CN112884520A

CN112884520A - Object processing method, device, electronic equipment, storage medium and program product

Info

Publication number: CN112884520A
Application number: CN202110257385.XA
Authority: CN
Inventors: 李蕾; 张逾; 许天涵
Original assignee: Lazas Network Technology Shanghai Co Ltd
Current assignee: Lazas Network Technology Shanghai Co Ltd
Priority date: 2021-03-09
Filing date: 2021-03-09
Publication date: 2021-06-01

Abstract

The embodiment of the disclosure discloses an object processing method, an object processing device, an electronic device, a storage medium and a program product, wherein the object processing method comprises the following steps: obtaining multi-dimensional candidate objects in a preset area to form a candidate object set; calculating a multi-dimensional space-time contribution score of the candidate object to a target entity, wherein the multi-dimensional space-time contribution score is used for representing the contribution degree of the candidate object to the target entity in multi-dimensional time and multi-dimensional space; and sequencing the candidate objects according to the multi-dimensional space-time contribution score, and acquiring a first preset number of candidate objects with the highest multi-dimensional space-time contribution score as first target objects. The technical scheme can obtain accurate and more comprehensive commodity sales data with pertinence, so as to be used as data support to make the sales decision of the merchant, and finally realize the optimization of the commodity sales structure of the merchant and the further improvement of the commodity sales volume of the merchant.

Description

Object processing method, device, electronic equipment, storage medium and program product

Technical Field

The present disclosure relates to the field of data processing technologies, and in particular, to an object processing method and apparatus, an electronic device, a storage medium, and a program product.

Background

With the progress of society, the commodity flow of retail merchants selling various commodities required by people is increasing day by day, but at present, the retail merchants usually determine what commodities are sold and what commodities are supplemented only by the sales data of the merchants or the sales data of the whole city, obviously, the sales data supporting the sales decision are too comprehensive and lack of pertinence, and the information of commodity demands cannot be accurately obtained, so a data processing method is urgently needed to obtain accurate, more comprehensive and more targeted commodity sales data, further, the more accurate, more comprehensive and more targeted commodity sales data is used as data support to make the sales decision of the merchants, and finally, the optimization of the commodity sales structure of the merchants is realized, and the commodity sales volume of the merchants is further improved.

Disclosure of Invention

The embodiment of the disclosure provides an object processing method and device, electronic equipment, a storage medium and a program product.

In a first aspect, an embodiment of the present disclosure provides an object processing method.

Specifically, the object processing method includes:

obtaining multi-dimensional candidate objects in a preset area to form a candidate object set;

calculating a multi-dimensional space-time contribution score of the candidate object to a target entity, wherein the multi-dimensional space-time contribution score is used for representing the contribution degree of the candidate object to the target entity in multi-dimensional time and multi-dimensional space;

and sequencing the candidate objects according to the multi-dimensional space-time contribution score, and acquiring a first preset number of candidate objects with the highest multi-dimensional space-time contribution score as first target objects.

With reference to the first aspect, in a first implementation manner of the first aspect, the multiple dimensions include one or more of the following dimensions: the object sales volume, the searched frequency of the object and the variation trend of the object sales volume.

With reference to the first aspect and the first implementation manner of the first aspect, in a second implementation manner of the first aspect, the obtaining a multi-dimensional candidate object in a preset region includes:

obtaining object sales dimension candidate objects in a preset area; and/or the presence of a gas in the gas,

acquiring a searched frequency dimension candidate object of an object in a preset area; and/or the presence of a gas in the gas,

and acquiring the object sales volume change trend dimension candidate object in the preset area.

With reference to the first aspect, the first implementation manner of the first aspect, and the second implementation manner of the first aspect, in a third implementation manner of the first aspect, the obtaining of the object sales dimension candidate object in the preset area is implemented as:

acquiring second preset quantity of object source attribute information with the highest sales volume in the preset area;

and acquiring a third preset number of objects with the highest sales volume from the objects with the object source attribute information as object sales volume dimension candidate objects in the preset area.

With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, and the third implementation manner of the first aspect, in a fourth implementation manner of the first aspect, the obtaining of the frequency dimension candidate object of the object in the preset region is implemented as:

acquiring object search historical data in the preset area;

determining a fourth preset number of search terms with highest frequency of occurrence according to the object search historical data;

and determining an object associated with the search word according to the search word, wherein the object is used as a searched frequency dimension candidate object of the object in the preset area.

With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, and the fourth implementation manner of the first aspect, in a fifth implementation manner of the first aspect, the obtaining of the object sales volume change trend dimension candidate object in the preset area is implemented as:

acquiring object sales data in a preset time period in the preset area;

calculating the sales increase rate of the object according to the object sales data;

and taking the objects with the fifth preset number and the highest sales volume growth rate as object sales volume change trend dimension candidate objects in the preset area.

With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, the fourth implementation manner of the first aspect, and the fifth implementation manner of the first aspect, in a sixth implementation manner of the first aspect, before the calculating a multidimensional space-time contribution score of the candidate object to the target entity, the method further includes:

and filtering the existing objects of the target entity for the candidate object set.

With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, the fourth implementation manner of the first aspect, the fifth implementation manner of the first aspect, and the sixth implementation manner of the first aspect, in a seventh implementation manner of the first aspect, the performing object filtering on the candidate object set for the target entity is implemented as:

acquiring inventory object identification information of the target entity;

comparing the inventory object identification information with the candidate object identification information in the candidate object set, and filtering out the candidate objects in the candidate object set which are the same as the inventory object identification information.

With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, the fourth implementation manner of the first aspect, the fifth implementation manner of the first aspect, the sixth implementation manner of the first aspect, and the seventh implementation manner of the first aspect, in an eighth implementation manner of the first aspect, the calculating a multidimensional space-time contribution score of the candidate object to the target entity includes:

determining one or more time periods having different durations and one or more areas having different coverage areas;

and calculating the multi-dimensional space-time contribution scores of the candidate objects to the target entity in different time periods and different areas.

With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, the fourth implementation manner of the first aspect, the fifth implementation manner of the first aspect, the sixth implementation manner of the first aspect, the seventh implementation manner of the first aspect, and the eighth implementation manner of the first aspect, in a ninth implementation manner of the first aspect, the calculating a multidimensional space-time contribution score of the candidate object to the target entity in different time periods and different areas is implemented as:

calculating a region weight value of a region where the candidate object is located;

calculating a time weight value of a time period corresponding to the historical sales behavior of the candidate object;

calculating the object sale contribution ratio of the candidate object in different time periods and different areas;

and performing weighted calculation on the region weight value, the time weight value and the object sales contribution ratio to obtain multidimensional space-time contribution scores of the candidate objects to the target entity in different time periods and different regions.

With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, the fourth implementation manner of the first aspect, the fifth implementation manner of the first aspect, the sixth implementation manner of the first aspect, the seventh implementation manner of the first aspect, the eighth implementation manner of the first aspect, and the ninth implementation manner of the first aspect, in a tenth implementation manner of the first aspect, before the calculating the multidimensional space-time contribution score of the candidate object to the target entity, the method further includes:

and carrying out de-duplication processing on the candidate objects.

With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, the fourth implementation manner of the first aspect, the fifth implementation manner of the first aspect, the sixth implementation manner of the first aspect, the seventh implementation manner of the first aspect, the eighth implementation manner of the first aspect, the ninth implementation manner of the first aspect, and the tenth implementation manner of the first aspect, in an eleventh implementation manner of the first aspect, the embodiment of the present disclosure further includes:

and sending the first target object information to the target entity.

With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, the fourth implementation manner of the first aspect, the fifth implementation manner of the first aspect, the sixth implementation manner of the first aspect, the seventh implementation manner of the first aspect, the eighth implementation manner of the first aspect, the ninth implementation manner of the first aspect, the tenth implementation manner of the first aspect, and the eleventh implementation manner of the first aspect, an embodiment of the present disclosure further includes, in a twelfth implementation manner of the first aspect:

and estimating the click rate of the first target object, and acquiring a sixth preset number of target objects with the highest click rate as second target objects.

With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, the fourth implementation manner of the first aspect, the fifth implementation manner of the first aspect, the sixth implementation manner of the first aspect, the seventh implementation manner of the first aspect, the eighth implementation manner of the first aspect, the ninth implementation manner of the first aspect, the tenth implementation manner of the first aspect, the eleventh implementation manner of the first aspect, and the twelfth implementation manner of the first aspect, in a thirteenth implementation manner of the first aspect, the estimating a click rate of the first target object is implemented as:

acquiring an embedded vector of the target entity and an embedded vector of the first target object;

setting an association tag according to whether an association relationship exists between the target entity and the first target object;

and inputting the embedded vector of the target entity, the embedded vector of the first target object and the associated tag into a pre-trained click rate estimation model to obtain the click rate of the first target object.

With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, the fourth implementation manner of the first aspect, the fifth implementation manner of the first aspect, the sixth implementation manner of the first aspect, the seventh implementation manner of the first aspect, the eighth implementation manner of the first aspect, the ninth implementation manner of the first aspect, the tenth implementation manner of the first aspect, the eleventh implementation manner of the first aspect, the twelfth implementation manner of the first aspect, and the thirteenth implementation manner of the first aspect, an embodiment of the present disclosure further includes, in a fourteenth implementation manner of the first aspect:

and sending the second target object information to the target entity.

In a second aspect, an object processing apparatus is provided in an embodiment of the present disclosure.

Specifically, the object processing apparatus includes:

the acquisition module is configured to acquire multi-dimensional candidate objects in a preset area to form a candidate object set;

a calculation module configured to calculate a multidimensional space-time contribution score of the candidate object to a target entity, wherein the multidimensional space-time contribution score is used for characterizing the degree of contribution of the candidate object to the target entity in multidimensional time and multidimensional space;

and the sequencing module is configured to sequence the candidate objects according to the multi-dimensional space-time contribution score, and obtain a first preset number of candidate objects with the highest multi-dimensional space-time contribution score as a first target object.

With reference to the second aspect, in a first implementation manner of the second aspect, the multiple dimensions include one or more of the following dimensions: the object sales volume, the searched frequency of the object and the variation trend of the object sales volume.

With reference to the second aspect and the first implementation manner of the second aspect, in a second implementation manner of the second aspect, the obtaining module is configured to:

With reference to the second aspect, the first implementation manner of the second aspect, and the second implementation manner of the second aspect, in a third implementation manner of the second aspect, the obtaining the candidate object in the object sales dimension in the preset area is configured to:

With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, and the third implementation manner of the second aspect, in a fourth implementation manner of the second aspect, the obtaining a portion of the frequency dimension candidate objects of the objects in the preset area is configured to:

acquiring object search historical data in the preset area;

With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, and the fourth implementation manner of the second aspect, in a fifth implementation manner of the second aspect, the portion for acquiring the object pin quantity variation trend dimension candidate object in the preset area is configured to:

acquiring object sales data in a preset time period in the preset area;

With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, the fourth implementation manner of the second aspect, and the fifth implementation manner of the second aspect, in a sixth implementation manner of the second aspect, the embodiment of the present disclosure further includes, before the calculating module, that:

a filtering module configured to perform object filtering on the candidate object set.

With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, the fourth implementation manner of the second aspect, the fifth implementation manner of the second aspect, and the sixth implementation manner of the second aspect, in a seventh implementation manner of the second aspect, the filtering module is configured to:

acquiring inventory object identification information of the target entity;

With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, the fourth implementation manner of the second aspect, the fifth implementation manner of the second aspect, the sixth implementation manner of the second aspect, and the seventh implementation manner of the second aspect, in an eighth implementation manner of the second aspect, the computing module is configured to:

With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, the fourth implementation manner of the second aspect, the fifth implementation manner of the second aspect, the sixth implementation manner of the second aspect, the seventh implementation manner of the second aspect, and the eighth implementation manner of the second aspect, in a ninth implementation manner of the second aspect, the section that calculates the multidimensional space-time contribution score of the candidate object to the target entity at different time periods and different areas is configured to:

With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, the fourth implementation manner of the second aspect, the fifth implementation manner of the second aspect, the sixth implementation manner of the second aspect, the seventh implementation manner of the second aspect, the eighth implementation manner of the second aspect, and the ninth implementation manner of the second aspect, in a tenth implementation manner of the second aspect, the computing module is preceded by a further module that:

a deduplication module configured to perform deduplication processing on the candidate object.

With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, the fourth implementation manner of the second aspect, the fifth implementation manner of the second aspect, the sixth implementation manner of the second aspect, the seventh implementation manner of the second aspect, the eighth implementation manner of the second aspect, the ninth implementation manner of the second aspect, and the tenth implementation manner of the second aspect, in an eleventh implementation manner of the second aspect, the embodiment of the present disclosure further includes:

a first sending module configured to send the first target object information to the target entity.

With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, the fourth implementation manner of the second aspect, the fifth implementation manner of the second aspect, the sixth implementation manner of the second aspect, the seventh implementation manner of the second aspect, the eighth implementation manner of the second aspect, the ninth implementation manner of the second aspect, the tenth implementation manner of the second aspect, and the eleventh implementation manner of the second aspect, in a twelfth implementation manner of the second aspect, the embodiment of the present disclosure further includes:

and the acquisition module is configured to estimate the click rate of the first target object and acquire a sixth preset number of target objects with the highest click rate as second target objects.

With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, the fourth implementation manner of the second aspect, the fifth implementation manner of the second aspect, the sixth implementation manner of the second aspect, the seventh implementation manner of the second aspect, the eighth implementation manner of the second aspect, the ninth implementation manner of the second aspect, the tenth implementation manner of the second aspect, the eleventh implementation manner of the second aspect, and the twelfth implementation manner of the second aspect, in a thirteenth implementation manner of the second aspect, the portion for estimating the click rate of the first target object is configured to:

With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, the fourth implementation manner of the second aspect, the fifth implementation manner of the second aspect, the sixth implementation manner of the second aspect, the seventh implementation manner of the second aspect, the eighth implementation manner of the second aspect, the ninth implementation manner of the second aspect, the tenth implementation manner of the second aspect, the eleventh implementation manner of the second aspect, the twelfth implementation manner of the second aspect, and the thirteenth implementation manner of the second aspect, the embodiment of the present disclosure further includes, in the fourteenth implementation manner of the second aspect:

a second sending module configured to send the second target object information to the target entity.

In a third aspect, the present disclosure provides an electronic device, including a memory and at least one processor, where the memory is configured to store one or more computer instructions, where the one or more computer instructions are executed by the at least one processor to implement the method steps of the above object processing method.

In a fourth aspect, the disclosed embodiments provide a computer-readable storage medium for storing computer instructions for an object processing apparatus, which includes computer instructions for executing the object processing method described above as an object processing apparatus.

In a fifth aspect, the present disclosure provides a computer program product comprising a computer program/instructions, wherein the computer program/instructions, when executed by a processor, implement the method steps of the above object processing method.

The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:

according to the technical scheme, the candidate objects are collected and the contribution degrees are ranked based on multiple dimensions, and then the target objects which can be sent to the target entity can be obtained. The technical scheme can obtain accurate and more comprehensive commodity sales data with pertinence, so as to be used as data support to make the sales decision of the merchant, and finally realize the optimization of the commodity sales structure of the merchant and the further improvement of the commodity sales volume of the merchant.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

Other features, objects, and advantages of the present disclosure will become more apparent from the following detailed description of non-limiting embodiments when taken in conjunction with the accompanying drawings. In the drawings:

FIG. 1 illustrates a flow diagram of an object processing method according to an embodiment of the present disclosure;

FIG. 2 illustrates an overall flow diagram of an object processing method according to an embodiment of the present disclosure;

fig. 3 illustrates a block diagram of an object processing apparatus according to an embodiment of the present disclosure;

FIG. 4 shows a block diagram of an electronic device according to an embodiment of the present disclosure;

fig. 5 is a schematic structural diagram of a computer system suitable for implementing an object processing method according to an embodiment of the present disclosure.

Detailed Description

Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. Also, for the sake of clarity, parts not relevant to the description of the exemplary embodiments are omitted in the drawings.

In the present disclosure, it is to be understood that terms such as "including" or "having," etc., are intended to indicate the presence of the disclosed features, numbers, steps, behaviors, components, parts, or combinations thereof, and are not intended to preclude the possibility that one or more other features, numbers, steps, behaviors, components, parts, or combinations thereof may be present or added.

It should be further noted that the embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

The technical scheme provided by the embodiment of the disclosure is based on multi-dimension to collect candidate objects and sort the contribution degrees, so that the target objects which can be sent to the target entity can be obtained. The technical scheme can obtain accurate and more comprehensive commodity sales data with pertinence, so as to be used as data support to make the sales decision of the merchant, and finally realize the optimization of the commodity sales structure of the merchant and the further improvement of the commodity sales volume of the merchant.

Fig. 1 illustrates a flowchart of an object processing method according to an embodiment of the present disclosure, which includes the following steps S101 to S103, as illustrated in fig. 1:

in step S101, obtaining multi-dimensional candidate objects in a preset region to form a candidate object set;

in step S102, calculating a multidimensional space-time contribution score of the candidate object to a target entity, wherein the multidimensional space-time contribution score is used for representing the degree of contribution of the candidate object to the target entity in multidimensional time and multidimensional space;

in step S103, the candidate objects are ranked according to the multi-dimensional space-time contribution score, and a first preset number of candidate objects with the highest multi-dimensional space-time contribution score are obtained as a first target object.

As mentioned above, with the progress of society, the commodity flow of retail merchants selling various commodities required by people is increasing day by day, but at present, retail merchants usually determine what commodities are sold and what commodities are supplemented only by the sales data of their own or the sales data of the whole city, obviously, the sales data supporting the sales decision is too comprehensive and lacks pertinence, and commodity demand information cannot be accurately obtained, so a data processing method is urgently needed to obtain accurate, more comprehensive and more targeted commodity sales data, and further, the more accurate, more comprehensive and more targeted commodity sales data is used as data support to make the sales decision of the merchants, and finally, the optimization of the merchant sales commodity structure and the further improvement of the commodity sales volume of the merchants are realized.

In view of the above drawbacks, the present embodiment proposes an object processing method, which performs collection and contribution degree ranking of candidate objects based on multiple dimensions, and further obtains a target object that can be sent to a target entity. The technical scheme can obtain accurate and more comprehensive commodity sales data with pertinence, so as to be used as data support to make the sales decision of the merchant, and finally realize the optimization of the commodity sales structure of the merchant and the further improvement of the commodity sales volume of the merchant.

In an embodiment of the present disclosure, the object processing method may be applied to a computer, a computing device, an electronic device, a server, a service cluster, and the like that perform computation on object-related data.

In an embodiment of the present disclosure, the preset area refers to a processing area range of a predetermined subsequent object, and the position and size of the preset area may be determined according to the needs of practical applications and the characteristics of the object to be processed, for example, the preset area may be set to be a smaller area such as a certain city, a certain area of a certain city, a honeycomb of a certain city, or an area within a specified range of a certain city.

In an embodiment of the present disclosure, the object refers to an object having multidimensional data, such as a commodity that can be sold, and the multidimensional data of the commodity that can be sold may include data of commodity sales amount, commodity searched frequency, commodity sales amount variation trend, and the like. Therefore, the multi-dimensional candidate object refers to a candidate object obtained based on multi-dimensional data acquisition, wherein the multi-dimension may include one or more of the following dimensions: object sales, frequency with which objects are searched, trend of object sales, etc.

In an embodiment of the present disclosure, the target entity refers to an entity to which determined target object information needs to be subsequently sent, for example, when the object is a commodity, the target entity may be a merchant selling the commodity.

In an embodiment of the present disclosure, the multidimensional space-time contribution score is used for characterizing the degree of contribution of the candidate object to the target entity in multidimensional time and multidimensional space, wherein the multidimensional time refers to one or more time periods with different durations, such as 7 days, 14 days, 28 days, and the like; the multi-dimensional space refers to one or more spatial regions covering different ranges, such as cities, regions of cities, cells of cities, and the like; and the multidimensional space-time contribution score refers to an object sales contribution ratio obtained by integrating factors of multidimensional time and multidimensional space, wherein the object sales contribution ratio refers to the ratio of the total sales of an object to the sales of the object in a preset space region and a preset time period.

After the multidimensional space-time contribution scores of the candidate objects in the candidate object set are calculated, the candidate objects can be ranked according to the multidimensional space-time contribution scores, a first preset number of candidate objects with the highest multidimensional space-time contribution scores can be regarded as the objects which can contribute the most to the target entity, and therefore the candidate objects can be used as first target objects subsequently, and the first target object information is sent to the target entity, so that the target entity can make a sales strategy according to the first target object information. The first preset number can be set according to the requirements of practical application and the characteristics of the objects.

In an embodiment of the present disclosure, the acquiring the multi-dimensional candidate object in the preset region in step S101 may include the following steps:

As mentioned above, the multiple dimensions may include one or more of the following dimensions: the method comprises the steps of obtaining an object sales volume, an object searched frequency, an object sales volume change trend and the like, so that obtaining a multi-dimensional candidate object in a preset area can comprise obtaining an object sales volume dimensional candidate object in the preset area; and/or acquiring a frequency dimension candidate object searched for by the object in the preset area; and/or acquiring the object sales volume change trend dimension candidate object in the preset area.

Specifically, the method comprises the following steps:

in an embodiment of the present disclosure, the obtaining of the object sales dimension candidate object in the preset area may be implemented as:

In this embodiment, when an object sales dimension candidate object in a preset area is obtained, first, a second preset number of object source attribute information with the highest sales in the preset area is obtained, where the object source attribute information refers to root-source attribute information of the object, for example, if the object is a commodity, the object source attribute information may be a brand of the commodity; and then, acquiring the objects with the object source attribute information, and then taking a third preset number of objects with the highest sales volume from the objects with the object source attribute information as object sales volume dimension candidate objects in the preset area. Taking the object as a commodity and the preset area as an a city as an example, a second preset number of commodity brands with the highest sales volume in the a city are obtained first, and then a third preset number of commodities with the highest sales volume in the commodity brands are obtained, and the commodities can be regarded as commodities with higher sales volume or higher popularity in the a city, so that the commodities can be used as candidate objects in the sales volume dimension of the object in the a city. The second preset quantity and the third preset quantity can be set according to the requirements of practical application and the characteristics of the object.

In an embodiment of the present disclosure, the obtaining of the frequency dimension candidate object of the object in the preset region may be implemented as:

acquiring object search historical data in the preset area;

In this embodiment, when acquiring a frequency dimension candidate object of an object in a preset area, first acquiring object search history data in the preset area, where the object search history data may be object search history data generated within a preset history time period; then determining a fourth preset number of search terms with highest frequency of occurrence according to the object search historical data; and finally, determining an object associated with the search word according to the search word, wherein the object is used as a searched frequency dimension candidate object of the object in the preset area. Still taking the object as a commodity and taking the preset area as an city A as an example, firstly, obtaining commodity searching historical data in a preset historical time period in the city A; then determining a fourth preset number of search terms with highest frequency of occurrence based on the object search historical data; and finally, determining commodities associated with the search terms based on the search terms by means of a term commodity association algorithm, wherein the commodities can be regarded as favorite commodities of the buyer in the preset historical time period in the city A, namely the commodities with higher preference of the buyer, and therefore the commodities can be used as candidate objects in the frequency dimension of searching the objects in the city A. The fourth preset number can be set according to the requirements of practical application and the characteristics of the objects.

In an embodiment of the present disclosure, the obtaining of the object sales volume change trend dimension candidate object in the preset area may be implemented as:

acquiring object sales data in a preset time period in the preset area;

In the embodiment, when an object sales volume change trend dimension candidate object in a preset area is obtained, firstly, object sales volume data in a preset time period in the preset area is obtained; then calculating the sales volume increase rate of the object in the preset time period according to the object sales volume data; and finally, taking the fifth preset number of objects with the highest sales volume growth rate as object sales volume change trend dimension candidate objects in the preset area. Still taking the object as a commodity and taking the preset area as an A city as an example, firstly, acquiring commodity sales data in a preset time period in the A city; and then calculating the sales increase rate of the commodity in the preset time period based on the commodity sales data to show the sales increase trend of the commodity, and finally obtaining a fifth preset number of commodities with the highest sales increase rate, wherein the commodities can be regarded as the commodities which are most popular with buyers in the preset time period in the city A, namely the commodities which can show the timeliness to a certain extent, so that the commodities can be used as candidate objects in the dimension of the object sales change trend in the city A. The fifth preset number can be set according to the requirements of actual application and the characteristics of the objects.

In an optional implementation manner of this embodiment, before the step S102 of calculating the multidimensional space-time contribution score of the candidate object to the target entity, the method may further include the following steps:

In order to avoid sending the same object information, ensure the validity of sending the object information, and improve the quality of sending the object information, in this embodiment, before determining the object to be sent to the target entity, the same object information needs to be filtered, that is, the related information of the object existing at present in the target entity is first obtained, then the candidate objects in the candidate object set are filtered based on the related information of the existing object, the object existing at present in the target entity is filtered, and the object not existing at present in the target entity is retained. In order to facilitate the comparison of the same objects, the related information of the objects may be object identification information with identifiability, such as object names, object codes, and the like. That is, in an optional implementation manner of this embodiment, the step of filtering the target entity existing object for the candidate object set may be implemented as:

acquiring inventory object identification information of the target entity;

The stock object of the target entity refers to an object which is currently existed in the target entity.

In an optional implementation manner of this embodiment, the step S102 of calculating the multidimensional space-time contribution score of the candidate object to the target entity may include the following steps:

As mentioned above, the multidimensional space-time contribution score refers to an object sales contribution ratio obtained by integrating factors of multidimensional time and multidimensional space, wherein the multidimensional time refers to one or more time periods with different durations, such as 7 days, 14 days, 28 days and the like; the multi-dimensional space refers to one or more spatial regions covering different ranges, such as cities, regions of cities, cells of cities, and the like. Thus, in this embodiment, in calculating the multi-dimensional spatio-temporal contribution score of the candidate to the target entity, one or more time periods having different durations, such as 3 time periods having durations of 7 days, 14 days, 28 days, etc., and one or more areas having different coverage, such as 3 areas of a city, a region of a city, a cell of a city, etc., are first determined; and then calculating multidimensional space-time contribution scores of the candidate objects to the target entity in different time periods and different areas so as to represent the contribution degrees of the candidate objects to the target entity in multidimensional time and multidimensional space.

In an optional implementation manner of this embodiment, the step of calculating contribution scores of the candidate objects to the target entity at different time periods and different areas may include the following steps:

In this embodiment, when calculating the contribution scores of the candidate object to the target entity in different time periods and different areas, the area weight value of the area where the candidate object is located is first calculated

Where k denotes a candidate k, i denotes a region dimension, such as: cells, regions, cities, etc., the larger the area coverage, the larger the area dimension, the weighted value of the area

Decaying as the region dimension i increases, the region weight values

The candidate object weight value is obtained through model training and learning, when the model training is carried out, the input of the model can be a region name or a region dimension and an object attribute, the output can be a region weight value of a region where the candidate object is located, and the object attribute can be attribute information such as an object name and an object identification code; then calculating the time weight value of the time period corresponding to the historical sale behavior of the candidate object

Where j represents a time dimension, such as: 7 days, 14 days, 28 days, etc., the longer the duration of the time period, the larger the time dimension, the time weight value

Decaying as the time dimension j increases, the time weight value

The time weight value of the time period corresponding to the historical sales behavior of the candidate object can be output; then calculating the object sale contribution ratio of the candidate objects in different time periods and different areas

As described above, the object sales contribution ratio refers to objects occurring within a predetermined spatial region and a predetermined time periodThe proportion of the sales of a certain object in the sales sum; finally, carrying out weighted calculation on the region weight value, the time weight value and the object sale contribution ratio to obtain a multi-dimensional space-time contribution Score of the candidate object to the target entity in different time periods and different regions_kAs shown in the following formula:

wherein h represents a target entity h,

representing a same category weight value which is between 0 and 1, taking 1 when the candidate object K is the same as the main sales category of the target entity h, and taking an empirical value smaller than 1 when the candidate object K is not the same as the main sales category of the target entity h, wherein the same category weight value is used for improving the multidimensional space-time contribution score of the candidate object which is the same as the main sales category of the target entity, n represents the total number of area dimensions I, m represents the total number of time dimensions J, I represents a set of area dimensions I, J represents a set of time dimensions J, and K (I, J) represents a set consisting of effective candidate objects on the area dimensions I and the time dimensions J,

GMV_ij ^kand the object sales value of the candidate object k in the time dimension i and the area dimension j is represented.

and carrying out de-duplication processing on the candidate objects.

In order to avoid the situation of repeatedly sending the same object information, in the embodiment, before calculating the multidimensional space-time contribution score of the candidate object to the target entity, the candidate object needs to be subjected to deduplication processing. For example, the deduplication of the candidate object may be implemented according to the related information of the candidate object, where the related information of the candidate object may be, for example, the name of the candidate object, the identification code of the candidate object, the picture source of the candidate object, the category to which the candidate object belongs, and the like, and then, the deduplication processing of the candidate object may be implemented based on the similarity calculation of the related information of the candidate object.

In an optional implementation manner of this embodiment, the method further includes the following steps:

In order to improve the quality of the objects subsequently sent to the target entity, further optimize the structure of the merchant sales commodity and improve the sales volume of the merchant commodity, and meanwhile, considering that the click rate of a certain object can reflect the popularity of the object to a great extent, in this embodiment, a second target object with higher value is screened from the obtained first target object, so as to subsequently send the information of the second target object to the target entity. Specifically, the second target objects are screened according to the click rate, that is, the click rate of the first target object is estimated first, and then the sixth preset number of target objects with the highest click rate are used as the second target objects to be subsequently sent to the target entity. The sixth preset number can be set according to the requirements of practical application and the characteristics of the objects.

In an optional implementation manner of this embodiment, the step of estimating the click rate of the first target object may be implemented as:

In this embodiment, an embedded vector of the target entity and an embedded vector of the first target object are first constructed, where the construction of the embedded vector may be implemented based on feature engineering in the prior art, and is not described in detail in this disclosure; then, setting an association tag according to whether an association relationship exists between the target entity and the first target object, wherein the association tag is used for representing whether the association relationship exists between the target entity and the first target object, and if the first target object constructs corresponding information at the target entity or once, namely the target entity sells the first target object once or currently, the association tag can be set to 1, otherwise, the association tag is set to 0; and finally, inputting the embedded vector of the target entity, the embedded vector of the first target object and the associated label into a pre-trained click rate pre-estimation model, so as to obtain the pre-estimated click rate of the first target object, wherein the input of the click rate pre-estimation model can be the embedded vector of a training object, the embedded vector of the training target entity and the associated label between the training object and the training target entity during training, and the output is the click rate of the training object on the target entity.

Fig. 2 illustrates an overall flowchart of an object processing method according to an embodiment of the present disclosure. As shown in fig. 2, it is assumed that the preset area is a city a, the object is a commodity, the object source attribute information is commodity brand information, the object search history data is a commodity search term, and the target entity is a merchant selling the commodity. Firstly, candidate commodities, namely commodities with higher recall sales volume, hot searched commodities and ordered commodities, are obtained from three dimensions of commodity sales volume, commodity searched frequency and commodity sales volume change trend, specifically, commodity brand information with the highest sales volume in a city A range is obtained, and then some commodities with the highest sales volume are obtained from the commodity brands according to commodity sales volume statistical data to form a commodity set with higher sales volume; the method comprises the steps that a commodity search word with high occurrence frequency in a city A range, namely a hot search word, is obtained, commodities associated with the hot search word are determined by means of a word commodity association algorithm, and a hot search commodity set is formed; the commodity sales data in the city A range are obtained, and the commodity with the highest sales increase rate is obtained by means of a commodity sales trend analysis algorithm, so that a current commodity set is formed. And filtering the commodities with higher sales volume, hot search commodities and seasonal commodities obtained by recalling to obtain a candidate commodity set.

And then carrying out de-duplication processing on the candidate commodity set, and then calculating multidimensional space-time contribution scores of the candidate commodity for the merchant in three different time periods of 7 days, 14 days and 28 days and in three different areas of the merchant, the honeycomb and the city, wherein the area coverage area is larger, the area weight value is smaller, and the time period duration is longer, the weight value is smaller. And sorting the candidate commodities according to the multidimensional space-time contribution score, recommending some candidate commodities with the highest multidimensional space-time contribution score to the merchant as first target commodities, wherein the generation process of the first target commodities can be regarded as a process of roughly arranging the target commodities.

Further, the embedded vector of the merchant and the embedded vector of the first target commodity can be continuously obtained, an association label is set according to whether the merchant and the first target commodity have an association relationship, the embedded vector of the merchant, the embedded vector of the first target commodity and the association label are input into a click rate estimation model trained in advance, the click rate of the first target commodity is predicted, some target commodities with the highest click rate are recommended to the merchant as second target commodities, and the generation process of the second target commodity can be regarded as a process of fine ranking of the target commodities.

The following are embodiments of the disclosed apparatus that may be used to perform embodiments of the disclosed methods.

Fig. 3 shows a block diagram of an object processing apparatus according to an embodiment of the present disclosure, which may be implemented as part or all of an electronic device by software, hardware, or a combination of both. As shown in fig. 3, the object processing apparatus includes:

an obtaining module 301, configured to obtain multi-dimensional candidate objects in a preset region to form a candidate object set;

a calculating module 302 configured to calculate a multidimensional space-time contribution score of the candidate object to a target entity, wherein the multidimensional space-time contribution score is used for characterizing the degree of contribution of the candidate object to the target entity in multidimensional time and multidimensional space;

a sorting module 303 configured to sort the candidate objects according to the multi-dimensional space-time contribution score, and obtain a first preset number of candidate objects with the highest multi-dimensional space-time contribution score as a first target object.

In view of the above drawbacks, in this embodiment, an object processing apparatus is provided, which performs collection and contribution degree ranking of candidate objects based on multiple dimensions, and thus can obtain a target object that can be sent to a target entity. The technical scheme can obtain accurate and more comprehensive commodity sales data with pertinence, so as to be used as data support to make the sales decision of the merchant, and finally realize the optimization of the commodity sales structure of the merchant and the further improvement of the commodity sales volume of the merchant.

In an embodiment of the present disclosure, the object processing apparatus may be implemented as a computer, a computing device, an electronic device, a server, a service cluster, or the like that performs computation on object-related data.

After the multidimensional space-time contribution scores of the candidate objects in the candidate object set are calculated, the candidate objects can be ranked according to the multidimensional space-time contribution scores, a first preset number of candidate objects with the highest multidimensional space-time contribution scores can be regarded as objects which can contribute most to the target entity, and therefore the candidate objects can be subsequently used as first target objects, a first sending module is arranged, and the first target object information is sent to the target entity so that the target entity can make a sales strategy according to the first target object information. The first preset number can be set according to the requirements of practical application and the characteristics of the objects.

In an embodiment of the present disclosure, the obtaining module may be configured to:

Specifically, the method comprises the following steps:

in an embodiment of the present disclosure, the portion for acquiring the object sales dimension candidate objects in the preset area may be configured to:

In an embodiment of the present disclosure, the portion of the object in the preset region searched for the frequency dimension candidate object may be configured to:

acquiring object search historical data in the preset area;

In an embodiment of the present disclosure, the acquiring the part of the object sales volume variation trend dimension candidate objects in the preset area may be configured to:

acquiring object sales data in a preset time period in the preset area;

In an optional implementation manner of this embodiment, before the calculating module, the method may further include:

In order to avoid sending the same object information, ensure the validity of sending the object information, and improve the quality of sending the object information, in this embodiment, before determining the object to be sent to the target entity, the same object information needs to be filtered, that is, the related information of the object existing at present in the target entity is first obtained, then the candidate objects in the candidate object set are filtered based on the related information of the existing object, the object existing at present in the target entity is filtered, and the object not existing at present in the target entity is retained. In order to facilitate the comparison of the same objects, the related information of the objects may be object identification information with identifiability, such as object names, object codes, and the like. That is, in an optional implementation manner of this embodiment, the filtering module may be configured to:

acquiring inventory object identification information of the target entity;

In an optional implementation manner of this embodiment, the calculation module may be configured to:

In an optional implementation manner of this embodiment, the part for calculating the multidimensional space-time contribution score of the candidate object to the target entity at different time periods and different regions may be configured to:

Decaying as the region dimension i increases, the region weight values

Decaying as the time dimension j increases, the time weight value

The model can also be obtained through model training and learning, when the model training is carried out, the input of the model can be the time period or the time dimension and the object attribute corresponding to the historical sale behavior of the candidate object, and the output is the resultTime weight values of time periods corresponding to the historical sales behaviors of the candidate objects; then calculating the object sale contribution ratio of the candidate objects in different time periods and different areas

As described above, the object sales contribution ratio refers to a ratio of sales of an object to a total of sales of the object that occur within a predetermined space region and a predetermined period of time; finally, carrying out weighted calculation on the region weight value, the time weight value and the object sale contribution ratio to obtain a multi-dimensional space-time contribution Score of the candidate object to the target entity in different time periods and different regions_kAs shown in the following formula:

wherein h represents a target entity h,

In an optional implementation manner of this embodiment, before the calculating module, the method further includes:

In an optional implementation manner of this embodiment, the apparatus further includes:

In order to improve the quality of the objects subsequently sent to the target entity, further optimize the structure of the merchant sales commodity and improve the sales volume of the merchant commodity, and meanwhile, considering that the click rate of a certain object can reflect the popularity of the object to a great extent, in this embodiment, a second target object with higher value is screened from the obtained first target object, so as to subsequently set a second sending module and send the information of the second target object to the target entity. Specifically, the second target objects are screened according to the click rate, that is, the click rate of the first target object is estimated first, and then the sixth preset number of target objects with the highest click rate are used as the second target objects to be subsequently sent to the target entity. The sixth preset number can be set according to the requirements of practical application and the characteristics of the objects.

In an optional implementation manner of this embodiment, the estimating of the click rate of the first target object may be configured to:

The present disclosure also discloses an electronic device, fig. 4 shows a block diagram of an electronic device according to an embodiment of the present disclosure, and as shown in fig. 4, the electronic device 400 includes a memory 401 and a processor 402; wherein the content of the first and second substances,

the memory 401 is used to store one or more computer instructions that are executed by the processor 402 to implement the above-described method steps.

Fig. 5 is a schematic block diagram of a computer system suitable for implementing a data processing method according to an embodiment of the present disclosure.

As shown in fig. 5, the computer system 500 includes a processing unit 501 that can execute various processes in the above-described embodiments 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 RAM503, various programs and data necessary for the operation of the system 500 are also stored. The processing unit 501, the ROM502, and the RAM503 are connected to each other by 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 portion 506 including a keyboard, a mouse, and the like; an output portion 507 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; 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 driver 510 is also connected to the I/O interface 505 as necessary. 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 necessary, so that a computer program read out therefrom is mounted into the storage section 508 as necessary. The processing unit 501 may be implemented as a CPU, a GPU, a TPU, an FPGA, an NPU, or other processing units.

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 disclosure. In this regard, each block in the flowcharts or block diagrams may represent a module, a program segment, or a 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 and/or flowchart illustration, and combinations of blocks in the block diagrams and/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 units or modules described in the embodiments of the present disclosure may be implemented by software or hardware. The units or modules described may also be provided in a processor, and the names of the units or modules do not in some cases constitute a limitation of the units or modules themselves.

As another aspect, the present disclosure also provides a computer-readable storage medium, which may be the computer-readable storage medium included in the apparatus in the above-described embodiment; or it may be a separate computer readable storage medium not incorporated into the device. The computer readable storage medium stores one or more programs for use by one or more processors in performing the methods described in the present disclosure.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is possible without departing from the inventive concept. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.

Claims

1. An object processing method, comprising:

2. The method of claim 1, the multiple dimensions comprising one or more of the following dimensions: the object sales volume, the searched frequency of the object and the variation trend of the object sales volume.

3. The method of claim 2, wherein the obtaining multi-dimensional candidate objects in a preset area comprises:

4. The method of claim 3, wherein the obtaining of object sales dimension candidate objects within a preset area is implemented as:

5. An object processing apparatus comprising:

6. The apparatus of claim 5, the multiple dimensions comprising one or more of: the object sales volume, the searched frequency of the object and the variation trend of the object sales volume.

7. The apparatus of claim 6, the acquisition module configured to:

8. An electronic device comprising a memory and at least one processor; wherein the memory is to store one or more computer instructions, wherein the one or more computer instructions are to be executed by the at least one processor to implement the method steps of any one of claims 1-4.

9. A computer-readable storage medium having stored thereon computer instructions, characterized in that the computer instructions, when executed by a processor, carry out the method steps of any of claims 1-4.

10. A computer program product comprising computer programs/instructions, wherein the computer programs/instructions, when executed by a processor, implement the method steps of any of claims 1-4.