CN116012086A

CN116012086A - Commodity price estimating method, commodity price estimating device, electronic equipment and storage medium

Info

Publication number: CN116012086A
Application number: CN202310093451.3A
Authority: CN
Inventors: 张涛; 周斌; 孙鑫焱; 龚涛
Original assignee: Shanghai Shizhuang Information Technology Co ltd
Current assignee: Shanghai Shizhuang Information Technology Co ltd
Priority date: 2023-02-02
Filing date: 2023-02-02
Publication date: 2023-04-25

Abstract

The embodiment of the invention discloses a commodity price evaluation method, a commodity price evaluation device, electronic equipment and a storage medium, and relates to the technical field of computers, wherein the commodity price evaluation method comprises the following steps: acquiring a selling request sent by user equipment, wherein the selling request comprises commodity attributes and selling prices of commodities to be sold; determining a target commodity set from a commodity database according to commodity attributes, and determining real-time characteristics about commodities to be sold according to the target commodity set; inputting the selling price and the real-time characteristics into a selling price evaluation model to obtain an evaluation result; and determining whether the selling price of the commodity to be sold is reasonable or not according to the evaluation result. According to the scheme provided by the embodiment, the characteristic change condition of the commodity to be sold is considered, so that when the selling price is estimated by using the selling price estimation model, the obtained estimation result is more accurate by combining the real-time characteristic, the accuracy of the estimation result is improved, and the beneficial effect of strictly controlling the commodity price is achieved.

Description

Commodity price estimating method, commodity price estimating device, electronic equipment and storage medium

Technical Field

The embodiment of the invention relates to a computer technology, in particular to a commodity price evaluation method, a commodity price evaluation device, electronic equipment and a storage medium.

Background

In the e-commerce field, there are cases where abnormal fluctuations occur in commodity prices due to the influence of social events, and sellers make malicious use of commodity prices in order to make a profit, and the like. Therefore, in order to maintain the trade order of the platform, the price of the commodity needs to be controlled so that the commodity can be sold on the platform according to a reasonable price.

The conventional scheme for evaluating the commodity price mainly adopts a time sequence method or a machine learning method, so that an evaluation interval about the commodity price is obtained, and the commodity price is further controlled in the evaluation interval. However, in the actual e-commerce environment, the price of the commodity is affected by multi-dimensional factors (such as supply-demand relationship and discussion heat), so that when the price is evaluated by the existing scheme, the problem of inaccurate management and control caused by incomplete consideration exists.

Disclosure of Invention

The embodiment of the invention provides a commodity price evaluation method, a commodity price evaluation device, electronic equipment and a storage medium, which can improve the existing scheme for evaluating commodity price.

In a first aspect, an embodiment of the present invention provides a method for evaluating a commodity price, including:

acquiring a selling request sent by user equipment, wherein the selling request comprises commodity attributes and selling prices of commodities to be sold;

Determining a target commodity set from a commodity database according to the commodity attribute, and determining real-time characteristics about the commodity to be sold according to the target commodity set;

and inputting the selling price and the real-time characteristics into a selling price evaluation model to obtain an evaluation result, and determining whether the selling price of the commodity to be sold is reasonable or not according to the evaluation result.

In a second aspect, an embodiment of the present invention provides an apparatus for evaluating a commodity price, the apparatus including:

the system comprises a request acquisition module, a vending module and a vending module, wherein the request acquisition module is used for acquiring a vending request sent by user equipment, and the vending request comprises commodity attributes and vending prices of commodities to be sold;

the feature determining module is used for determining a target commodity set from a commodity database according to the commodity attribute and determining real-time features of the commodity to be sold according to the target commodity set;

the result evaluation module is used for inputting the selling price and the real-time characteristics into a selling price evaluation model to obtain an evaluation result, and determining whether the selling price of the commodity to be sold is reasonable or not according to the evaluation result.

In a third aspect, an embodiment of the present invention further provides an electronic device, including:

At least one processor; and

a memory communicatively coupled to the at least one processor; wherein,,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of evaluating commodity prices according to any of the embodiments of the present invention.

In a fourth aspect, an embodiment of the present invention further provides a computer readable storage medium, where computer instructions are stored, where the computer instructions are configured to cause a processor to implement the method for evaluating a commodity price according to any one of the embodiments of the present invention.

According to the commodity price evaluation scheme provided by the embodiment of the invention, a selling request sent by user equipment is firstly obtained, wherein the selling request comprises commodity attributes and selling prices of commodities to be sold; then determining a target commodity set from a commodity database according to commodity attributes, and determining real-time characteristics about commodities to be sold according to the target commodity set; inputting the selling price and the real-time characteristics into a selling price evaluation model to obtain an evaluation result; and finally, determining whether the selling price of the commodity to be sold is reasonable or not according to the evaluation result. According to the scheme provided by the embodiment, the characteristic change condition of the commodity to be sold is considered, so that when the selling price is estimated by using the selling price estimation model, the obtained estimation result is more accurate by combining the real-time characteristic, the problem that consideration factors are not comprehensive when the selling price is estimated in the existing scheme is solved, the accuracy of the estimation result is improved, and the commodity price is convenient to strictly control.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of embodiments of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic flow chart of a commodity price assessment method according to an embodiment of the present invention;

FIG. 2 is another flow chart of a method for evaluating a price of a commodity according to an embodiment of the present invention;

FIG. 3 is a schematic flow chart of generating a sales price evaluation model according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of a commodity price estimating apparatus according to an embodiment of the present invention;

fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.

Fig. 1 is a schematic flow chart of a commodity price evaluation method according to an embodiment of the present invention, where the method may be performed by a commodity price evaluation device, the device may be implemented in hardware and/or software, and the device may be configured in a computer device such as a server. Referring to fig. 1, the method may specifically include the steps of:

S110, acquiring a selling request sent by the user equipment.

The vending request may be a request from a user clicking a preset button on an application integrated with the user device. The preset button may be "i want to sell" or "sell merchandise" and the like, and the manner of sending the sell request from the user device is not limited herein.

Wherein the vending request includes a commodity attribute and a vending price of the commodity to be vended. The current commodity attribute can be identified based on a picture identification technology after a commodity picture of the commodity to be sold is uploaded by a user; the related attributes of the commodities to be sold can be manually input for the user, and the commodity attributes obtained after the background manual verification can be obtained; the price for sale is the selling price desired by the user.

The above-mentioned commodity attributes may include commodity category of commodity to be sold, commodity brand, commodity co-name, commodity color, official selling price, etc., and the specific commodity attributes include contents without limitation.

Wherein, the commodity category indicates the category of the current commodity, and the current category can comprise shoes, clothes, bags, watches, cosmetics, accessories and the like.

S120, determining a target commodity set from a commodity database according to commodity attributes, and determining real-time characteristics about commodities to be sold according to the target commodity set.

The commodity database can be a database of all commodity components sold on the e-commerce platform. The commodity database can be used for managing the commodities in the commodity database in a distributed storage mode so as to be convenient for managing the commodities.

When the target commodity set is determined from the commodity database according to the commodity attributes, the current target commodity set may include a plurality of target commodity sets. Illustratively, taking the example that the commodity attribute includes a commodity type, a commodity brand and a commodity model, a first target commodity set about the commodity type can be determined, a second target commodity set about the commodity brand can be determined, and a third target commodity set about the commodity brand can be determined; wherein the commodity number of the first target commodity set is larger than the commodity number of the second target commodity set is larger than the commodity number of the third target commodity set. The number of sets of target commodity sets specifically determined is not limited herein, and corresponds to the hierarchical granularity of commodity attributes.

When the target commodity sets are determined from the commodity database according to commodity attributes, the corresponding characteristics of each target commodity set are determined according to the related commodity information of the target commodity sets, which is acted on the target commodity sets, so that the corresponding characteristics of each target commodity set are used for representing the real-time characteristics of the commodities to be sold currently. Therefore, in order to make the commodities in the target commodity set representative while reducing the analysis of the amount of useless data, commodity data in a first preset period of time may be acquired from the commodity database as the target commodity set according to the commodity attribute.

The first preset time period may be the last week, two weeks, or one month, etc., and the selection of the specific preset time period is not limited herein.

Optionally, the number of goods contained in each target data set is plural, and the goods contained in each target data set may include successfully transacted goods and unsuccessfully transacted goods according to transaction types. The successful transaction commodity representation platform allows the transaction to be carried out on the platform according to the current selling price after auditing the selling price of the target commodity by the seller, and the commodity is successfully sold; the unsuccessful transaction commodity can be a commodity which is not checked successfully by a platform because the selling price of a seller is too high, and is not allowed to be sold, or can be a commodity which is checked by the platform and is allowed to be transacted on the platform according to the current selling price but is not successfully sold after the selling price of the target commodity is checked by the seller. The transaction types of the goods contained in each target data set are not limited herein. The purpose of this is to be able to obtain more transaction characteristics about the current commodity for sale, facilitating a comprehensive assessment of the selling price of the commodity for sale in a subsequent step.

When the real-time characteristics about the commodities to be sold are determined according to the target commodity sets, the current real-time characteristics can be the successful transaction price, the sale price, the official sale price of all the transaction commodities in each target commodity set, the corresponding transaction price characteristics, sale price characteristics, price change characteristics and the like about each target commodity set; further, real-time characteristics about the commodity to be sold can be determined according to the corresponding price-forming characteristics, price-selling characteristics and price-changing characteristics of each target commodity set, and the current real-time characteristics can reflect the price-changing trend of the commodity to be sold.

S130, inputting the selling price and the real-time characteristics into a selling price evaluation model to obtain an evaluation result, and determining whether the selling price of the commodity to be sold is reasonable or not according to the evaluation result.

The selling price evaluation model is a model obtained by training the related data of the transaction commodity corresponding to all commodity categories in the commodity database.

After the selling price and the real-time characteristics are input into the selling price evaluation model, the obtained evaluation result can be a result of whether the current selling price is reasonable or not, and if the selling price accords with the change trend of the real-time characteristics, the selling price evaluation result of the commodity to be sold can be reasonable or pass; if the price is not met, for example, the price is too high to meet the change trend of the real-time feature, the price evaluation result of the commodity to be sold may be "unreasonable" or "failed".

Optionally, the evaluation result output by the selling price evaluation model is not limited by the above example, but may be a probability value about the current selling price abnormality, and when the probability value exceeds a preset value, the selling price abnormality of the current commodity to be sold may be evaluated, without passing the selling request of the user; when the probability value does not exceed the preset value, the selling price of the current commodity to be sold can be estimated to be normal, and the user is allowed to sell the current commodity on the platform through the selling request of the user.

The predetermined value may be 0.5, 0.6 or 0.8, and the specific predetermined value is not limited herein.

The commodity price evaluation method provided by the embodiment of the invention comprises the steps of firstly, obtaining a selling request sent by user equipment, wherein the selling request comprises commodity attributes and selling prices of commodities to be sold; then determining a target commodity set from a commodity database according to commodity attributes, and determining real-time characteristics about commodities to be sold according to the target commodity set; inputting the selling price and the real-time characteristics into a selling price evaluation model to obtain an evaluation result; and finally, determining whether the selling price of the commodity to be sold is reasonable or not according to the evaluation result. According to the scheme provided by the embodiment, the characteristic change condition of the commodity to be sold is considered, so that when the selling price is estimated by using the selling price estimation model, the obtained estimation result is more accurate by combining the real-time characteristic, the problem that consideration factors are not comprehensive when the selling price is estimated in the existing scheme is solved, the accuracy of the estimation result is improved, and the commodity price is convenient to strictly control.

Fig. 2 is another flow chart of a commodity price evaluation method according to an embodiment of the present invention, where the relationship between the present embodiment and the above embodiment further refines the corresponding features of the above embodiment. As shown in fig. 2, the method may include the steps of:

s210, acquiring a selling request sent by user equipment.

The vending request includes a merchandise attribute and a vending price of the merchandise to be vended.

S220, determining a first-level target commodity set corresponding to the first-level attribute from the commodity database, determining a second-level target commodity set corresponding to the second-level attribute from the first-level target commodity set, and determining a third-level target commodity set corresponding to the third-level attribute from the second-level target commodity set.

The commodity attributes include a primary attribute, a secondary attribute, and a tertiary attribute. Wherein the commodity database comprises a plurality of primary attributes, and the current primary attributes can comprise footwear, clothing, luggage, watch, cosmetic, accessory and the like; including a plurality of secondary attributes in each primary attribute, the secondary attributes included in current footwear may be, for example, brand a, brand B, brand C, brand D, etc.; a plurality of tertiary attributes are included in each secondary attribute, and illustratively, the tertiary attributes included in the current a model may be series, color, size, number, and the like.

Optionally, to further facilitate classification management of commodities in the commodity database, taking footwear as an example, the current secondary attribute may also be sports, leisure, business, home, etc.; further, the current secondary attribute can also comprise a plurality of tertiary attributes, and the current tertiary attribute can be brand A, brand B, brand C, brand D and the like; further, the current three-level attribute may further include a plurality of four-level attributes, and for example, the four-level attributes included in the current a model may be color, size, number, and the like. The types of attributes contained in the specific merchandise database, as well as the specific attribute content contained in each attribute type, are not limited herein.

Taking the example of the footwear with the commodity attribute of the commodity to be sold being red, 37 codes and the brand being A in the selling request sent by the user, the current primary target attribute is footwear, the secondary target attribute is A brand, and the tertiary target attribute is 37 codes and red; the corresponding first-level target commodity set, second-level target commodity set and third-level target commodity set can be determined in the first-level attribute, second-level attribute and third-level attribute of the commodity database according to the current first-level target attribute, second-level target attribute and third-level target attribute. The number of commodities contained in the first-level target commodity set, the second-level target commodity set and the third-level target commodity set is reduced step by step, and the commodity attribute contained in the third-level target commodity set is identical to the commodity attribute of the commodity to be sold, namely the commodity contained in the third-level target commodity set is the commodity set of the current commodity to be sold which is traded in a historical time period.

S221, obtaining a target commodity set according to the first-level target commodity set, the second-level target commodity set and the third-level target commodity set.

The first-level target attribute is taken as shoes, the second-level target attribute is taken as a brand A, the third-level target attribute is taken as a 37-code and red example, and a shoe set in a commodity database can be taken as a first-level target commodity set; the brand set A is used as a secondary target commodity set; the 37 codes and the red color are used as the three-level target commodity set, so that the target commodity set is obtained according to the first-level target commodity set, the second-level target commodity set and the three-level target commodity set.

Optionally, when a specific commodity cannot be located in the three-level attribute included in the commodity database, the commodity database may include four-level attributes, five-level attributes, and the like, and the attribute level included in the specific commodity database is not limited herein, so long as the target commodity with the same commodity attribute as the commodity to be sold can be found in the attribute level with the finest granularity.

And S230, calculating commodity information corresponding to each historical transaction commodity in the primary target commodity set, the secondary target commodity set and the tertiary target commodity set respectively to obtain primary target transaction characteristics, secondary target transaction characteristics and tertiary target transaction characteristics.

The commodity information may include official sales prices, historical transaction prices, and historical outgoing sales prices.

Calculating commodity information corresponding to each historical transaction commodity in the primary target commodity set, wherein the mode of obtaining primary target transaction characteristics can be as follows: obtaining primary target price characteristics according to the change trend of historical price of each historical transaction commodity in the primary target commodity set; obtaining primary target selling price characteristics according to the change trend of the historical selling price of each historical transaction commodity in the primary target commodity set; and obtaining a first-level price change characteristic according to the price difference change trend of the official selling price and the historical transaction price corresponding to each historical transaction commodity.

The change trend of the price, and the change trend of the price difference may be obtained by calculating the maximum value, the average value, and the 95-bit price of each historical transaction commodity, and the specific manner of determining the change trend of the price is not limited herein.

Correspondingly, in the step of calculating the commodity information corresponding to each historical transaction commodity in the secondary target commodity set to obtain the secondary target transaction characteristic, and in the step of calculating the commodity information corresponding to each historical transaction commodity in the tertiary target commodity set, the mode of obtaining the tertiary target transaction characteristic is the same as the mode of obtaining the primary target transaction characteristic, and details are omitted herein.

In summary, according to the scheme provided in this embodiment, the first-level target transaction feature includes: primary target price-forming characteristics, primary target price-selling characteristics and primary price-changing characteristics; the secondary target transaction characteristics include: a secondary target price-forming feature, a secondary target price-selling feature, and a secondary price-changing feature; the three-level target transaction feature includes: three-level target price-forming characteristics, three-level target price-selling characteristics and three-level price-changing characteristics.

Optionally, in order to reduce the data calculation amount in the subsequent step and accelerate the response speed of the server, the feature extraction can be further performed again on the primary target transaction feature, the secondary target transaction feature and the tertiary target transaction feature respectively, so that each target commodity set corresponds to one transaction feature and the like. The data content contained in the specific primary target transaction characteristic, secondary target transaction characteristic, and tertiary target transaction characteristic is not limited herein.

S231, acquiring successful transaction commodities in a preset time period from the three-level target commodity set, and constructing successful transaction characteristics according to commodity information corresponding to the successful transaction commodities.

In order to make the obtained real-time characteristics more consistent with the change trend of the commodities to be sold, when the successful transaction characteristics are constructed according to the commodity information of the successful transaction commodities, the current successful transaction characteristics can comprise historical transaction characteristics and historical bidding characteristics.

One implementation, the manner of constructing the historical transaction characteristics according to the merchandise information of the successfully transacted merchandise may be: acquiring the bargain price of each successful trade commodity in the three-level target commodity set based on a preset time period, and calculating the bargain price characteristic of the current successful trade commodity according to the bargain price; constructing attention weights related to the price characteristics of the deals according to the selling price and the deals corresponding to each successfully-traded commodity; and obtaining the historical transaction characteristics of the successfully transacted commodity according to the attention weight, the selling price and the transaction price characteristics.

Accordingly, the manner in which the historical bidding features are constructed from the merchandise information of successfully transacted merchandise may be: acquiring the selling price of each commodity successfully transacted in the three-level target commodity set based on a preset time period, and calculating the selling price characteristic of the commodity successfully transacted at present according to the selling price; constructing attention weights related to the characteristics of the selling prices according to the selling prices and the bargain prices corresponding to each successfully-traded commodity; historical bidding features of successfully transacted goods are obtained based on the attention weight, the price for sale, and the price for sale feature.

The predetermined time period may be one week, two weeks, or one month, and the selection of the specific predetermined time period is not limited herein.

S232, calculating the primary target transaction characteristic, the secondary target transaction characteristic, the tertiary target transaction characteristic and the successful transaction characteristic to obtain the real-time characteristic of the commodity to be sold.

In the current step, the manner of calculating the real-time characteristics of the commodity to be sold may be to divide weights for the primary target transaction characteristics, the secondary target transaction characteristics, the tertiary target transaction characteristics and the successful transaction characteristics based on the time sequence characteristics, and to obtain the real-time characteristics of the commodity to be sold in combination with a preset algorithm.

The preset algorithm may be a statistical method or linear transformation, and the selection of the specific preset algorithm is not limited herein.

S240, inputting the selling price and the real-time characteristics into a selling price evaluation model to obtain an evaluation result, and determining whether the selling price of the commodity to be sold is reasonable or not according to the evaluation result.

Referring to fig. 3, fig. 3 is a schematic flow chart of generating a sales price evaluation model according to an embodiment of the invention; the sales price evaluation model provided in this embodiment may be generated as follows:

s310, acquiring a training data set.

The training data set includes at least one category of merchandise, each category of merchandise including at least one historical transaction merchandise. Optionally, each item category includes at least one item type, and each item type includes at least one historical transaction item.

The above-mentioned commodity categories may include all commodity categories sold on an e-commerce platform, and may include, for example, footwear, apparel, luggage, watches, make-up, accessories, and the like; the merchandise type may indicate a corresponding brand of merchandise on the current merchandise category; the historical transaction merchandise indicates that the merchandise contained in each merchandise category is transacted at a historical time, and the current historical transaction merchandise may be a successful transaction merchandise or an unsuccessful transaction merchandise, and the type of the specific historical transaction merchandise is not limited herein.

S320, calculating commodity information of each historical transaction commodity to obtain offline characteristics of each commodity category.

The commodity information includes official selling prices, historical transaction prices and historical outgoing selling prices.

Optionally, where each item category includes at least one item type, each item type includes at least one historically transacted item, the offline feature of each item category may include the offline feature of the corresponding item type. The current step may be implemented as: calculating commodity information of each historical transaction commodity to obtain offline characteristics of each commodity type; and calculating the offline characteristics of each commodity type to obtain the offline characteristics of the corresponding commodity type.

The offline characteristics for each commodity type may include a historical price-in characteristic, a historical price-out characteristic, and a historical price change characteristic. The historical price feature is obtained according to the actual price of each commodity; the historical selling price characteristics are obtained according to selling prices input by a user on user equipment when each commodity is sold; the historical price change characteristics are obtained according to the corresponding selling price and actual bargain price of each commodity.

In one implementation, the current step calculates the commodity information of each historical transaction commodity, and the offline characteristic of each commodity type can be obtained by the following ways:

acquiring a first-level commodity set, a second-level commodity set and a third-level commodity set contained in each commodity category; calculating primary transaction characteristics, secondary transaction characteristics and tertiary transaction characteristics corresponding to each commodity type according to official selling prices, historical transaction prices and historical outgoing selling prices corresponding to each historical transaction commodity of the primary commodity set, the secondary commodity set and the tertiary commodity set respectively; and obtaining the offline characteristic of each commodity category according to the primary transaction characteristic, the secondary transaction characteristic and the tertiary transaction characteristic.

In the commodity database, the number of the included historical transaction commodities is massive, so that the trained selling price evaluation model is suitable for evaluating selling prices of any commodity. Therefore, according to the scheme provided by the embodiment, when the selling price evaluation model is trained, the selected commodity data contains commodity information corresponding to all commodity types.

The difference between the process of calculating the primary transaction characteristic, the secondary transaction characteristic and the tertiary transaction characteristic corresponding to each commodity type in the current step and the process of calculating the primary target transaction characteristic, the secondary target transaction characteristic and the tertiary target transaction characteristic corresponding to each historical transaction commodity in the step S230 is that the step S230 is to obtain and determine the primary target commodity set, the secondary target commodity set and the tertiary target commodity set under the condition that the attribute of the commodity to be sold is known; and the current step is used for classifying all the data in the database, and then respectively calculating a first-level commodity set, a second-level commodity set and a third-level commodity set of each historical transaction commodity in each commodity type, wherein the subsequent calculation process is the same and is not described in detail herein.

Accordingly, in the present embodiment, the process of obtaining the offline characteristic of each commodity type according to the primary transaction characteristic, the secondary transaction characteristic and the tertiary transaction characteristic is the same as the process of obtaining the real-time characteristic of the commodity for sale in step S231, and will not be described herein.

S330, respectively constructing historical successful transaction characteristics and historical successful bidding characteristics according to commodity information included in each commodity category.

In a preferred embodiment, the historical successful transaction characteristics include a transaction difference characteristic and a transaction multiplier characteristic; in the current step, the construction of the historical successful transaction characteristic according to the commodity information included in each commodity class can be realized by the following modes:

a) And acquiring the historical transaction price of each historical transaction commodity in the target commodity category based on a preset period, and calculating the transaction price characteristic of the target commodity type according to the historical transaction price.

The target commodity type is any commodity type in the target commodity type; the target commodity is any commodity in the training data set.

The historical price of the commodity order of the same type per day can be calculated according to the historical price of the commodity order of the commodity recorded in the electronic commerce platform, so that the price characteristics of the commodity of the target type can be calculated.

The current deal price characteristics may include maximum, average, and 95-point prices, crowd values, median values, etc. for the deal price. The content contained in the specific exchange price feature is not limited herein.

When the transaction difference feature and the transaction multiple feature of the same type of commodity are calculated later, the corresponding description is made by taking the transaction price feature including the maximum value, the average value and the 95-bit price of the transaction price as examples.

Selecting order transaction records in a preset period, wherein the current preset period is represented by T= [ T ] ₁ ,t ₂ ,t ₃ ,…,t]For example, a trade price maximum series p for the same type of commodity over a period T may be constructed _max Average value sequence p of trade prices _agv And trade 95 quantile price sequence p ₉₅ Tool for cleaning and cleaningThe volume may be represented as follows:

b) And constructing attention weights related to the feature of the transaction price according to the historical sale price and the historical transaction price corresponding to each historical transaction commodity.

The historical selling price is the price that the seller places for each item when sold on the e-commerce platform.

When the price feature of the deal provided in this embodiment includes the maximum value, the average value and the 95-bit price, the attention weight related to the price feature of the deal is constructed, namely, the maximum value and the historical selling price p are constructed _c Attention weight a of (2) _m Building average and historical sales price p _c Attention weight a of (2) _agv Construction of 95-position price and historical sales price p _c Attention weight a of (2) ₉₅ Specifically, the method can be represented by the following modes:

c) And obtaining the transaction difference value characteristic and the transaction multiple characteristic of the target commodity type according to the attention weight, the historical selling price and the transaction price characteristic.

The transaction difference characteristic indicates the relationship between the transaction price characteristic and the historical selling price, and the current day maximum difference characteristic f can be obtained by the following method _m Difference of current day mean characteristic f _avg And 95-degree price difference feature f ₉₅ ：

f _m ＝A _m *[|p _c -p _m,t1 |,|p _c -p _m,t2 |,…,|p _c -p _m,t |] (7)

f _avg ＝A _avg *[|p _c -p _avg,t1 |,|p _c -p _avg,t2 |,…,|p _c -p _avg,t |] (8)

f ₉₅ ＝A ₉₅ *[|p _c -p _95,t1 |,|p _c -p _95,t2 |,…,|p _c -p _95,t |] (9)

The trade multiple feature indicates the multiple relation of the trade price feature and the historical selling price, so as to further judge the price change trend. The characteristic f of the maximum multiple of the current day can be obtained by the following method _m,r Mean multiple of day feature f _avg,r And 95-degree price sharing multiple feature f on the same day _95,r ：

f _m,r ＝A _m *[p _c /p _m,t1 ,p _c /p _m,t2 ,…,p _c /p _m,t ] (10)

f _avg,r ＝A _avg *[p _c /p _avg,t1 ,p _c /p _agv,t2 ,…,p _c /p _agv,t ] (11)

f _95,r ＝A ₉₅ *[p _c /p _95,t1 ,p _c /p _95,t2 ,…,p _c /p _95,t ] (12)

The transaction difference characteristic and the transaction multiple characteristic of the same type of commodity in a preset period can be obtained through the formula (7) -the formula (9) and the formula (10) -the formula (12).

Correspondingly, when the historical successful bidding features are built according to commodity information included in each commodity type in the current step, the historical successful bidding features comprise bidding difference features and bidding multiple features.

Specifically, according to the seller history successful bid records recorded in the e-commerce platform, the maximum value, the average value and the 95-level price of the successful bid price of the seller of the same type of commodity every day are calculated, and further according to the steps a) -c) included in the step S330, the bid difference feature and the bid multiple feature of the same type of commodity are obtained in the same manner, and the detailed implementation process is not described herein.

S340, acquiring the commodity label of each historical transaction commodity.

When analyzing the commodities in the training set, each commodity comprises a commodity label which is used for indicating whether the current commodity belongs to abnormal bidding in historical transaction. Illustratively, the current commodity label can be represented by 0 and 1, if the commodity label of the current commodity is 0, the historical transaction is indicated as normal bidding; if the commodity label of the current commodity is 1, the historical transaction is indicated to be abnormal bidding.

In one embodiment, the acquisition of the merchandise tag for each historically transacted merchandise may be accomplished by:

constructing a fluctuation factor about historical transaction commodities; and determining the commodity label of the historical transaction commodity according to the fluctuation factor, commodity information and the sales price of the competition platform.

Regarding the commodity which is successfully traded in history, when the user sells the current commodity, the relationship between the price of the commodity with the same type and the price of the commodity with the official business is kept to float in a certain range, if the current floating range is not exceeded, the commodity label which normally bids on the current commodity is marked; if the current floating range is exceeded, further acquiring a floating factor of the commodity in the current transaction, wherein the fluctuation factor comprises commodity stock quantity and commodity heat clicking quantity; if the current commodity stock is less and/or the commodity discussion heat is higher, the current selling price of the user exceeds the floating range, and further referring to the selling price of the competitive platform, if the current selling price and the selling price of the competitive platform are within a reasonable range, the normal bidding can be marked; if the current commodity stock quantity or commodity discussion heat does not meet the fluctuation condition, the commodity stock quantity or commodity discussion heat is marked as abnormal bidding.

S350, training a preset decision tree algorithm according to the offline characteristics, the historical successful transaction characteristics, the historical successful bid characteristics and the commodity labels to generate a selling price evaluation model.

The method comprises the steps of taking offline characteristics, historical successful transaction characteristics, historical successful bidding characteristics and commodity labels as training samples, presetting sample labels of all training samples, inputting all training samples into a preset decision tree algorithm, extracting relevant characteristic data about commodity transaction prices, and finally outputting transverse control deviation data related to the next moment through an output layer of a model. And then comparing sample labels corresponding to the training samples after the evaluation results are output each time to judge the accuracy of the current training of the model until the output results are within an error range after the relevant test data are input to the model, namely the difference loss between the final output results and the sample labels of the training samples reaches a certain convergence, and then indicating that the current selling price evaluation model is trained.

According to the commodity price evaluation method provided by the embodiment of the invention, when the selling price evaluation model is constructed, the time sequence difference value characteristic and the time sequence multiple characteristic based on attention weight are designed by taking the change characteristics of historical price and successful selling price into consideration, and the difference information and the multiple information of recent bidding are fully considered, so that the fluctuation condition of the bidding of the mined commodity is facilitated. And the judgment of abnormal bidding is introduced through the commodity label, so that the accuracy of the sales price evaluation model for identifying abnormal bidding commodities can be improved.

Fig. 4 is a schematic structural diagram of a commodity price estimating apparatus according to an embodiment of the present invention, where the apparatus is adapted to execute the commodity price estimating method according to the embodiment of the present invention. As shown in fig. 4, the apparatus may specifically include: a request acquisition module 410, a feature determination module 420, and a result evaluation module 430; wherein:

a request obtaining module 410, configured to obtain a vending request sent by a user device, where the vending request includes a commodity attribute and a vending price of a commodity to be vended;

a feature determining module 420, configured to determine a target commodity set from a commodity database according to the commodity attribute, and determine real-time features about the commodity for sale according to the target commodity set;

the result evaluation module 430 is configured to input the selling price and the real-time feature to a selling price evaluation model, obtain an evaluation result, and determine whether the selling price of the commodity for sale is reasonable according to the evaluation result.

The commodity price evaluation device provided by the embodiment of the invention firstly obtains a selling request sent by user equipment, wherein the selling request comprises commodity attributes and selling prices of commodities to be sold; then determining a target commodity set from a commodity database according to commodity attributes, and determining real-time characteristics about commodities to be sold according to the target commodity set; inputting the selling price and the real-time characteristics into a selling price evaluation model to obtain an evaluation result; and finally, determining whether the selling price of the commodity to be sold is reasonable or not according to the evaluation result. According to the scheme provided by the embodiment, the characteristic change condition of the commodity to be sold is considered, so that when the selling price is estimated by using the selling price estimation model, the obtained estimation result is more accurate by combining the real-time characteristic, the problem that consideration factors are not comprehensive when the selling price is estimated in the existing scheme is solved, the accuracy of the estimation result is improved, and the commodity price is convenient to strictly control.

In one embodiment, the commodity attributes include a primary attribute, a secondary attribute, and a tertiary attribute;

the feature determination module 420 includes: a commodity set determining unit and a commodity set obtaining unit, wherein:

the commodity set determining unit is used for determining a first-level target commodity set corresponding to the first-level attribute from the commodity database, determining a second-level target commodity set corresponding to the second-level attribute from the first-level target commodity set, and determining a third-level target commodity set corresponding to the third-level attribute from the second-level target commodity set;

and the commodity set obtaining unit is used for obtaining the target commodity set according to the primary target commodity set, the secondary target commodity set and the tertiary target commodity set.

In one embodiment, the feature determination module 420 further includes: an information calculation unit, a feature construction unit, and a first feature calculation unit, wherein:

the information calculation unit is used for calculating commodity information corresponding to each historical transaction commodity in the primary target commodity set, the secondary target commodity set and the tertiary target commodity set respectively to obtain primary target transaction characteristics, secondary target transaction characteristics and tertiary target transaction characteristics;

The characteristic construction unit is used for acquiring successful transaction commodities in a preset time period from the three-level target commodity set and constructing successful transaction characteristics according to the transaction information of the successful transaction commodities;

the first feature calculation unit is used for calculating the primary target transaction feature, the secondary target transaction feature, the tertiary target transaction feature and the successful transaction feature to obtain the real-time feature of the commodity to be sold.

In one embodiment, the apparatus further comprises: the system comprises a data acquisition module, an information calculation module, a feature construction module, a label acquisition module and a model generation module, wherein:

the data acquisition module is used for acquiring a training data set, wherein the training data set comprises at least one commodity category, and each commodity category comprises at least one historical transaction commodity;

the information calculation module is used for calculating commodity information of each historical transaction commodity to obtain offline characteristics of each commodity category;

the characteristic construction module is used for respectively constructing historical successful transaction characteristics and historical successful bidding characteristics according to commodity information included in each commodity category;

the tag acquisition module is used for acquiring a commodity tag of each historical transaction commodity, and the commodity tag is used for indicating whether the current commodity belongs to abnormal bidding in the historical transaction;

And the model generation module is used for training a preset decision tree algorithm according to the offline characteristic, the historical successful transaction characteristic, the historical successful bid characteristic and the commodity label of each commodity category to generate the selling price evaluation model.

In one embodiment, the merchandise information includes official selling prices, historical transaction prices, and historical outgoing selling prices;

the information calculation module includes: the system comprises a commodity set acquisition unit, a second characteristic calculation unit and an offline characteristic acquisition unit, wherein:

the commodity set acquisition unit is used for acquiring a primary commodity set, a secondary commodity set and a tertiary commodity set contained in each commodity category;

the second feature calculation unit is used for calculating primary transaction features, secondary transaction features and tertiary transaction features corresponding to each commodity type according to the official selling price, the historical transaction price and the historical selling price corresponding to each historical transaction commodity of the primary commodity set, the secondary commodity set and the tertiary commodity set respectively;

and the offline characteristic obtaining unit is used for obtaining the offline characteristic of each commodity category according to the primary transaction characteristic, the secondary transaction characteristic and the tertiary transaction characteristic.

In one embodiment, the historical successful transaction characteristics include a transaction difference characteristic and a transaction multiplier characteristic; the commodity category includes at least one commodity type, each commodity type including at least one of the historical transaction commodities;

the feature construction module comprises: price characteristic calculating unit, weight constructing unit and transaction characteristic obtaining unit, wherein:

the price characteristic calculation unit is used for acquiring the historical transaction price of each historical transaction commodity in a target commodity type based on a preset period, and calculating the transaction price characteristic of the target commodity type according to the historical transaction price, wherein the target commodity type is any commodity type in the commodity categories;

a weight construction unit, configured to construct an attention weight related to the feature of the transaction price according to the historical sales price and the historical transaction price corresponding to each of the historical transaction commodities;

and a transaction characteristic obtaining unit configured to obtain the transaction difference characteristic and the transaction multiple characteristic of the target commodity type according to the attention weight, the historical selling price and the transaction price characteristic.

In one embodiment, the tag acquisition module includes: a fluctuation factor construction unit and a commodity label determination unit, wherein:

A fluctuation factor construction unit for constructing a fluctuation factor concerning the history transaction commodity, the fluctuation factor including a commodity stock quantity and a commodity heat click quantity;

and the commodity label determining unit is used for determining the commodity label of the historical transaction commodity according to the fluctuation factor, the commodity information and the sales price of the competition platform.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional modules is illustrated, and in practical application, the above-described functional allocation may be performed by different functional modules according to needs, i.e. the internal structure of the apparatus is divided into different functional modules to perform all or part of the functions described above. The specific working process of the functional module described above may refer to the corresponding process in the foregoing method embodiment, and will not be described herein.

The embodiment of the invention also provides electronic equipment, which comprises: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of evaluating commodity prices according to any of the embodiments of the present invention.

The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores computer instructions, and the computer instructions are used for enabling a processor to implement the commodity price assessment method according to any embodiment of the invention when being executed.

Referring now to FIG. 5, there is illustrated a schematic diagram of a computer system 500 suitable for use in implementing an electronic device of an embodiment of the present invention. The electronic device shown in fig. 5 is only an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

As shown in fig. 5, the computer system 500 includes a Central Processing Unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the system 500 are also stored. The CPU 501, ROM 502, and RAM 503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.

The following components are connected to the I/O interface 505: an input section 506 including a keyboard, a mouse, and the like; an output portion 507 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker, and the like; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The drive 510 is also connected to the I/O interface 505 as needed. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as needed so that a computer program read therefrom is mounted into the storage section 508 as needed.

In particular, according to embodiments of the present disclosure, the processes described above with reference to 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 shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 509, and/or installed from the removable media 511. The above-described functions defined in the system of the present invention are performed when the computer program is executed by a Central Processing Unit (CPU) 501.

The computer readable medium shown in the present invention may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any 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 context of this document, 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, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. 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 flowcharts 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 and/or units involved in the embodiments of the present invention may be implemented in software, or may be implemented in hardware. The described modules and/or units may also be provided in a processor, e.g., may be described as: a processor includes a request acquisition module, a feature determination module, and a result evaluation module. The names of these modules do not constitute a limitation on the module itself in some cases.

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 present alone without being fitted into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to include: acquiring a selling request sent by user equipment, wherein the selling request comprises commodity attributes and selling prices of commodities to be sold; determining a target commodity set from a commodity database according to the commodity attribute, and determining real-time characteristics about the commodity to be sold according to the target commodity set; and inputting the selling price and the real-time characteristics into a selling price evaluation model to obtain an evaluation result, and determining whether the selling price of the commodity to be sold is reasonable or not according to the evaluation result.

According to the technical scheme provided by the embodiment of the invention, the characteristic change condition of the commodity to be sold is considered, so that when the selling price is estimated by using the selling price estimation model, the obtained estimation result is more accurate by combining the real-time characteristic, the problem that consideration factors are not comprehensive when the selling price is estimated in the existing scheme is solved, the accuracy of the estimation result is improved, and the beneficial effect of strictly controlling the commodity price is achieved.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives can occur depending upon design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. A method of evaluating a commodity price, comprising:

2. The method of claim 1, wherein the commodity attributes comprise a primary attribute, a secondary attribute, and a tertiary attribute;

the determining the target commodity set from the commodity database according to the commodity attribute comprises the following steps:

Determining a first-level target commodity set corresponding to the first-level attribute from the commodity database, determining a second-level target commodity set corresponding to the second-level attribute from the first-level target commodity set, and determining a third-level target commodity set corresponding to the third-level attribute from the second-level target commodity set;

and obtaining the target commodity set according to the first-level target commodity set, the second-level target commodity set and the third-level target commodity set.

3. The method of claim 2, wherein said determining real-time characteristics about said commodity for sale from said target commodity set comprises:

calculating commodity information corresponding to each historical transaction commodity in the primary target commodity set, the secondary target commodity set and the tertiary target commodity set respectively to obtain primary target transaction characteristics, secondary target transaction characteristics and tertiary target transaction characteristics;

acquiring successful transaction commodities in a preset time period from the three-level target commodity set, and constructing successful transaction characteristics according to commodity information corresponding to the successful transaction commodities;

and calculating the primary target transaction characteristic, the secondary target transaction characteristic, the tertiary target transaction characteristic and the successful transaction characteristic to obtain the real-time characteristic of the commodity to be sold.

4. The method of claim 1, wherein the sales price assessment model is generated by:

acquiring a training data set, wherein the training data set comprises at least one commodity category, and each commodity category comprises at least one historical transaction commodity;

calculating commodity information of each historical transaction commodity to obtain offline characteristics of each commodity category;

respectively constructing historical successful transaction characteristics and historical successful bidding characteristics according to commodity information included in each commodity category;

acquiring commodity labels of each historical transaction commodity, wherein the commodity labels are used for indicating whether the current commodity belongs to abnormal bidding in the historical transaction;

and training a preset decision tree algorithm according to the offline characteristic, the historical successful transaction characteristic, the historical successful bid characteristic and the commodity label of each commodity category to generate the selling price evaluation model.

5. The method of claim 4, wherein the merchandise information includes official sales prices, historical transaction prices, and historical outgoing sales prices;

calculating the commodity information of each historical transaction commodity to obtain the offline characteristic of each commodity category, wherein the method comprises the following steps:

Acquiring a primary commodity set, a secondary commodity set and a tertiary commodity set contained in each commodity category;

calculating primary transaction characteristics, secondary transaction characteristics and tertiary transaction characteristics corresponding to each commodity type according to the official selling price, the historical transaction price and the historical sale price corresponding to each historical transaction commodity of the primary commodity set, the secondary commodity set and the tertiary commodity set respectively;

and obtaining the offline characteristic of each commodity category according to the primary transaction characteristic, the secondary transaction characteristic and the tertiary transaction characteristic.

6. The method of claim 4, wherein the historical successful transaction signature comprises a transaction difference signature and a transaction multiplier signature; the commodity category includes at least one commodity type, each commodity type including at least one of the historical transaction commodities;

the construction of the historical successful transaction feature according to the commodity information included in each commodity category comprises the following steps:

acquiring a historical transaction price of each historical transaction commodity in a target commodity type based on a preset period, and calculating a transaction price characteristic of the target commodity type according to the historical transaction price, wherein the target commodity type is any commodity type in the commodity categories;

Constructing attention weights related to the transaction price characteristics according to the historical sales price and the historical transaction price corresponding to each historical transaction commodity;

and obtaining the transaction difference value characteristic and the transaction multiple characteristic of the target commodity type according to the attention weight, the historical selling price and the transaction price characteristic.

7. The method of claim 4, wherein said obtaining a merchandise tag for each of said historically transacted merchandise comprises:

constructing a fluctuation factor about the historical transaction commodity, wherein the fluctuation factor comprises commodity stock quantity and commodity heat clicking quantity;

and determining the commodity label of the historical transaction commodity according to the fluctuation factor, the commodity information and the sales price of the competition platform.

8. An apparatus for evaluating a commodity price, comprising:

9. An electronic device, the electronic device comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of evaluating commodity prices according to any of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements a method of evaluating a commodity price according to any one of claims 1 to 7.