CN112561552A

CN112561552A - Method and device for adjusting value attribute of article

Info

Publication number: CN112561552A
Application number: CN201910918757.1A
Authority: CN
Inventors: 平霄霄
Original assignee: Beijing Jingdong Century Trading Co Ltd; Beijing Jingdong Shangke Information Technology Co Ltd
Current assignee: Beijing Jingdong Century Trading Co Ltd; Beijing Jingdong Shangke Information Technology Co Ltd
Priority date: 2019-09-26
Filing date: 2019-09-26
Publication date: 2021-03-26

Abstract

The invention discloses a method and a device for adjusting value attributes of articles, and relates to the technical field of computers. One embodiment of the method comprises: respectively acquiring transaction data of the target object in the current time period and the first time period according to the identification of the target object and the identification of the target object; acquiring a value elasticity coefficient of a target article in a first time period, and determining the value elasticity coefficient of the target article in the current time period according to transaction data and the value elasticity coefficient; and adjusting the value attribute of the target object in the current time period by using the determined value elasticity coefficient to obtain the adjusted value attribute. According to the implementation mode, through iterative updating of the value elasticity coefficient, the dependency on historical periodic data is greatly reduced, more sales schemes are created for enterprises, and accordingly fine management of large-scale article value attributes is achieved without manual participation.

Description

Method and device for adjusting value attribute of article

Technical Field

The invention relates to the technical field of computers, in particular to a method and a device for adjusting value attributes of articles.

Background

The value elasticity coefficient is the ratio between the percentage change of sales volume of an article and the percentage change of its value attribute, and is defined as follows:

wherein epsilon represents the value elasticity coefficient of the goods, Q represents the sales volume of the goods, P represents the value attribute of the goods,

indicating the amount of change.

The value elasticity coefficient of the article reflects the degree of change of the market demand caused by the change of the value attribute of the article, and is the main basis for determining the price increase or price reduction of an enterprise. At present, fitting calculation is carried out by adopting a linear regression method based on historical quantitative price (transaction amount and value attribute) data of articles so as to obtain a value elasticity coefficient of each time period.

In the process of implementing the invention, the inventor finds that the prior art has at least the following problems:

1) each calculation needs to acquire data of a longer history period (for example, 1-2 years), and the calculation result is biased to an average value and cannot represent the characteristic that the article is in each season;

2) for the articles with high transaction frequency, the value elasticity coefficient of the articles may be slowly changed under the control of historical data, so that the change of the current market factor cannot be reflected in time.

Disclosure of Invention

In view of this, embodiments of the present invention provide a method and an apparatus for adjusting an article value attribute, which can at least solve the problem that a subsequent value elastic coefficient cannot reflect seasonality and further affects subsequent article price adjustment due to an excessively long history period for obtaining sample data in the prior art.

To achieve the above object, according to an aspect of an embodiment of the present invention, there is provided an article value attribute adjusting method including:

respectively acquiring transaction data of the target object in the current time period and the first time period according to the identification of the target object; wherein the first time period is a historical time period which is separated from the current time period by a preset time interval;

acquiring a value elasticity coefficient of the target item in the first time period, and determining the value elasticity coefficient of the target item in the current time period according to the transaction data and the value elasticity coefficient; wherein the value elasticity coefficient is the sensitivity of the article demand to the value attribute variation;

and adjusting the value attribute of the target object in the current time period by using the determined value elasticity coefficient to obtain the adjusted value attribute.

Optionally, the first time period is an initial time period when first calculation is performed;

before the obtaining of the transaction data of the target item in the current time period and the first time period respectively, further comprising:

acquiring a historical transaction record of the target object within a preset historical time; the preset historical time comprises a plurality of historical time periods, and the last time period is the initial time period;

analyzing the historical transaction records to obtain historical transaction data of the target object in each historical time period;

and inputting the historical transaction data into a first value elastic coefficient model to obtain the value elastic coefficient of the target object in the initial time period.

Optionally, after the obtaining of the historical transaction record of the target item within the predetermined historical time period, the method further includes:

if the number of the historical transaction records is smaller than a preset number threshold value, determining the category of the target object, and acquiring a first historical transaction record of each object in the category within the preset historical time;

analyzing the first historical transaction record to obtain first historical transaction data of each article in each historical time period;

inputting the first historical transaction data into a second value elasticity coefficient model to obtain the value elasticity coefficient of the category or the value elasticity coefficient of each brand under the category;

and according to the priority order, taking the value elasticity coefficient of the brand to which the target item belongs or the value elasticity coefficient of the category as the value elasticity coefficient of the target item in the initial time period.

Optionally, the determining the value elasticity coefficient of the target item in the current time period according to the transaction data and the value elasticity coefficient includes:

inputting the transaction data and the value elasticity coefficient into a filter to obtain the value elasticity coefficient of the target object in the current time period; wherein the filter is further configured to perform a noise adjustment based on the transaction data of the target item at the current time period and the transaction data at the first time period.

To achieve the above object, according to another aspect of an embodiment of the present invention, there is provided an article value attribute adjusting apparatus including:

the information analysis module is used for respectively acquiring transaction data of the target object in the current time period and the first time period according to the identification of the target object; wherein the first time period is a historical time period which is separated from the current time period by a preset time interval;

the coefficient determining module is used for acquiring the value elasticity coefficient of the target object in the first time period and determining the value elasticity coefficient of the target object in the current time period according to the transaction data and the value elasticity coefficient; wherein the value elasticity coefficient is the sensitivity of the article demand to the value attribute variation;

and the value attribute adjusting module is used for adjusting the value attribute of the target object in the current time period by using the determined value elasticity coefficient to obtain the adjusted value attribute.

further comprising an initial coefficient determination module for:

Optionally, the initial coefficient determining module is further configured to:

Optionally, the coefficient determining module is configured to:

To achieve the above object, according to still another aspect of embodiments of the present invention, there is provided an article value attribute adjusting electronic device.

The electronic device of the embodiment of the invention comprises: one or more processors; a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement any of the above-described methods of adjusting a value attribute of an item.

To achieve the above object, according to a further aspect of the embodiments of the present invention, there is provided a computer-readable medium on which a computer program is stored, the program, when executed by a processor, implementing any one of the above-mentioned article value attribute adjusting methods.

According to the scheme provided by the invention, one embodiment of the invention has the following advantages or beneficial effects: the value elasticity coefficient of the current time period is updated iteratively based on the transaction data and the value elasticity coefficient of the first time period, so that the dependency on historical periodic data is greatly reduced. The transaction rule of the goods is obtained by means of filter and big data processing, more sales schemes can be created for enterprises, the enterprises can conveniently control the fluctuation range of the value attributes of the goods, and therefore the fine management of the value attributes of the goods in a large scale can be achieved without manual participation.

Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.

Drawings

The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:

FIG. 1 is a schematic flow chart of a method for adjusting an item value attribute according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of a process for determining a day-of-day value elasticity coefficient based on previous day data;

FIG. 3 is a schematic flow chart diagram of an alternative method of adjusting value attributes of an item in accordance with an embodiment of the present invention;

FIG. 4 is a schematic flow chart diagram of an alternative method of adjusting value attributes of an item in accordance with an embodiment of the present invention;

FIG. 5 is a schematic representation of the process from last two years of historical characterization data for an item of the category to generating an initial value elastic coefficient for each item under the category;

FIG. 6 is a flow chart illustrating a method for adjusting a value attribute of a specific object according to an embodiment of the present invention;

FIG. 7 shows an overall generalized schematic of an embodiment of the present invention;

FIG. 8 is a schematic diagram of the main modules of an article value attribute adjusting apparatus according to an embodiment of the present invention;

FIG. 9 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;

FIG. 10 is a schematic block diagram of a computer system suitable for use with a mobile device or server implementing an embodiment of the invention.

Detailed Description

Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Referring to fig. 1, a main flowchart of an article value attribute adjusting method according to an embodiment of the present invention is shown, including the following steps:

s101: respectively acquiring transaction data of the target object in the current time period and the first time period according to the identification of the target object; wherein the first time period is a historical time period which is separated from the current time period by a preset time interval;

s102: acquiring a value elasticity coefficient of the target item in the first time period, and determining the value elasticity coefficient of the target item in the current time period according to the transaction data and the value elasticity coefficient; wherein the value elasticity coefficient is the sensitivity of the article demand to the value attribute variation;

s103: and adjusting the value attribute of the target object in the current time period by using the determined value elasticity coefficient to obtain the adjusted value attribute.

In the above embodiment, for step S101, when specifically calculating the value elasticity coefficient in the current time period, in addition to the transaction data in the current time period, the transaction data in a time period (i.e. the first time period) before the current time period needs to be considered, and the transaction data can be obtained based on the transaction record thereof.

The time period here may be one day, two days or one month, two months, etc., for example yesterday and today, morning and afternoon, specifically set by the staff.

In addition, the first time period is a historical time period that is separated from the current time period by a predetermined time interval, for example, the previous day, two days ago. Both may be the same duration, e.g., both are 24 hours; the time length of the invention can be different, for example, 9:00-12:00 in the morning and 13:00-17:00 in the afternoon, and the invention is mainly carried out in the same time length mode according to the setting of workers.

The transaction data may include transaction amount, value attribute, price of item page, browsing amount, etc., and the present invention is mainly described by taking two necessary factors of transaction amount and value attribute as examples.

1) The transaction amount, i.e., the number of transactions of the item. For the transaction amount, the transaction amount can be the total transaction amount or the daily average transaction amount in the corresponding time period; for example, taking two days as a time period unit, counting the sum of the transaction amounts of the same item in a plurality of orders within two days as a total transaction amount, and if the average value is taken, the daily transaction amount is obtained;

2) value attribute, the price actually paid for the consumer. The value attribute can also be an average value attribute in a corresponding time period; for example, the value attributes of the same item in a plurality of orders in a day are counted and averaged to obtain the average value in the day unit.

Considering that the seller will adopt marketing means, the value attribute is not directly equal to the price of selling page items, but is obtained by correcting the page price and the promotion amount of the items, such as the page price-promotion amount of the items.

In step S102, when not first calculating, the value elasticity coefficient of the article in the current time period needs to be calculated based on the value elasticity coefficient of the first time period.

The value elastic coefficients of different items may be different, and an item-value elastic coefficient list may be established to record the value elastic coefficients of the items at different time periods. Thus, a list of corresponding item-value elasticity coefficients may be determined based on the identity of the item, such as a number, name, description, etc., from which the value elasticity coefficient for the first time period prior to the current time period is then obtained.

However, when the value elastic coefficient is calculated for the first time, the value elastic coefficient needs to be calculated based on the historical data of a certain historical duration, and the value elastic coefficient at the initial time period is obtained, which is described with reference to subsequent fig. 3 and fig. 4, and is not described herein again. However, the value elastic coefficient calculation after the initial period is based on the value elastic coefficient updated in the first period.

For step S103, the value elasticity coefficient is ultimately used for pricing of the item. Due to business needs, the variation range of the value attribute of the article in a short period cannot be too large, otherwise, a drop impression is generated for consumers, and loss of passenger flow and benefits is brought to enterprises. Therefore, after calculating the value elastic coefficient for each time segment, the variation range thereof may be limited, for example, the elastic fluctuation range may be controlled by the elastic standard deviation.

After the value elasticity coefficient is obtained or the value elasticity coefficient is further limited, the optimal value attribute of the article can be determined by using the mean value and the variance of the elasticity value attribute, or the value elasticity coefficient model can be comprehensively optimized by constructing the transaction amount and the gross profit of the article to adjust the value attribute of the article, and the optimal value attribute of the article is obtained through calculation.

Furthermore, in the actual implementation process, sometimes the benefit brought by the optimal value attribute may be smaller than the current value attribute of the article, and considering this situation, the article may be divided into two groups for testing, one group is sold with the optimal value attribute, the other group is sold with the current unadjusted value attribute, the profits of the two groups are compared after selling for a period of time, and the value attribute with higher profits is selected as the final value attribute.

Referring to fig. 2, taking the first time period as the previous time period in the current time period as an example, a process of determining the current-day value elasticity coefficient based on the previous-day data is shown: and inputting the value elasticity coefficient, the transaction amount and the value attribute of the article in the previous day and the transaction amount and the value attribute of the current day into a filter or a neural network to obtain the value elasticity coefficient of the article in the current day, and controlling the change amplitude of the value elasticity coefficient by using the elasticity standard deviation.

In the actual operation process, the value elastic coefficient of the previous day also needs to be updated continuously. For example, a business may request that the value elastic coefficient for an item at 2019.06.13 be determined, then the value elastic coefficient may be calculated based on the value elastic coefficient of 2019.06.12 the day before. The staff can obtain 2016.06.12-2018.06.12 or 2017.06.12-2018.06.12 transaction records of the article to determine the value elasticity coefficient of 2018.06.12 on the initial date, and then continuously update the value elasticity coefficient of each date, so that the finally obtained value elasticity coefficient of the article on the 2019.06.12 date is more accurate.

According to the method provided by the embodiment, the value elasticity coefficient of the current time period is updated based on the first time period, so that iterative updating of the value elasticity coefficient is realized, dependence on historical periodic data of the article is greatly reduced, enterprises can conveniently control fluctuation range of the value attribute of the article, and accordingly, fine management of the value attribute of the article in a large scale is realized without manual participation.

Referring to fig. 3, a flow chart of an optional item value attribute adjustment method according to an embodiment of the present invention is shown, including the following steps:

s301: acquiring a historical transaction record of a target article within a preset historical time according to the identification of the target article; the preset historical time comprises a plurality of historical time periods, and the last time period is an initial time period;

s302: analyzing the historical transaction records to obtain historical transaction data of the target object in each historical time period;

s303: inputting the historical transaction data into a first value elastic coefficient model to obtain a value elastic coefficient of the target object in the initial time period;

s304: respectively acquiring transaction data of the target object in the initial time period and the second time period; wherein the initial time period is a historical time period which is separated from the second time period by a preset time interval;

s305: determining a value elasticity coefficient of the target item in the second time period according to the transaction data and the value elasticity coefficient;

s306: and adjusting the value attribute of the target object in the second time period by using the determined value elasticity coefficient to obtain the adjusted value attribute.

Updating the value elastic coefficient of an item requires a value elastic coefficient at an initial time period. Although the value elastic coefficient is gradually corrected in the working process of the filter, the accuracy of the value elastic coefficient in the initial time period influences the accuracy of the calculation result of the subsequent filter to a certain extent.

In the above embodiment, the initial time period in steps S301 and S302 is a time period in which the value elasticity coefficient is calculated for the first time for the article, for example, 6 months 11 to 13 days 2019.

And calculating the initial value elasticity coefficient of each article in a regression fitting mode based on the historical transaction data of the articles so as to improve the accuracy of the value elasticity coefficient of the articles in the initial time period.

The historical transaction data may be derived based on historical transaction records for the item. For example, taking a day as a unit, acquiring transaction records of the current day in the last two years, so as to obtain daily transaction amount, daily average value attribute and daily stock state of the article; however, in the unit of month, the monthly transaction amount, the monthly average value attribute and the monthly stock state are obtained.

The inventory state is used for describing whether the inventory of the articles is saturated or not, and the value is between 0 and 1. Usually, the stock state needs to be calculated based on the stock quantity, for example, the stock quantity of the goods in the national warehouses is weighted at a certain day, or the ratio of the stock quantity to the transaction amount may be specifically calculated as follows:

wherein status represents the inventory status index, stock represents the inventory quantity,

the average transaction amount is represented, and here, may be a daily average transaction amount, a monthly average transaction amount, or the like.

Although the stock quantity can be considered, the stock quantity values are different, for example, 200 and 30000, and the stock quantity needs to be integrated into the same order of magnitude in actual calculation, so that the operation is complicated. Therefore, the invention mainly considers the inventory state to eliminate the influence of the difference of the counting units of the articles on the calculation process, thereby facilitating the overall management statistics.

It should be noted that the characteristic data included in the historical transaction data may be different from the characteristic data included in the transaction data in fig. 1; for example, historical transaction data may have more inventory status than transaction data. For the generalized linear regression method, three general factors need to be considered; the filter in fig. 1 is designed based on the definition of the value elasticity coefficient, and the factor of stock of the goods can be not considered.

For step S303, the first-value elastic coefficient model may be a general linear regression method:

log Q＝ε×log P+β₀

wherein, beta₀An intercept term is represented, P represents a transaction amount, and a value elastic coefficient is calculated by taking log Q as a hidden variable and log P as an independent variable. Other independent variables such as inventory, flow rate and the like can be added in the actual calculation according to specific situations.

The first value elastic coefficient model can also be a mixed linear regression mode, and the inventory/inventory state information is considered at the moment, and the specific formula is as follows:

log Q＝ε×log P+β₁stock+β₀

wherein, beta₁The coefficient of the stock is specifically set by a worker.

For steps S304-S306, the process of calculating the value elastic coefficient for the second time, i.e., the second time period after the initial time period, is performed.

In a manner consistent with that shown in fig. 1, the value elastic coefficient of the second time period is updated by using the value elastic coefficient of the initial time period, and then the value elastic coefficient of the third time period (a time period after the second time period) is updated by using the value elastic coefficient of the second time period, so that the value elastic coefficient is continuously updated.

The method provided by the embodiment is suitable for scenes with more historical characteristic data, and the value elasticity coefficient of the goods in the initial time period is calculated by using a general linear regression model, so that the sensitivity of consumers to different goods prices is evaluated. Compared with the prior art, the method only uses the historical transaction records with longer historical periods when calculating the initial time period, and only considers the transaction data and the value elasticity coefficient of the first time period before the current time period in the subsequent calculation process, thereby effectively reducing the dependency on the historical data.

Referring to fig. 4, a schematic flow chart of an alternative item value attribute adjustment method according to an embodiment of the present invention is shown, including the following steps:

s401: acquiring a historical transaction record of a target article within a preset historical time according to the identification of the target article; the preset historical time comprises a plurality of historical time periods, and the last time period is an initial time period;

s402: if the number of the historical transaction records is smaller than a preset number threshold value, determining the category of the target object, and acquiring a first historical transaction record of each object in the category within the preset historical time;

s403: analyzing the first historical transaction record to obtain first historical transaction data of each article in each historical time period;

s404: inputting the first historical transaction data into a second value elasticity coefficient model to obtain the value elasticity coefficient of the category or the value elasticity coefficient of each brand under the category;

s405: according to the priority order, taking the value elasticity coefficient of the brand to which the target item belongs or the value elasticity coefficient of the category as the value elasticity coefficient of the target item in the initial time period;

s406: respectively acquiring transaction data of the target object in the initial time period and the second time period; wherein the initial time period is a historical time period which is separated from the second time period by a preset time interval;

s407: determining a value elasticity coefficient of the target item in the second time period according to the transaction data and the value elasticity coefficient;

s408: and adjusting the value attribute of the target object in the second time period by using the determined value elasticity coefficient to obtain the adjusted value attribute.

In the above embodiment, step S401 may be described with reference to step S301 shown in fig. 3, and steps S406 to S408 may be described with reference to steps S304 to S306 shown in fig. 1 and fig. 3, which are not described again.

In the above embodiment, in step S402, when there is no history feature data for a certain article or the history feature data is too small (less than a predetermined number threshold), the value elastic coefficient cannot be calculated using the general linear regression value elastic coefficient model, and thus a hybrid linear regression value elastic coefficient model is proposed.

The threshold value may be a certain number, and in this case, the embodiment is different from that in fig. 3, for example, 100, and the mode of fig. 4 is mainly used for newly marketed articles, and the mode of fig. 3 is mainly used for articles with a long time to market. However, when the threshold value is infinite or has a large value, the method shown in fig. 4 is required.

In a pricing scenario it may be assumed that: the value elastic coefficients under the same brand under one category are close, such as snacks. Based on this consideration, for an item with less transaction records, it can be obtained based on its belonging category/brand, so that the historical transaction records of each item under the category to which the item belongs need to be obtained, so that the value elasticity coefficient can cover more items, each item is ensured to have a value elasticity coefficient in the initial time period, and the obtained result is more biased to the integrity of the category.

The category here may be a secondary category or a tertiary category, etc., which is determined according to the service and data conditions. For distinguishing from the historical transaction records and the historical transaction data of the target item, the first historical transaction record and the first historical transaction data are used for representation.

Further, the historical period duration of the historical transaction records of each item under the category may be the same as the predetermined historical duration shown in fig. 3, for example, both may be two years, but may also be different. For a single article, it is necessary to ensure that the obtained sample data is sufficient, but when the number of articles in a category is large enough, if the history period is too long, the sample data is too much, and the subsequent calculation amount is too large, so that the obtained data period can be considered by an operator.

For steps S403 and S404, the second value elastic coefficient model is mainly a mixed linear regression value elastic coefficient model, and the regression fitting formula adopted is as follows:

log Q＝ε×log P+β₁stock+β₀

wherein the coefficient beta₀And beta₁The value of (2) is set by a worker.

Referring to fig. 5, the process from the historical transaction data of a certain category of articles in the last two years to the generation of the initial value elastic coefficient of each article under the category is illustrated:

the information input into the mixed linear regression model is: daily transaction amount of each article in a certain category in the last two years, value attribute and stock state in each date. And outputting the value elastic coefficient model to obtain three value elastic coefficients which are respectively:

the value elasticity coefficient of the type of the article, the value elasticity coefficient of each brand type under the article and the value elasticity coefficient of the type of the article; wherein:

1) calculating the value elasticity coefficient of the category through historical data of all articles under the category;

2) the value elasticity coefficient of the brand is obtained by calculation according to the type of the brand and historical data of all articles under the brand;

3) the value elasticity coefficient of the article is calculated through the historical data of the article.

For step S405, generally, the smaller the particle size, the higher the accuracy obtained. An article, such as a home appliance, a cosmetic, etc., contains the most tags; multiple labels may also be included under a brand, such as restaurants, clothing; but an item typically has only one specific label, such as an appliance.

For the three value elastic coefficients obtained by mixing the linear regression models, the priority is set as: the value elastic coefficient of the article itself > value elastic coefficient of brand > value elastic coefficient of category. Subsequently, in the process of calculating the value elasticity coefficient of each article, the elasticity with the highest optimization level category can be selected as the final value elasticity coefficient of the article.

For items with less historical feature data, the transaction records may reflect only part of the consumer's sensitivity to their price, and therefore, the value elasticity coefficient of the brand or class to which they belong is selected primarily. However, for an article with a large amount of historical feature data, the value elastic coefficient of the article itself can be selected according to the priority.

The method provided by the embodiment can be used for calculating the value elasticity coefficient of the articles with less historical transaction records based on the article types or brands to which the articles belong, so that the coverage rate of the value elasticity coefficient on the articles is improved, and the value elasticity coefficient of the articles in the initial time period is ensured. And based on the thought that the smaller the granularity is, the higher the precision is, priority setting is carried out on the value elastic coefficient, the selectivity of the value elastic coefficient is provided, and the calculation precision is improved.

Referring to fig. 6, a flowchart of a specific item value attribute adjustment method according to an embodiment of the present invention is shown, including the following steps:

s601: acquiring a historical transaction record of a target article within a preset historical time according to the identification of the target article; the preset historical time comprises a plurality of historical time periods, and the last time period is an initial time period;

s602: if the number of the historical transaction records is larger than or equal to a preset number threshold value, analyzing the historical transaction records to obtain historical transaction data of the target object in each historical time period;

s603: inputting the historical transaction data into a first value elastic coefficient model to obtain a value elastic coefficient of the target object in the initial time period;

s604: if the number of the historical transaction records is smaller than a preset number threshold value, determining the category of the target object, and acquiring a first historical transaction record of each object in the category within the preset historical time;

s605: analyzing the first historical transaction record to obtain first historical transaction data of each article in each historical time period;

s606: inputting the first historical transaction data into a second value elasticity coefficient model to obtain the value elasticity coefficient of the category and the value elasticity coefficient of each brand under the category;

s607: according to the priority order, taking the value elasticity coefficient of the brand to which the target item belongs or the value elasticity coefficient of the category as the value elasticity coefficient of the target item in the initial time period;

s608: respectively acquiring transaction data of the target object in the initial time period and the second time period; wherein the initial time period is a previous time period separated from the second time period by a predetermined time interval;

s609: inputting the transaction data and the value elasticity coefficient of the target object in the initial time period into a filter to obtain the value elasticity coefficient of the target object in the second time period; wherein the filter is further configured to perform noise adjustment based on the transaction data of the target item over the initial time period and the transaction data over the second time period;

s610: and adjusting the value attribute of the target object in the second time period by using the obtained value elasticity coefficient to obtain the adjusted value attribute.

In the above embodiment, for steps S601 to S603, refer to the description shown in fig. 3, for steps S604 to S607, refer to the description shown in fig. 4, and for steps S608 to S610, refer to the descriptions shown in fig. 1 to 4, which are not repeated herein.

In the above embodiment, in step S609, the value elastic coefficient may be updated by a filter.

In actual calculation, the filter has two error terms, namely a system error term and a measurement error term. The system error term reflects the error of the filter in the sales amount prediction, and the measurement error term reflects the deviation between the data recorded by the system and the actual data in the current time period. In the initial calculation, the two error terms exist based on the historical sales data of the articles recorded by the system, and in the later updating process of the value elasticity coefficient in each time period, the adjustment is continuously carried out along with each calculation of the filter.

The invention mainly adopts the self-adaptive Kalman filter, and the whole process is shown in figure 7.

The self-adaptive Kalman filter judges whether the system dynamic changes or not continuously by the filtering itself while filtering by using the measurement data so as to estimate and correct the value elastic coefficient model parameters and the noise statistical characteristics, improve the filtering design and reduce the actual error of the filtering. The filtering method organically integrates system identification and filtering design.

As a numerical estimation optimization method, the adaptive Kalman filter is widely applied to the fields of communication, signal processing, weather forecast and the like. When the adaptive Kalman filter is applied to solve the practical problem, the acquired domain knowledge is used for formalized description of the system, an accurate mathematical value elastic coefficient model is established, and then the design and implementation work of the filter is carried out based on the value elastic coefficient model.

In addition, the adaptive kalman filter is more suitable for processing of time series and white gaussian noise data than other filters, and can adjust the influence weight of the history data and the current data. These characteristics make the adaptive kalman filter more suitable for the context of calculating the value elastic coefficient of an article according to the present invention.

Compared with the prior art, the method provided by the embodiment of the invention has the following beneficial effects:

1) only when the value elasticity coefficient at the initial date is calculated, the historical data with a long period is considered, and then the value elasticity coefficient calculation of each time period is adjusted and updated based on the value elasticity coefficient of the historical time period with a fixed distance;

2) for the value elasticity coefficient calculation of the initial time period, if the historical transaction records are more, a general linear regression method can be adopted; but for the articles with less records, the value elasticity coefficients of the categories and brands of the articles need to be obtained, so that the articles have the value elasticity coefficients in the initial time period;

3) for the obtained value elastic coefficient, priority setting can be carried out according to the granularity, and the precision of the obtained value elastic coefficient is improved;

4) in the process of updating the value elastic coefficient, the filter can automatically balance the errors of the predicted sales volume and the data record sales volume of the system, and continuously adjust the gain coefficient so as to incline to the volume price of the current time period in the weight, thereby optimizing the value elastic coefficient;

5) the value elastic coefficient obtained by calculation is fused with the current seasonal influence, the rationality of the seasonal value elastic coefficient of the articles is ensured, and meanwhile, the change of the current market can be captured sensitively, so that the price adjustment of the articles is more objective and effective. The seasonality may be spring, summer, autumn, winter, or month, or may be a busy season, a slack season, a sales promotion season, or the like.

Referring to fig. 8, there is shown a schematic diagram of main modules of an article value attribute adjusting apparatus 800 according to an embodiment of the present invention, including:

the information analysis module 801 is configured to obtain transaction data of a target item in a current time period and a first time period according to an identifier of the target item; wherein the first time period is a historical time period which is separated from the current time period by a preset time interval;

a coefficient determining module 802, configured to obtain a value elasticity coefficient of the target item in the first time period, and determine the value elasticity coefficient of the target item in the current time period according to the transaction data and the value elasticity coefficient; wherein the value elasticity coefficient is the sensitivity of the article demand to the value attribute variation;

and a value attribute adjusting module 803, configured to adjust the value attribute of the target item in the current time period by using the determined value elasticity coefficient, so as to obtain an adjusted value attribute.

In the implementation device of the invention, the first time period is an initial time period during first calculation;

also included is an initial coefficient determination module 804 (not shown) for:

In the device for implementing the present invention, the initial coefficient determining module 804 is further configured to:

In the device for implementing the present invention, the coefficient determining module 804 is configured to:

In addition, the detailed implementation of the device in the embodiment of the present invention has been described in detail in the above method, so that the repeated description is not repeated here.

FIG. 9 illustrates an exemplary system architecture 900 to which embodiments of the invention may be applied.

As shown in fig. 9, the system architecture 900 may include

end devices

901, 902, 903, a network 904, and a server 905 (by way of example only). Network 904 is the medium used to provide communication links between

terminal devices

901, 902, 903 and server 905. Network 904 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

A user may use the

terminal devices

901, 902, 903 to interact with a server 905 over a network 904 to receive or send messages and the like. The

terminal devices

901, 902, 903 may have installed thereon various messenger client applications such as, for example only, a shopping-like application, a web browser application, a search-like application, an instant messaging tool, a mailbox client, social platform software, etc.

The

terminal devices

901, 902, 903 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The server 905 may be a server providing various services, such as a background management server (for example only) providing support for shopping websites browsed by users using the

terminal devices

901, 902, 903. The backend management server may analyze and perform other processing on the received data such as the product information query request, and feed back a processing result (for example, target push information, product information — just an example) to the terminal device.

It should be noted that the method for adjusting the value attribute of the article according to the embodiment of the present invention is generally executed by the server 905, and accordingly, the apparatus for adjusting the value attribute of the article is generally disposed in the server 905.

It should be understood that the number of terminal devices, networks, and servers in fig. 9 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

Referring now to FIG. 10, a block diagram of a computer system 1000 suitable for use with a terminal device implementing an embodiment of the invention is shown. The terminal device shown in fig. 10 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.

As shown in fig. 10, the computer system 1000 includes a Central Processing Unit (CPU)1001 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)1002 or a program loaded from a storage section 1008 into a Random Access Memory (RAM) 1003. In the RAM 1003, various programs and data necessary for the operation of the system 1000 are also stored. The CPU 1001, ROM 1002, and RAM 1003 are connected to each other via a bus 1004. An input/output (I/O) interface 1005 is also connected to bus 1004.

The following components are connected to the I/O interface 1005: an input section 1006 including a keyboard, a mouse, and the like; an output section 1007 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 1008 including a hard disk and the like; and a communication section 1009 including a network interface card such as a LAN card, a modem, or the like. The communication section 1009 performs communication processing via a network such as the internet. The driver 1010 is also connected to the I/O interface 1005 as necessary. A removable medium 1011 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 1010 as necessary, so that a computer program read out therefrom is mounted into the storage section 1008 as necessary.

In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication part 1009 and/or installed from the removable medium 1011. The computer program executes the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 1001.

It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor includes an information analysis module, a coefficient determination module, and a value attribute adjustment module. Where the names of these modules do not in some cases constitute a limitation on the module itself, for example, the coefficient determination module may also be described as a "module that determines a value elasticity coefficient for a current time period based on the sales volume information and the value elasticity coefficient for a previous time period".

As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise:

Compared with the prior art, the technical scheme of the embodiment of the invention has the following beneficial effects:

The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An article value attribute adjusting method, characterized by comprising:

2. The method of claim 1, wherein the first time period is an initial time period at a first calculation;

3. The method of claim 2, further comprising, after said obtaining a historical transaction record for said target item over a predetermined historical period of time:

4. The method according to any one of claims 1-3, wherein said determining a value elasticity coefficient for the target item at the current time period based on the transaction data and the value elasticity coefficient comprises:

5. An article value attribute adjusting apparatus, comprising:

6. The apparatus of claim 5, wherein the first time period is an initial time period when first calculated;

the apparatus further comprises an initial coefficient determination module to:

7. The apparatus of claim 6, wherein the initial coefficient determination module is further configured to:

8. The apparatus of any of claims 5-7, wherein the coefficient determination module is configured to:

9. An electronic device, comprising:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-4.

10. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-4.