CN117455579B

CN117455579B - Commodity recommendation intervention method, commodity recommendation intervention device, medium and equipment

Info

Publication number: CN117455579B
Application number: CN202311795784.7A
Authority: CN
Inventors: 董旭; 吴文龙
Original assignee: Shenzhen Zhiyan Technology Co Ltd; Shenzhen Qianyan Technology Co Ltd
Current assignee: Shenzhen Zhiyan Technology Co Ltd; Shenzhen Qianyan Technology Co Ltd
Priority date: 2023-12-25
Filing date: 2023-12-25
Publication date: 2024-04-09
Anticipated expiration: 2043-12-25
Also published as: CN117455579A

Abstract

The application relates to a commodity recommendation intervention method, a commodity recommendation intervention device, a medium and a device, wherein the commodity recommendation intervention method comprises the following steps: responding to a commodity searching request, and respectively recalling commodity items matched with the commodity searching request from a plurality of data sources to obtain recalled commodity sets corresponding to the data sources; acquiring a occupying commodity set, deleting commodity items, which are overlapped with the occupying commodity set, in each recall commodity set, wherein the occupying commodity set comprises at least one commodity item and a to-be-occupied position thereof; according to the intervention display scores obtained by the corresponding commodity items in each recall commodity set, carrying out fine-ranking treatment on all commodity items in all recall commodity sets to obtain a fine-ranking commodity set; and adding the commodity items in the occupied commodity set to the ordering order corresponding to the to-be-occupied order of the commodity items in the fine-ranking commodity set to obtain a recommended commodity set for responding to the commodity search request. The method and the device realize optimization of the commodity search results and are favorable for realizing personalized operation of the commodity search results.

Description

Commodity recommendation intervention method, commodity recommendation intervention device, medium and equipment

Technical Field

The application relates to the technical field of electronic commerce information, in particular to a commodity recommendation intervention method, a commodity recommendation intervention device, a medium and a commodity recommendation intervention device.

Background

In the e-commerce platform, collaborative filtering technology is often adopted to realize commodity recommendation. Collaborative filtering is a common recommendation algorithm that uses the principle of finding other users or goods similar to the user by analyzing the user's behavior and preferences, and then using these similarities to make recommendations.

The realization process of the collaborative filtering recommendation system comprises two main steps: and calculating the similarity of the users and generating a recommendation result. The pure collaborative filtering recommendation system has some technical defects and problems.

First, when the user behavior data is sparse or cold-started, it is difficult to find sufficiently similar users or goods, resulting in inaccurate recommendation results. The e-commerce platform based on the independent stations cannot share the user and commodity information, so that when a new commodity is put on the e-commerce platform or a new user logs in, corresponding historical data is lacking, and the collaborative filtering recommendation algorithm has limited functions.

Second, collaborative filtering recommendation systems are susceptible to data preferences, creating the drawbacks of information cocoons, which may result in recommendations that are too narrow or too consistent.

In addition, collaborative filtering technology is often implemented based on an end-to-end deep learning model, and the generated results are directly pushed to users, so that the results cannot be interfered from the operation angle, and the platform cannot effectively control commodity recommendation results, so that the requirements of users cannot be fully met.

Therefore, on the basis of widely adopting collaborative filtering technology in the existing e-commerce platform to obtain commodity recommendation results, further technical optimization is needed to optimize commodity recommendation results.

Disclosure of Invention

The application aims to provide a commodity recommendation intervention method, a commodity recommendation intervention device, a medium and a device.

According to one aspect of the present application, there is provided a commodity recommendation intervention method, including:

responding to a commodity searching request, and respectively recalling commodity items matched with the commodity searching request from a plurality of data sources to obtain recalled commodity sets corresponding to the data sources;

acquiring a occupying commodity set, deleting commodity items, which are overlapped with the occupying commodity set, in each recall commodity set, wherein the occupying commodity set comprises at least one commodity item and a to-be-occupied position thereof;

according to the intervention display scores obtained by the corresponding commodity items in each recall commodity set, carrying out fine-ranking treatment on all commodity items in all recall commodity sets to obtain a fine-ranking commodity set;

and adding the commodity items in the occupied commodity set to the ordering order corresponding to the to-be-occupied order of the commodity items in the fine-ranking commodity set to obtain a recommended commodity set for responding to the commodity search request.

According to another aspect of the present application, there is provided a commodity recommendation intervention apparatus including:

the data recall module is used for responding to the commodity search request and recalling commodity items matched with the commodity search request from a plurality of data sources respectively to obtain recalled commodity sets corresponding to the data sources;

the commodity duplicate removal module is used for acquiring a occupying commodity set, deleting commodity items in each recall commodity set, which are overlapped with the occupying commodity set, wherein the occupying commodity set comprises at least one commodity item and a to-be-occupied position thereof;

the commodity precision arranging module is used for carrying out precision arranging treatment on all commodity items in all recall commodity sets according to the intervention display scores correspondingly obtained by the commodity items in all recall commodity sets to obtain a precision arranging commodity set;

the occupation optimization module is used for adding the commodity items in the occupation commodity set to the ordering order corresponding to the to-be-occupied order of the commodity items in the fine-arranged commodity set to obtain a recommended commodity set for responding to the commodity search request.

According to another aspect of the present application, there is provided a computer device comprising a central processor and a memory, the central processor being adapted to invoke the steps of running a computer program stored in the memory to perform the commodity recommendation intervention method described herein.

According to another aspect of the present application, there is provided a non-transitory readable storage medium storing a computer program implemented in accordance with the commodity recommendation intervention method in the form of computer readable instructions, the computer program when executed by a computer to perform the steps included in the method.

The present application has a number of technical advantages over the prior art, including but not limited to:

firstly, designating a plurality of commodity items and corresponding positions to be occupied by presetting a position occupied commodity set to indicate that the commodity items display the corresponding positions in a given plurality of positions, acquiring a recall commodity set matched with a commodity search request from a plurality of data sources after a user submits the commodity search request, firstly deleting repeated commodity items overlapped with the position occupied commodity set from the recall commodity set, enabling the commodity items designated with the positions to be occupied not to participate in a link of finely sorting all the recall commodity sets, and adding the commodity items in the position occupied commodity set into the sorting positions corresponding to the finely sorted commodity set according to the positions to be occupied after finishing finely sorting to obtain the finely sorted commodity set, thereby realizing effective intervention on a multi-source recall result and conveniently realizing personalized operation based on the multi-source recall result.

Secondly, according to the multi-source recall result effectively intervening, for the independent station, the search result optimization of the collaborative filtering recommendation algorithm can be realized by means of the preset occupied commodity set according to the conditions of sparse data, cold start and the like of the independent station, meanwhile, the defect of data preference can be overcome, the commodity recommendation result is generalized, commodity items in the independent station can obtain more fair recommendation opportunities through the preset occupied commodity set, and therefore the improvement of the total platform exchange is promoted.

In addition, the occupied commodity set can be customized by the platform or the independent station, so that the technical means of personalized operation of the platform or the independent station on the multi-source recall result is enriched, the function of commodity advertisement implantation can be further realized in the commodity recommendation result, the whole scheme is easy to realize, the deployment cost is low, the operation efficiency is high, and higher comprehensive benefits can be brought.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a network architecture of an exemplary e-commerce platform of the present application;

FIG. 2 is a schematic flow chart of a method for recommending and intervening goods in an embodiment of the present application;

FIG. 3 is a schematic flow chart of the precise sorting of each recall commodity set in an embodiment of the present application;

FIG. 4 is a schematic flow chart of fusing a placeholder commodity set with a fine-rank commodity set in an embodiment of the present application;

FIG. 5 is a schematic flow chart of responding to a product search request according to a recommended product set in an embodiment of the present application;

fig. 6 is a schematic structural diagram of a commodity recommendation intervention device in an embodiment of the present application;

fig. 7 is a schematic structural diagram of a computer device in an embodiment of the present application.

Detailed Description

In the network architecture shown in fig. 1, the e-commerce platform 82 is deployed in the internet to provide corresponding services to users thereof, and the merchant user terminal device 80 and the consumer user terminal device 81 of the e-commerce platform 82 are similarly connected to the internet to use the services provided by the e-commerce platform. For example, the e-commerce platform can open advertisement delivery service for merchant users of online stores in the e-commerce platform by configuring an advertisement system, and under the condition that the merchant users submit advertisement campaign information, target audiences corresponding to advertisement delivery are determined for the merchant users, and commodity campaign information in the advertisement campaign information is delivered to the corresponding target audiences.

The exemplary e-commerce platform 82 provides matching of supply and demand for products and/or services to the public by means of an internet infrastructure, in the e-commerce platform 82, the products and/or services are provided as merchandise information, and for simplicity of description, the concepts of merchandise, products, etc. are used in this application to refer to the products and/or services in the e-commerce platform 82, specifically, physical products, digital products, tickets, service subscriptions, other off-line fulfillment services, etc.

In reality, each entity of the parties can access the identity of the user to the e-commerce platform 82, and the purpose of participating in the business activity realized by the e-commerce platform 82 is realized by using various online services provided by the e-commerce platform 82. These entities may be natural persons, legal persons, social organizations, etc. The e-commerce platform 82 corresponds to both merchant and consumer entities in commerce, and there are two broad categories of merchant users and consumer users, respectively. The online service can be used in the e-commerce platform 82 by the identity of the merchant user, while the online service can be used in the e-commerce platform 82 by the identity of the consumer, including the real or potential consumer, of the merchant user. In actual business activities, the same entity can perform activities on the identity of a merchant user and the identity of a consumer user, so that the user can flexibly understand the activities.

The infrastructure for deploying the e-commerce platform 82 mainly comprises a background architecture and front-end equipment, wherein the background architecture runs various online services through a service cluster, and the service functions of the background architecture are enriched and perfected by middleware or front-end services facing a platform side, services facing a consumer, services facing a merchant and the like; the head-end equipment primarily encompasses the terminal equipment that the user uses to access the e-commerce platform 82 as a client, including but not limited to various mobile terminals, personal computers, point-of-sale devices, and the like. For example, a merchant user may enter merchandise information for his online store through merchant user terminal device 80 or generate his merchandise information using an open interface of the e-commerce platform; the consumer user can access the webpage of the online store realized by the electronic commerce platform 82 through the consumer user terminal device 81, and trigger the shopping flow through the shopping keys provided on the webpage, and various online services provided by the electronic commerce platform 82 are invoked in the shopping flow, so that the purpose of purchasing is realized.

In some embodiments, the e-commerce platform 82 may be implemented by a processing facility including a processor and memory that stores a set of instructions that, when executed, cause the e-commerce platform 82 to perform the e-commerce and support functions referred to herein. The processing facility may be part of a server, client, network infrastructure, mobile computing platform, cloud computing platform, fixed computing platform, or other computing platform, and provide electronic components of the merchant platform 82, merchant devices, payment gateways, application developers, marketing channels, transport providers, client devices, point-of-sale devices, and the like.

The e-commerce platform 82 may be implemented as online services such as cloud computing services, software as a service (SaaS), infrastructure as a service (IaaS), platform as a service (PaaS), desktop as a service (DaaS), hosted software as a service, mobile back end as a service (MBaaS), information technology management as a service (ITMaaS), and the like. In some embodiments, the various features of the e-commerce platform 82 may be implemented to be adapted to operate on a variety of platforms and operating systems, e.g., for an online store, the administrator user may enjoy the same or similar functionality, whether in the various embodiments iOS, android, homonyOS, web page, etc.

The e-commerce platform 82 may implement its respective independent station for each merchant to run its respective online store, providing the merchant with a respective instance of the commerce management engine for the merchant to establish, maintain, and run one or more of its online stores in one or more independent stations. The business management engine instance can be used for content management, task automation and data management of one or more online stores, and various specific business processes of the online stores can be configured through interfaces or built-in components and the like to support the realization of business activities. The independent station is an infrastructure of the e-commerce platform 82 with cross-border service functionality, and merchants can maintain their online stores more centrally and autonomously based on the independent station. The stand-alone stations typically have merchant-specific domain names and memory space, with relative independence between the different stand-alone stations, and the e-commerce platform 82 may provide standardized or personalized technical support for a vast array of stand-alone stations, so that merchant users may customize their own adaptive commerce management engine instances and use such commerce management engine instances to maintain one or more online stores owned by them.

The online store may implement background configuration and maintenance by the merchant user logging in his business management engine instance with an administrator identity, which, in support of various online services provided by the infrastructure of the e-commerce platform 82, may configure various functions in his online store, review various data, etc., e.g., the merchant user may manage various aspects of his online store, such as viewing recent activities of the online store, updating online store inventory, managing orders, recent access activities, total order activities, etc.; the merchant user may also view more detailed information about the business and visitors to the merchant's online store by retrieving reports or metrics, such as sales summaries showing the merchant's overall business, specific sales and participation data for the active sales marketing channel, etc.

The e-commerce platform 82 may provide a communications facility and associated merchant interface for providing electronic communications and marketing, such as utilizing an electronic message aggregation facility to collect and analyze communications interactions between merchants, consumers, merchant devices, customer devices, point-of-sale devices, etc., to aggregate and analyze communications, such as for increasing the potential to provide product sales, etc. For example, a consumer may have problems with the product, which may create a dialogue between the consumer and the merchant (or an automated processor-based proxy on behalf of the merchant), where the communication facility is responsible for interacting and providing the merchant with an analysis of how to increase sales probabilities.

In some embodiments, an application program suitable for being installed to a terminal device may be provided to serve access requirements of different users, so that various users can access the e-commerce platform 82 in the terminal device through running the application program, for example, a merchant background module of an online store in the e-commerce platform 82, and in the process of implementing the business activity through the functions, the e-commerce platform 82 may implement various functions related to supporting implementation of the business activity as middleware or online service and open corresponding interfaces, and then implant a tool kit corresponding to the interface access function into the application program to implement function expansion and task implementation. The commerce management engine may include a series of basic functions and expose those functions through APIs to online service and/or application calls that use the corresponding functions by remotely calling the corresponding APIs.

Under the support of the various components of the commerce management engine instance, the e-commerce platform 82 may provide online shopping functionality, enabling merchants to establish contact with customers in a flexible and transparent manner, consumer users may purchase items online, create merchandise orders, provide delivery addresses for the items in the merchandise orders, and complete payment confirmation of the merchandise orders. The merchant may then review and fulfill or cancel the order. The audit component carried by the business management engine instance may enable compliance use of the business process to ensure that the order is suitable for fulfillment prior to actual fulfillment. Orders can sometimes be fraudulent, requiring verification (e.g., identification card checking), a payment method that requires the merchant to wait to ensure funds are received can act to prevent such risk, and so on. The order risk may be generated by fraud detection tools submitted by third parties through an order risk API or the like. Before fulfillment, the merchant may need to acquire payment information or wait to receive payment information in order to mark the order as paid before the merchant can prepare to deliver the product. Such as this, a corresponding examination can be made. The audit flow may be implemented by a fulfillment component. Merchants can review, adjust the job, and trigger related fulfillment services by way of fulfillment components, such as: through manual fulfillment services, use when a merchant picks and packages a product in a box, purchases a shipping label and enters its tracking number, or simply marks an item as fulfilled; a custom fulfillment service that may define sending emails for notification; an API fulfillment service that may trigger a third party application to create a fulfillment record at a third party; a legacy fulfillment service that may trigger custom API calls from a business management engine to a third party; the gift card fulfills the service. Generating a number and activating the gift card may be provided. Merchants may print shipping slips using an order printer application. The fulfillment process may be performed when the items are packaged in boxes and ready for shipment, tracking, delivery, verification by the consumer, etc.

It can be seen that the service provided by the e-commerce platform is based on the fact that products are expanded as cores, corresponding commodity data are basic data of the e-commerce platform, commodity information is provided through the commodity data, mining and utilization of the commodity data are bases for realizing various technical services, and basic services are provided for operation of an advertisement system by utilizing user transaction data and commodity data in the commodity data of the e-commerce platform. Therefore, the advertising system can be operated in any one or more servers of the cluster of the e-commerce platform, so that various functions can be realized by utilizing various commodity data provided by the e-commerce platform.

Referring to fig. 2, in some embodiments, the commodity recommendation intervention method of the present application may be implemented as a computer program product, running in a server in an e-commerce platform, including:

step S5100, responding to a commodity searching request, and respectively recalling commodity items matched with the commodity searching request from a plurality of data sources to obtain recalled commodity sets corresponding to the data sources;

the e-commerce platform often displays a plurality of commodity items to a consumer user through a page so as to achieve the purpose of popularization. In an exemplary application scenario, a consumer user accesses a commodity recommendation page of an independent station in an electronic commerce platform through terminal equipment, a plurality of pits are preset in the commodity recommendation page, commodity information of a corresponding commodity item is displayed in each pit, commodity titles, commodity prices and commodity pictures of the commodity item are displayed, the whole pit is linked to a commodity detail page of the commodity item, and when one pit is touched by the user, the user jumps to the commodity detail page of the corresponding commodity item. The commodity recommendation page can be a page specially used for realizing commodity recommendation, can be a commodity detail page of a commodity item currently browsed by a consumer user, can also be a search result page returned after the consumer user inputs a commodity related keyword, and the like.

In general, in the process of accessing a consumer user, a terminal device submits a commodity search request in advance to trigger a server to execute a corresponding commodity search process, and finally returns a corresponding commodity search result, and then the terminal device analyzes and displays commodity information in the commodity search result to each pit. For example, the commodity search request may be automatically triggered to be submitted when the user enters a commodity detail page of a certain commodity item and enters a page specially used for realizing commodity recommendation; or, the commodity searching request can be triggered and submitted by the user after inputting the corresponding keyword or commodity picture in the commodity searching page and confirming the searching operation.

And after receiving a commodity searching request triggered and submitted by a user at the terminal equipment, the server of the electronic commerce platform responds to the commodity searching request to execute commodity recall business logic. In general, the server presets a plurality of data recall channels, each data recall channel corresponds to a corresponding data source, and different data recall channels can use respective corresponding recommendation algorithms to provide commodity items matched with the commodity search request as commodity search results, so as to respectively obtain recall commodity sets formed by the matched commodity items. In an exemplary data recall channel, a data recall interface of the electronic commerce platform can be called, and a collaborative filtering recommendation system is called by means of the data recall interface to execute commodity searching in a commodity database of an independent station serving as a first data source so as to obtain a recall commodity set formed by corresponding matched commodity items; in another exemplary data recall channel, the local cache spam data can be called as a second data source, and the recall commodity set is formed by searching and obtaining commodity items matched with the commodity search request in the second data source by utilizing locally-realized business logic based on rules or collaborative filtering recommendation algorithm. It will be appreciated that a plurality of such data sources may be provided as desired, without being limited by the above examples, whereby, upon receiving a commodity search request, the server invokes the data recall interface corresponding to each data source according to the commodity search request, and may return the corresponding recalled commodity set.

The data stored by each data source may be characterized, for example, the exemplary first data source may be commodity data of a total commodity item on an independent station, and various commodity information of the total commodity item is provided; an exemplary second data source may be ranking data formed by the e-commerce platform making statistics of certain metrics for the total number of items of merchandise at the individual station, such as a list of items of merchandise that have been popular in the last seven days. An exemplary second data source is stored in a local cache and becomes cache spam data, so that the defects caused by data sparseness and cold start can be overcome, and a spam commodity item is provided for a commodity search request. Of course, the data stored by the various data sources and the media in which the data is stored are not limited by the above examples, for example, the data sources may be data sources corresponding to different commodity databases, respectively, the algorithms used in performing data recall on the data sources may be different, and so on, and may be implemented in a flexible manner by those skilled in the art according to the spirit disclosed herein.

When the collaborative filtering recommendation algorithm or the collaborative filtering recommendation system realized by the collaborative filtering recommendation algorithm is used for data recall, the collaborative filtering recommendation algorithm can utilize information carried in the commodity searching request, such as user characteristic information and/or commodity characteristic information, and perform similar commodity matching according to historical record data corresponding to the user characteristic information and historical access data of commodity items corresponding to the commodity characteristic information, so that each commodity item matched with the commodity searching request can obtain a corresponding recall commodity set. Similarly, as long as the data recall interface corresponding to a certain data source can search out matched commodity items from the corresponding data source according to the information carried by the commodity search request to construct a recall commodity set, the subsequent process of the application can be served without being limited by a specific adopted algorithm.

Step S5200, acquiring a occupying commodity set, deleting commodity items in each recall commodity set, which are overlapped with the occupying commodity set, wherein the occupying commodity set comprises at least one commodity item and a to-be-occupied position thereof;

a space-occupying commodity set can be preset in the server, and the space-occupying commodity set can be edited and determined in advance by an operation user of the independent station, a management user of the e-commerce platform or any other legal authorized user. In the occupied commodity set, one or more commodity items are stored, and each commodity item is assigned with a to-be-occupied position, wherein the to-be-occupied position is used for representing a specific pit position in a plurality of pits in a commodity recommendation page, namely, the to-be-occupied position points to the plurality of pits in the commodity recommendation page, and the ordering position is the same as the to-be-occupied position, so that the commodity item is to be displayed in the pit in which the ordering position corresponding to the to-be-occupied position is located.

The items in the recalled item sets obtained from the data sources can be further sorted accurately, so that the item most matched with the item search request can be displayed more forward, but the item in the occupied item set is finally displayed in the designated pit in the item recommendation page, in this case, the item in the occupied item set can not participate in sorting of the items in the recalled item sets, and therefore, for the repeated items which are simultaneously present in the occupied item set and also in any one of the recalled item sets, the repeated items in the recalled item set are deleted, only the repeated items are reserved in the occupied item set, duplication elimination is realized, and the items in the occupied item set are not present in the recalled item sets any more.

And deleting the commodity items in the occupied commodity set from each recall commodity set, so that repeated recommendation of the same commodity item in the final recommended commodity set can be avoided, the independence of the commodity items in the occupied commodity set can be maintained, and after the recall commodity set is subjected to fine sorting to obtain the fine-arranged commodity set, each commodity item is accurately inserted into a pit corresponding to the fine-arranged commodity set according to the to-be-occupied position of each commodity item in the occupied commodity set.

In one embodiment, the occupied commodity set does not have repeated commodity items, but two or more recall commodity sets have the same commodity item, and for the situation, each recall commodity set can be de-duplicated, so that all recall commodity sets have the same commodity item only once, and the uniqueness of each commodity item in all recall commodity sets is maintained, so that the finally obtained fine-ordering commodity set can be ensured not to have repeated commodity items.

Step S5300, performing fine-ranking treatment on all commodity items in all recalled commodity sets according to the intervention display scores correspondingly obtained by the commodity items in all recalled commodity sets to obtain a fine-ranking commodity set;

in order to finish the precise sorting of the multiple recalled commodity items, namely the commodity items in each recalled commodity set, each commodity item in each recalled commodity set can be scored according to the same preset evaluation rule, the intervention display score corresponding to each commodity item is determined, and screening is conducted from all commodity items in all recalled commodity sets according to the intervention display score, so that a precise sorting commodity set is obtained.

Unlike the conventional way of designing the score for the commodity item, the intervention display score can be designed into a dual-purpose index, which is used for measuring the possibility of replacing the corresponding commodity item on one hand and reflecting the potential sales value of the commodity item on the other hand, according to which the evaluation rule of the intervention display score can be set by a person skilled in the art as required, for example, the evaluation rule can be set to perform comprehensive quantitative evaluation according to one or more data indexes in the commodity information of the commodity item to obtain the corresponding intervention display score. When the evaluation rule is designed, each data index related to the characterization of the selling degree in the commodity information can be inspected and determined from the point of whether the commodity is free of sales, so that the data of the corresponding commodity under each data index can be obtained for comprehensive quantification. These data metrics may be flexibly selected as desired, for example, advertisement conversion rate, advertisement click-through rate, etc. of the merchandise item. The respective data indicators may also be indicators related to sales potential of the merchandise items, such as ranking of the merchandise items in a list in an e-commerce platform, profit margin, discount rate, etc. Each data index may be not only numerical data, but also enumeration data or boolean data, for example, may be boolean data representing whether the data belongs to a new product or a main push product, and the data index corresponding to the enumeration data or the boolean data may be mapped into a certain score to participate in comprehensive quantization among the data indexes.

And calculating the intervention display scores of all the commodity items obtained by integrating all the commodity items under all the data indexes according to the scoring rules aiming at all the commodity items in all the recall commodity sets, and combining all the commodity items in all the recall commodity sets into the same data set, wherein all the commodity items are ranked according to the intervention display scores, so that a refined commodity set is obtained.

The intervention presentation score is generally quantified in terms of value, with higher scores representing more potential sales value, more worth being replaced by placeholders, and conversely, lower potential sales value is relatively less likely to be replaced. Accordingly, in the data set obtained by combining the recall commodity sets, the commodity items can be subjected to reverse ordering according to the intervention display scores, so that the commodity items are arranged from high to low to form a fine-arranged commodity set.

In some embodiments, the data set may be further screened, and the commodity items in which the intervention display score does not reach the preset threshold may be deleted, so that only the commodity items in which the intervention display score reaches the preset threshold are reserved to form the fine-ranking commodity set, so as to ensure that the commodity items in the fine-ranking commodity set have higher potential sales value. In further embodiments, the number of pits required to be displayed on the commodity recommendation page of the terminal device is generally determined, and if the total number of commodity items in the fine-arranged commodity set is not equal to the total number of pits in the commodity recommendation page, at this time, the fine-arranged commodity set can be complemented by selecting commodity items from any recall commodity set, so that the total number of commodity items therein reaches the total number of pits.

And S5400, adding the commodity items in the occupied commodity set to the ordering order corresponding to the to-be-occupied order of the commodity items in the fine-arranged commodity set to obtain a recommended commodity set for responding to the commodity search request.

The fine-arranging commodity item already comprises a plurality of commodity items, the occupying commodity set also comprises one or more commodity items, and in order to enable the commodity items in the occupying commodity set to be combined into the fine-arranging commodity set, each commodity item in the occupying commodity set can be inserted into or replaced into a sequencing position of the fine-arranging commodity set corresponding to the position to be occupied of the commodity item according to the position to be occupied designated by the occupying commodity item in the occupying commodity set. The sorting order of each commodity item in the fine-arranged commodity set is determined according to the intervention display score, so that the effect of reflecting the potential sales value is achieved, the commodity items in the occupied commodity set are assigned corresponding inserting or replacing sorting orders through the to-be-occupied order, the commodity items in the occupied commodity set are implanted into the positions with the corresponding potential sales value in the fine-arranged commodity set, the display of the commodity items in the to-be-occupied order precise intervention fine-arranged commodity set assigned in the occupied commodity set is achieved, and therefore the organic fusion of the occupied commodity set and the fine-arranged commodity set is completed, and the recommended commodity set is obtained.

The recommended commodity set can be directly used for responding to a commodity search request submitted by a consumer user, or can be used for responding to the commodity search request after tail cutting and screening are carried out according to a preset rule, for example, according to the total number of pits of a commodity recommendation page at the terminal equipment. When the commodity searching request is responded, each commodity item in the recommended commodity set can be packaged in a format according to a preset format requirement, and then the packaged commodity item is pushed to terminal equipment where a consumer user is located as a commodity searching result to be analyzed and displayed in each corresponding pit of the commodity recommending page, so that the response to the commodity searching request is completed.

From the above embodiments, the present application has a number of technical advantages, including but not limited to:

Considering that when the aim of a plurality of identical commodity items in the finally obtained fine-ordering commodity set is not expected to appear, not only is no repeated commodity item required to be ensured between the occupied commodity set and the recall commodity set, but also is no repeated commodity item required to be ensured between different recall commodity sets, the embodiment adopts a unified algorithm to solve the problem so as to avoid redundancy or repeated duplicate removal operation, and accordingly, on the basis of any embodiment of the method of the application, the commodity item, which is overlapped with the occupied commodity set, in each recall commodity set is deleted, comprises:

Step S5110, acquiring priorities corresponding to the occupied commodity set and each recall commodity set, wherein the occupied commodity set has the highest priority, and each recall commodity set is configured with different priorities according to the data source to which the occupied commodity set belongs;

the server designates the corresponding priority for each data source in advance, regards the occupied commodity set as one data source, sets the corresponding priority and calls the data source when needed. That is, the occupied commodity set and each recall commodity set have their corresponding priorities, wherein the priority of the occupied commodity set is set to the highest priority, and the other recall commodity sets have different priorities according to the importance of the data sources, but are lower than the priority of the occupied commodity set. The priority of each recall commodity set may, for example, set a first data source corresponding to a commodity database of the e-commerce platform to be of a next highest priority, and set a second data source corresponding to local cache spam data to be of a lowest priority, where in this example, the priority relationship after each data source is reflected to each data set is: the occupied commodity set is the recall commodity set of the first data source and the recall commodity set of the second data source.

And step 5120, performing de-duplication processing on the commodity items in the occupied commodity set and the recall commodity sets, and only keeping the repeatedly-appearing commodity items in the set with the highest relative priority, and deleting the repeated commodity items in the set with the lower relative priority.

After the priorities corresponding to the occupied commodity sets and the recall commodity sets are determined, commodity items repeatedly appearing across a plurality of commodity sets are detected according to a unified algorithm, then the repeated commodity items are only reserved in the commodity set with the highest relative priority in each commodity set, and the corresponding repeated commodity items appearing in other commodity sets with lower relative priorities are deleted. After the duplicate removal processing is performed according to the unified algorithm, each commodity item only appears in the commodity set with the relatively highest priority, wherein the commodity item in the occupied commodity set corresponds to the highest priority, so that the commodity item which appears in the occupied commodity set can not be removed when the duplicate is removed, and the fact that the commodity item set by manual intervention can still be fused with the fine-arranged commodity set finally is ensured.

In the above embodiment, the priority is set for the data sources of the occupied commodity set and each recall commodity set, and the unified algorithm is applied to remove the weight of the commodity items according to the priority, so that the commodity items in the occupied commodity set can not be deleted by the weight removing operation, the repeated commodity items in the final fine-arranged commodity set can be effectively avoided, the operation is efficient, and the data is ordered.

On the basis of any embodiment of the method of the present application, please refer to fig. 3, according to the intervention display scores obtained by the corresponding commodity items in each recalled commodity set, performing fine-ranking processing on all commodity items in all recalled commodity sets to obtain a fine-ranking commodity set, including:

step S5210, filtering commodity items in each recall commodity set according to preset filtering conditions;

the recalled commodity sets obtained from the recalls of the data sources may be uneven in quality, and therefore, it is necessary to filter the commodity items in each recalled commodity set so as to remove the false deposit, so that the filtered and retained commodity items can be more effectively matched with the commodity search request.

When filtering each recall commodity set, preset filtering conditions are applied, and the filtering conditions can be flexibly designed, for example, whether any commodity information such as price, sales and the like reaches a corresponding set value or not is filtered, or filtering is performed according to a white list or a black list of commodity items and the like. It will be appreciated that after filtering, the matching degree between the item in each recalled item set and the search condition in the item search request is higher.

Step S5220, calculating intervention display scores of all recalled commodity concentrated commodity items according to a plurality of data indexes of the commodity items;

As disclosed in the foregoing embodiments, scoring of each item of merchandise may be achieved by specifying multiple data metrics with the same scoring rule, so as to determine a filtered intervention presentation score corresponding to each item of merchandise in each recalled merchandise set. Because the intervention display scores of all commodity items are comprehensively quantitatively determined in association with the same data index, although all recall commodity sets come from different data sources, the commodity items among the recall commodity sets are unified in evaluation dimension through the intervention display scores, and the commodity items in all recall commodity sets are comparably realized through the corresponding intervention display scores.

Step S5230, sorting the commodity items in the intermediate commodity set according to the intervention display scores of the commodity items in the intermediate commodity set formed by the recall commodity sets;

in order to achieve precise ordering of all commodity items in each recalled commodity set, all commodity items in each recalled commodity set can be combined into the same data set, and the data set is used as an intermediate commodity set. Considering that the higher the score of the intervention display score is, the higher the potential sales capacity of the commodity item is represented, so that on the basis of the intermediate commodity set, the commodity items are inversely ordered according to the intervention display score, so that the earlier the ordering is, the higher the corresponding potential sales capacity is, and the effect of the pit order in the commodity recommendation page of the terminal equipment is just unified.

And step S5240, screening part of commodity items from the intermediate commodity sets according to the intervention display scores of the commodity items to construct a fine-ranking commodity set.

The intermediate commodity set is obtained by combining and sorting a plurality of recall commodity sets, the total number of pits in the commodity recommendation page of the terminal equipment is limited, and if the intervention display scores of the commodity items in the intermediate commodity set are also indicative of that the popularization value of the corresponding commodity items is possibly not high, further screening can be carried out on the basis of the intermediate commodity set according to the intervention display scores so as to screen the commodity items with higher quality to form the fine-ranking commodity set.

When screening, firstly screening the intermediate commodity set by using a preset threshold value corresponding to the intervention display score, screening commodity items with the intervention display score higher than the threshold value, deleting commodity items with the intervention display score lower than the threshold value, and if the number of the commodity items in the intermediate commodity set exceeds the total number of pits in a commodity recommendation page of the terminal equipment at the moment, performing tail cutting treatment on the intermediate data set according to the total number of pits to obtain a plurality of commodity items with the same total number of pits to form a final fine-arranged commodity set. If the total number of the commodity items in the fine-arranged commodity set does not reach the total number of pits, the commodity items can be obtained from all recall commodity sets to complement the fine-arranged commodity set.

According to the embodiment, in the process of finely arranging the recall commodity sets corresponding to the plurality of data sources after filtering, the intervention display scores of the commodity items play a key role, and after screening the commodity items of each recall commodity set according to the intervention display scores, the constructed finely arranged commodity set is constructed, wherein the commodity items are not only highly matched with the search conditions in the commodity search request, so that the precision of commodity search is improved, but also the sorting order of the commodity items can effectively reflect the potential sales value of the commodity items under the influence of the function of the intervention display scores, so that the operation of leading the commodity items in the correspondingly ordered order in the finely arranged commodity set to be inserted or directly replaced according to the occupation order in the occupation commodity set has the corresponding value.

On the basis of any embodiment of the method, according to a plurality of data indexes of the commodity items, calculating the intervention display scores of the commodity items in the recall commodity sets, wherein the method comprises the following steps:

step S5221, calculating normalized scores of all recall commodity concentrated commodity items under a plurality of preset data indexes;

when the intervention display scores of the commodity items are comprehensively determined for the commodity items in the recall commodity sets according to the data indexes, the normalized scores corresponding to the data indexes of the commodity items can be calculated independently. For ease of operation, the normalized score may be controlled to be in the numerical interval of [0,1 ]. For the case that the data index belongs to the numerical value type, the normalization score can be determined by applying a maximum and minimum normalization mode, and the following formula is referred to:

Wherein,is a numerical value falling within a numerical value interval of 0-1 after normalization treatment; />A current value for a current data indicator; />The minimum value in the index set of the current type data is set; />The maximum value is in the current type data index set.

For the data index belonging to the enumeration type or the boolean type, a mapping relationship between the data and the numerical value can be established, and the mapping relationship can be mapped to the numerical value interval of [0,1] in the same way, so that the mapping relationship can be flexibly set by a person skilled in the art.

And step 5222, taking the preset intervention display probability corresponding to each data index as the weight of the data index, and solving the weighted total score of the normalized scores of each data index of each commodity item to serve as the intervention display score of each commodity item.

When designing the scoring rule of the intervention display score, the intervention display probability corresponding to each data index can be set in advance to represent the weight occupied by each index in the determination of the intervention display score, so that after each commodity item determines the normalized score of each data index, the normalized scores of each data index of each commodity item can be weighted and summarized according to the following formula to obtain a weighted total score as the intervention display score of the commodity item:

Wherein,is commodity item->Is a tamper-evident score of (2); />Data index for the commodity item +.>Normalized score obtained,/->Is the data index in the scoring rule +.>And displaying the probability corresponding to the preset intervention.

In the above embodiment, for each commodity item, the normalized score of each commodity item under the data index is scored according to the maximum value and the minimum value between the values of each commodity item under the same data index, the data of each commodity item under each data index is normalized to the same value interval, and the corresponding preset weight is adapted to each data index, so that the normalized scores of the plurality of data indexes of each commodity item are fused to the same intervention display score, and the intervention display score can effectively quantify the value attribute of each commodity item reflected under the same data index, so that each commodity item can be compared through the respective intervention display score, and the accurate and reliable result of the commodity item is ensured.

On the basis of any embodiment of the method, the method for screening partial commodity items from the intermediate commodity set according to the intervention display scores of the commodity items is constructed as a fine-ranking commodity set and comprises the following steps:

Step S5241, screening a plurality of commodity items with intervention display scores exceeding a preset threshold value from the middle commodity set to form a fine-ranking commodity set;

as disclosed in the foregoing, a plurality of commodity items whose intervention display scores exceed the preset threshold may be directly screened from the intermediate commodity set according to the preset threshold to form a refined commodity set, and if necessary, the total number of commodity items in the refined commodity set may be controlled, for example, the total number of pits in the commodity recommendation page of the terminal device may be controlled not to exceed.

And step S5242, judging whether the total number of the commodity items in the fine-ranking commodity set reaches the preset pit total number, and when the total number of the commodity items does not reach the preset pit total number, extracting the commodity items which are close to the fine-ranking commodity set from the recall commodity set belonging to the fine-ranking commodity set to complement the fine-ranking commodity set, wherein the fine-ranking commodity set comprises a plurality of commodity items with preset ranking relations.

In order to avoid that the total number of the commodity items in the fine-discharge commodity set is insufficient to fill the preset pits in the commodity recommendation page, the total number of the commodity items in the fine-discharge commodity set can be judged, whether the total number of the commodity items reaches the preset pits or not is judged, and when the total number of the preset pits is reached, additional processing is not needed. When the total number of the preset pits is not reached, commodity items can be called from the preset recall commodity set belonging to the ranked commodity set to be supplemented to the fine ranked commodity set. The recalled commodity set belonging to the ranked commodity set can be the cached spam data, namely the second data source. The commodity items contained in the commodity set are ranked and counted according to a certain rule, the ranking relation of the commodity items is determined, and the commodity items can be called according to the ranking order. The ranking basis among the commodity items can be set according to the commodity hot sale degree, commodity click rate, commodity conversion rate and the like as required, and the ranking commodity set can also be directly formed by directly acquiring the electronic commerce ranking list of the electronic commerce platform. When the commodity items are required to be called from the ranked commodity set for supplementing the refined ranked commodity set, the supplementing can be sequentially called according to the ranking order.

In the above embodiment, in order to avoid that the commodity items in the fine-discharge commodity set are insufficient to correspond to each pit in the commodity recommendation page, the recall commodity set belonging to the fine-discharge commodity set calls the commodity items to complement the fine-discharge commodity set, which plays a role of covering the bottom of the fine-discharge commodity set, ensures that the commodity search request can obtain a plurality of commodity items corresponding to the total number of preset pits, avoids the commodity search result from being too narrow, and can overcome the problems of sparse data, cold start and the like.

On the basis of any embodiment of the method of the present application, referring to fig. 4, adding the commodity item in the occupied commodity set to the ordering order corresponding to the to-be-occupied order of the commodity item in the fine-ordering commodity set includes:

step S5410, judging whether the total number of commodity items in the fine-arranged commodity set reaches the preset pit total number;

according to two different situations of whether the total number of the commodity items in the fine-arranged commodity set reaches the preset pit total number of the commodity recommendation page of the terminal equipment, different strategies can be applied to fusion of the occupied commodity set and the fine-arranged commodity set, and accordingly whether the total number of the commodity items in the fine-arranged commodity set exceeds the pit total number is judged first, and a corresponding judgment result is obtained.

Step S5420, when the total number of preset pits is reached, adding the commodity items in the occupied commodity set into the fine-ranking commodity set in an inserting and/or replacing mode according to the corresponding relation between the to-be-occupied positions of the commodity items in the occupied commodity set and the ordering positions in the fine-ranking commodity set so as to obtain a recommended commodity set;

when the judging result shows that the total number of the commodity items in the fine-arranged commodity set reaches the total number of pits, the method shows that the number of the commodity items in the fine-arranged commodity set can fill up the pits in the commodity recommendation page, in this case, in one embodiment, for each commodity item in the occupied commodity set, the commodity items stored in the sorting order corresponding to the to-be-occupied order of the commodity items in the fine-arranged commodity set are replaced, so that the number of the commodity items in the fine-arranged commodity set is ensured not to be increased any more, and the recommended commodity set is obtained. In another embodiment, each item in the occupied-position commodity set may be inserted into the position in the fine-discharge commodity set corresponding to the position to be occupied, the item in the front of the position to be occupied may be inserted first, so that the item in the fine-discharge commodity set is inserted in front and pushed back by one pit, and then the item in the next position to be occupied is inserted correspondingly, and so on, so that the recommended commodity set may be obtained. Meanwhile, the commodity items of the occupied commodity set can be added into the fine-ranking commodity set in an inserting and replacing mode, in one embodiment, the commodity with higher occupation in the occupied commodity set is added into the fine-ranking commodity set in an inserting mode, the commodity with lower occupation in the occupied commodity set is replaced in a replacing mode, and the corresponding cis-ranking commodity after reordering is replaced, so that the recommended commodity set is finally formed.

And step S5430, inserting the commodity items in the occupied commodity set into the sequencing order corresponding to the fine-ranking commodity set according to the to-be-occupied order of the commodity items in the occupied commodity set when the preset pit total number is not reached, so as to obtain the recommended commodity set.

When the judging result shows that the total number of the commodity items in the fine-arranged commodity set does not reach the preset pit total number, the method shows that the number of the commodity items in the fine-arranged commodity set is insufficient to fill the pits in the commodity recommendation page, in this case, for each commodity item in the occupied commodity set, the commodity item is inserted into a sorting order position corresponding to the to-be-occupied order position of the commodity item in the fine-arranged commodity set, the sorting order position and the original commodity items behind the sorting order position are sorted backwards, and the number of the commodity items in the fine-arranged commodity set is increased, so that the corresponding recommended commodity set is obtained.

Of course, in one embodiment, after a single item of the occupied-bit commodity set is inserted into the fine-row commodity set when the preset pit total number is not reached, the method may further return to step S5410 to continue the iterative judgment, and so on until the total number of the commodity items in the fine-row commodity set reaches the preset pit total number, if the total number of the commodity items in the occupied-bit commodity set still has the commodity items to be processed, step S5420 may be executed according to the judgment result, and the remaining commodity items to be processed are replaced into the fine-row commodity set, where the number of the commodity items of the finally obtained recommended commodity set is just equal to the preset pit total number.

According to the embodiment, through analyzing the relation between the total number of the commodity items in the fine-arranged commodity set and the total number of pits in the commodity recommendation page, different strategies can be flexibly applied to insert or replace the commodity items in the occupied commodity set into the fine-arranged commodity set, so that the total number of the commodity items in the fine-arranged commodity set is reasonably controlled, the total number of the commodity items is matched with the total number of pits in the commodity recommendation page as much as possible, and the pits in the commodity recommendation page can be ensured to completely display commodity information of each commodity item.

On the basis of any embodiment of the method of the present application, referring to fig. 5, adding the commodity item in the occupied commodity set to the ordered sequence corresponding to the to-be-occupied sequence of the commodity item in the precisely arranged commodity set, and after obtaining the recommended commodity set for responding to the commodity search request, the method includes:

step S5500, acquiring commodity information of commodity items in the recommended commodity set, wherein the commodity information comprises commodity pictures, commodity titles and commodity page links;

after the search commodity set matched with the commodity search request is determined, the data package is carried out on commodity items in the recommended commodity set according to the requirement of commodity recommendation page display in the terminal equipment, and therefore commodity information corresponding to each commodity item is acquired from a commodity database of the independent station according to the commodity items in the recommended commodity set.

In the present embodiment, the commodity information acquired for each commodity item includes, but is not limited to, a commodity picture, a commodity title, and a commodity page link. The commodity picture is preferably a commodity main picture default set for the commodity item in the commodity database.

S5600, packaging commodity information of commodity items in the recommended commodity set into commodity display information according to a preset format, and associating the commodity display information with ordering positions in the recommended commodity set to construct a commodity display list corresponding to each commodity item in the recommended commodity set;

the method is suitable for displaying the format requirements of commodity information of each commodity item in a recommended commodity set in a commodity recommendation page, and according to the corresponding format, the commodity information of each commodity item in the recommended commodity set can be subjected to data encapsulation, namely, according to a certain preset format, commodity pictures, commodity titles and commodity page links of each commodity item are encapsulated into corresponding commodity display messages, meanwhile, the commodity display messages of each commodity item are associated with ordering positions of the commodity item in the recommended commodity set, so that encapsulation configuration of the commodity information of each commodity item in the recommended commodity set is realized, a corresponding commodity display list is obtained, and the commodity display list can be used for displaying search result data corresponding to a commodity search request.

And step S5700, pushing the commodity display list to terminal equipment submitting the commodity search request, and analyzing and displaying each commodity display message in the commodity display list to pits corresponding to the ordering order in a display page of the terminal equipment by the terminal equipment.

After obtaining the commodity display list corresponding to the commodity search request, the server pushes the commodity display list to the terminal equipment where the consumer user submitting the commodity search request is located, the terminal equipment analyzes the commodity display list to obtain each commodity display message therein, then analyzes each commodity display message correspondingly to obtain commodity information such as commodity pictures, commodity titles, commodity page links and the like of each commodity item and ordering order, and then displays the commodity pictures and commodity titles of each commodity item to positions of commodity recommendation pages corresponding to the ordering order of the commodity item, so that analysis display of the commodity display list is realized, and commodity search results corresponding to the commodity search request are displayed in each position of the commodity recommendation page. And when a user clicks the commodity picture or the commodity title of one pit, the user can jump to the corresponding commodity page link to load the commodity detail page of the corresponding commodity item.

According to the above embodiment, according to the recommended commodity set corresponding to the commodity search request, the commodity information of each commodity item in the recommended commodity set is packaged in a preset format and then is associated with the ordering order of each commodity item, and is synchronized to the terminal equipment for analysis and display, so that the commodity item which is intervened and implanted according to the occupied commodity set can be displayed in the corresponding pit of the commodity recommendation page of the terminal equipment, the manual intervention of the search result recalled by multiple data sources is effectively realized, and the expansion of search business is realized.

Referring to fig. 6, another embodiment of the present application further provides a commodity recommendation intervention apparatus, which includes a data recall module 5100, a commodity duplication removal module 5200, a commodity precision arrangement module 5300, and a space optimization module 5400, where the data recall module 5100 is configured to recall commodity items matched with a commodity search request from a plurality of data sources respectively in response to the commodity search request, and obtain recalled commodity sets corresponding to the data sources; the commodity duplicate removal module 5200 is configured to acquire a occupying commodity set, delete commodity items in each recall commodity set, which are overlapped with the occupying commodity set, wherein the occupying commodity set comprises at least one commodity item and a to-be-occupied position thereof; the commodity fine-ranking module 5300 is configured to perform fine-ranking processing on all commodity items in all recalled commodity sets according to the intervention display scores correspondingly obtained by the commodity items in each recalled commodity set, so as to obtain a fine-ranking commodity set; the occupation optimization module 5400 is configured to add the commodity items in the occupation commodity set to the ordering order corresponding to the to-be-occupied order of the commodity items in the fine-ordering commodity set, so as to obtain a recommended commodity set for responding to the commodity search request.

On the basis of any embodiment of the apparatus of the present application, the commodity deduplication module 5200 includes: the priority determining unit is used for obtaining the priority corresponding to the occupied commodity set and each recall commodity set, wherein the occupied commodity set has the highest priority, and each recall commodity set is configured with different priorities according to the data source to which the occupied commodity set belongs; and the duplicate removal processing unit is used for carrying out duplicate removal processing on the commodity items in the occupied commodity set and the recall commodity sets, keeping the repeatedly-appearing commodity items only in the set with the highest relative priority, and deleting the repeated commodity items in the set with the lower relative priority.

On the basis of any embodiment of the apparatus of the present application, the commodity fine-arranging module 5300 includes: the commodity filtering unit is used for filtering commodity items in the recall commodity sets according to preset filtering conditions;

a score determining unit configured to calculate an intervention display score of each recalled commodity item in the commodity set according to the plurality of data indexes of the commodity item; the sorting processing unit is used for sorting the commodity items in the intermediate commodity set according to the intervention display scores of the commodity items in the intermediate commodity set formed by the recall commodity sets; and the commodity screening unit is used for screening part of commodity items from the middle commodity collection according to the intervention display scores of the commodity items and constructing the commodity items into a fine-ranking commodity collection.

On the basis of any embodiment of the apparatus of the present application, the score determining unit includes: the index quantifying subunit is used for calculating normalized scores of all the recall commodity concentrated commodity items under a plurality of preset data indexes; the weighting scoring subunit is configured to take the preset intervention display probability corresponding to each data index as the weight of the data index, and calculate the weighted total score of the normalized score of each data index of each commodity item to be used as the intervention display score of each commodity item.

On the basis of any embodiment of the apparatus of the present application, the commodity screening unit includes: the scoring preferential subunit is arranged for screening a plurality of commodity items with interference display scores exceeding a preset threshold value from the intermediate commodity set to form a fine-ranking commodity set; and the commodity completion subunit is used for judging whether the total number of commodity items in the refined commodity set reaches the preset pit total number, and when the total number of commodity items does not reach the preset pit total number, extracting commodity items which are close to the top of the refined commodity set from the recall commodity set belonging to the ranked commodity set, and supplementing the refined commodity set, wherein the ranked commodity set comprises a plurality of commodity items with preset ranking relation.

On the basis of any embodiment of the apparatus of the present application, the occupation optimization module 5400 includes: the matching judging unit is used for judging whether the total number of commodity items in the fine-arranged commodity set reaches the preset pit total number or not; the replacement processing unit is used for adding the commodity items in the occupied commodity set into the fine-ranking commodity set in an inserting and/or replacing mode according to the corresponding relation between the to-be-occupied positions of the commodity items in the occupied commodity set and the ordering positions in the fine-ranking commodity set when the total number of the preset pits is reached, so that a recommended commodity set is obtained; and the inserting processing unit is used for inserting the commodity items in the occupied commodity set into the sequencing order corresponding to the fine-ranking commodity set according to the to-be-occupied order of the commodity items in the occupied commodity set when the total number of the preset pits is not reached, so as to obtain the recommended commodity set.

On the basis of any embodiment of the apparatus of the present application, following the operation of the occupation optimization module 5400, the commodity recommendation intervention apparatus of the present application includes: the information acquisition module is used for acquiring commodity information of the commodity items in the recommended commodity set, wherein the commodity information comprises commodity pictures, commodity titles and commodity page links; the message packaging module is used for packaging the commodity information of the commodity items in the recommended commodity set into commodity display messages according to a preset format and associating the commodity display messages with the sequencing order of the commodity information in the recommended commodity set to construct a commodity display list corresponding to each commodity item in the recommended commodity set; the commodity display module is used for pushing the commodity display list to terminal equipment for submitting the commodity search request, and the terminal equipment analyzes and displays each commodity display message in the commodity display list to pits corresponding to the ordering order in a display page of the terminal equipment.

Referring to fig. 7, another embodiment of the present application further provides a computer device, as shown in fig. 7, according to an embodiment of the present application. The computer device includes a processor, a computer readable storage medium, a memory, and a network interface connected by a system bus. The computer readable storage medium of the computer device stores an operating system, a database and a computer program for packaging computer readable instructions, the database can store a control information sequence, and the computer readable instructions can enable the processor to realize a commodity recommendation intervention method when being executed by the processor. The processor of the computer device is used to provide computing and control capabilities, supporting the operation of the entire computer device. The memory of the computer device may have stored therein computer readable instructions that, when executed by the processor, may cause the processor to perform the merchandise recommendation intervention method of the present application. The network interface of the computer device is for communicating with a terminal connection. It will be appreciated by those skilled in the art that the structure shown in fig. 7 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

The processor in this embodiment is configured to execute specific functions of each module and its sub-module in fig. 6, and the memory stores program codes and various data required for executing the above modules or sub-modules. The network interface is used for data transmission between the user terminal or the server. The memory in the present embodiment stores program codes and data required for executing all modules/sub-modules in the commodity recommendation intervention apparatus of the present application, and the server can call the program codes and data of the server to execute the functions of all sub-modules.

The present application also provides a storage medium storing computer readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the merchandise recommendation intervention method of any of the embodiments of the present application.

The present application also provides a computer program product comprising computer programs/instructions which, when executed by one or more processors, implement the steps of the commodity recommendation intervention method of any of the embodiments of the present application.

Those skilled in the art will appreciate that implementing all or part of the above-described methods of embodiments of the present application may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed, may comprise the steps of embodiments of the methods described above. The storage medium may be a computer readable storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).

The foregoing is only a partial embodiment of the present application, and it should be noted that, for a person skilled in the art, several improvements and modifications can be made without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.

In summary, the method and the device utilize the occupation positions designated for the commodity items in the occupied commodity set, implant corresponding commodity items in the corresponding ordering positions of the fine-arranged commodity set obtained by fine-arranging after multi-source recall, realize the intervention of the multi-source recall result, overcome the defects caused by bad factors such as data sparseness, cold start, data preference and the like, realize the optimization of the commodity search result, and help to realize the personalized operation of the commodity search result.

Claims

1. A method of merchandise recommendation intervention, comprising:

adding the commodity items in the occupied commodity set to the ordering order corresponding to the to-be-occupied order of the commodity items in the fine-ranking commodity set to obtain a recommended commodity set for responding to the commodity search request;

the deleting commodity items in each recall commodity set, which are overlapped with the occupied commodity set, comprises the following steps:

acquiring priorities corresponding to the occupied commodity set and each recall commodity set, wherein the occupied commodity set has the highest priority, and each recall commodity set is configured with different priorities according to the data source to which the occupied commodity set belongs;

carrying out de-duplication treatment on the commodity items in the occupying commodity set and the recall commodity sets, only keeping the repeatedly-appearing commodity items in the set with the highest relative priority, and deleting the repeated commodity items in the set with the lower relative priority;

the adding the commodity item in the occupying commodity set to the ordering order corresponding to the to-be-occupied order of the commodity item in the precisely arranged commodity set comprises the following steps:

Judging whether the total number of commodity items in the fine-arranged commodity set reaches the preset pit total number or not;

when the total number of the preset pits is reached, adding the commodity items in the occupied commodity set into the fine-ranking commodity set in an inserting or replacing mode according to the corresponding relation between the to-be-occupied positions of the commodity items in the occupied commodity set and the ordering positions in the fine-ranking commodity set so as to obtain a recommended commodity set;

and when the total number of the preset pits is not reached, inserting the commodity items in the occupied commodity set into the sequencing cis corresponding to the fine-ranking commodity set according to the to-be-occupied cis of the commodity items in the occupied commodity set so as to obtain the recommended commodity set.

2. The commodity recommendation intervention method according to claim 1, wherein the performing fine-ranking processing on all commodity items in all recalled commodity sets according to the intervention display scores obtained by the commodity items in each recalled commodity set, to obtain a fine-ranking commodity set, comprises:

filtering commodity items in each recall commodity set according to preset filtering conditions;

calculating intervention display scores of all recalled commodity items in the commodity set according to a plurality of data indexes of the commodity items;

sorting the commodity items in the intermediate commodity set according to the intervention display scores of the commodity items in the intermediate commodity set formed by the recall commodity sets;

And screening partial commodity items from the intermediate commodity sets according to the intervention display scores of the commodity items to construct a fine-ranking commodity set.

3. The merchandise recommendation intervention method of claim 2, wherein calculating an intervention presentation score for each recalled merchandise item in the merchandise set based on the plurality of data metrics for the merchandise item comprises:

calculating normalized scores of commodity items in all recall commodity sets under a plurality of preset data indexes;

and taking the preset intervention display probability corresponding to each data index as the weight of the data index, and solving the weighted total score of the normalized scores of each data index of each commodity item to serve as the intervention display score of each commodity item.

4. The commodity recommendation intervention method of claim 2, wherein selecting a portion of the commodity items from the intermediate commodity collection according to the intervention display score of the commodity items is configured as a fine-ranked commodity collection, comprising:

screening a plurality of commodity items with intervention display scores exceeding a preset threshold value from the middle commodity set to form a fine-ranking commodity set;

judging whether the total number of commodity items in the fine-ranking commodity set reaches the preset pit total number, and when the total number of commodity items does not reach the preset pit total number, extracting commodity items with the front ranking from the recall commodity set belonging to the ranking commodity set to complement the fine-ranking commodity set, wherein the ranking commodity set comprises a plurality of commodity items with preset ranking relations.

5. The commodity recommendation intervention method according to any one of claims 1 to 4, wherein adding the commodity item in the occupied commodity set to a ranking order corresponding to a to-be-occupied order of the commodity item in the fine-ranked commodity set, to obtain a recommended commodity set for responding to the commodity search request, comprises:

acquiring commodity information of commodity items in the recommended commodity set, wherein the commodity information comprises commodity pictures, commodity titles and commodity page links;

packaging commodity information of the commodity items in the recommended commodity set into commodity display information according to a preset format, and associating the commodity display information with ordering positions in the recommended commodity set to construct a commodity display list corresponding to each commodity item in the recommended commodity set;

pushing the commodity display list to terminal equipment submitting the commodity search request, and analyzing and displaying each commodity display message in the commodity display list to pits corresponding to the ordering order in a display page of the terminal equipment by the terminal equipment.

6. A merchandise recommendation intervention device, comprising:

the occupation optimization module is used for adding the commodity items in the occupation commodity set to the ordering order corresponding to the to-be-occupied order of the commodity items in the fine-arranged commodity set to obtain a recommended commodity set for responding to the commodity search request;

the commodity duplicate removal module comprises:

the priority determining unit is used for obtaining the priority corresponding to the occupied commodity set and each recall commodity set, wherein the occupied commodity set has the highest priority, and each recall commodity set is configured with different priorities according to the data source to which the occupied commodity set belongs;

the duplicate removal processing unit is used for carrying out duplicate removal processing on the commodity items in the occupied commodity set and the recall commodity sets, keeping the repeatedly-appearing commodity items only in the set with the highest relative priority, and deleting the repeated commodity items in the set with the lower relative priority;

The occupation optimization module comprises:

the matching judging unit is used for judging whether the total number of commodity items in the fine-arranged commodity set reaches the preset pit total number or not;

the replacement processing unit is used for adding the commodity items in the occupied commodity set into the fine-ranking commodity set in an inserting and/or replacing mode according to the corresponding relation between the to-be-occupied positions of the commodity items in the occupied commodity set and the ordering positions in the fine-ranking commodity set when the total number of the preset pits is reached, so that a recommended commodity set is obtained;

and the inserting processing unit is used for inserting the commodity items in the occupied commodity set into the sequencing order corresponding to the fine-ranking commodity set according to the to-be-occupied order of the commodity items in the occupied commodity set when the total number of the preset pits is not reached, so as to obtain the recommended commodity set.

7. A computer device comprising a central processor and a memory, characterized in that the central processor is arranged to invoke a computer program stored in the memory for performing the steps of the method according to any of claims 1 to 5.

8. A non-transitory readable storage medium, characterized in that it stores in form of computer readable instructions a computer program implemented according to the method of any one of claims 1 to 5, which when invoked by a computer, performs the steps comprised by the corresponding method.