim 1 .

5. and performing pre-processing on the product information for application to the data processing model. The information processing method according to claim 4.

6. the product information includes the historical output volume; Pre-processing the product information for application to the data processing model includes: identifying a period characteristic for the period based on a comparison of the historical output amount to the output amount; the period characteristic indicates whether the certain period is a peak period for outputting products to the outside, Determining the causal relationship includes: determining a time dependency of the output quantity of each product in the plurality of products based on the time characteristic; The information processing method according to claim 5.

7. the product information includes the location information, Pre-processing the product information for application to the data processing model includes: clustering the plurality of geographic locations indicated by the location information based on the output volume of at least some of the plurality of products; Determining the causal relationship includes: determining a location dependency of the output quantity of at least some of the products in the plurality of products based on a result of the clustering. The information processing method according to claim 5.

8. providing information about the at least one target product to a subject associated with the plurality of products. The information processing method according to claim 1 .

9. The data processing model includes a causal model. The information processing method according to claim 1 .

10. An electronic device, A processor; a memory coupled to said processor, storing instructions which, when executed by said processor, cause said electronic device to perform a method according to any one of claims 1 to 9; Including, electronic equipment.

11. A computer program product which, when executed by a processor, causes the information processing method according to any one of claims 1 to 9 to be implemented.

Images