CN115641191A

CN115641191A - Data pushing method based on data analysis and AI system

Info

Publication number: CN115641191A
Application number: CN202211533839.2A
Authority: CN
Inventors: 秦华辉; 徐荣松
Original assignee: Heze Mudan Yihan Network Technology Co ltd
Current assignee: Guangzhou Yuanxiang E Commerce Co ltd; Guangzhou Yuanxiang Information Technology Co ltd
Priority date: 2022-12-02
Filing date: 2022-12-02
Publication date: 2023-01-24
Anticipated expiration: 2042-12-02
Also published as: CN115641191B

Abstract

According to the data pushing method and the AI system based on data analysis provided by the embodiment of the invention, firstly, an online product pushing information set corresponding to a product pushing information set is obtained, at least one to-be-determined product pushing information set is identified according to the relevance indexes between the product pushing information set and each online product pushing information set, then, a target product pushing information set which is consistent with the product pushing information set and is a subclass of the product pushing information set is identified, and a product pushing information set sequence related to the subclass of the product pushing information set is established through the product pushing information set and the target product pushing information set. In the established product push information set sequence, the product push information sets correspond to the product types with consistency, the relevance indexes accord with the preset relevance indexes, and meanwhile, the product push information sets are consistent, so that the matching degree of the obtained product push information sets is greatly improved, the pertinence of push data is enhanced, and the product conversion rate is improved.

Description

Data pushing method based on data analysis and AI system

Technical Field

The present application relates to the field of data processing, and in particular, to a data pushing method and an AI system based on data analysis.

Background

In e-commerce operation, when a user clicks a product to browse, in order to increase the conversion rate of the e-commerce platform, the platform often pushes other similar product push information related to the product clicking information of the user, so as to increase products entering the user selection category and promote conversion. Therefore, how to reasonably and accurately push product push information is an important point to be considered, in the prior art, for pushed product information, during early analysis, matching elements which are often considered are few, for example, the same type of the same price, however, when a user searches for a product to browse, the considered elements are not limited to the above factors, and therefore, a new accurate and reasonable pushing mode needs to be provided.

Disclosure of Invention

The invention aims to provide a data pushing method and an AI system based on data analysis to solve the problem of inaccurate pushing.

In a first aspect, an embodiment of the present application provides a data pushing method based on data analysis, where the method is applied to a server, where the server is in communication connection with a client, and the method includes:

acquiring at least one online product push information set of a product category to which the product push information set belongs;

determining relevance indexes of the product push information sets and the push information sets of all the products which are on line one by one, and then identifying at least one to-be-determined product push information set of which the relevance indexes meet preset relevance indexes from the at least one to-be-on-line product push information set;

acquiring at least one target product push information set of which the push information set of the to-be-determined product and the push information set of the product are subclasses of the same push information set;

establishing a product push information set sequence related to the subclass of the product push information set, wherein the product push information set sequence covers the product push information set and the target product push information set;

and when a pushing event triggering a product indicated by any product pushing information set in the product pushing information set sequence is detected, pushing the content associated with the product pushing information set sequence to the client.

As an implementation manner, when the product push information set attribute corresponding to the product push information set sequence is a same-series product push information set, the obtaining at least one online product push information set of a product category to which the product push information set belongs includes:

obtaining summary information carried by the product pushing information set;

performing preset indication information identification on the summary information to obtain preset indication information of the product push information set;

determining the product push information set attribute of the product push information set based on the preset indication information;

and when the product push information set attribute indicates that the product push information set is a same series of product push information sets, acquiring at least one online product push information set of the product category to which the product push information set belongs.

As an implementation manner, when the product push information set attribute corresponding to the product push information set sequence is a same-series product push information set, the determining, one by one, a relevance index of the product push information set and each online product push information set includes:

obtaining summary information carried by the online product push information sets one by one, and performing preset indication information identification on the summary information to obtain preset indication information of the online product push information sets;

determining the product push information set attributes of the online product push information sets one by one according to the preset indication information;

identifying the obtained online product push information set in the online product push information set, wherein the attribute of the online product push information set is the online product push information set of the same series of product push information sets;

and determining the relevance indexes of the product push information sets and the online product push information sets of which the product push information sets have the same series of product push information sets in terms of attributes one by one.

As an implementation manner, the determining, one by one, a relevance index of the product push information set and each of the online product push information sets includes:

determining first summary information carried by the product push information set and second summary information carried by each online product push information set;

vector extraction is carried out aiming at the first general information to obtain a first general information vector related to the product pushing information set;

performing vector extraction on second summary information carried by each online product push information set one by one to obtain second summary information vectors related to each online product push information set;

and determining vector relevance indexes of the first summary information vector and each second summary information vector one by one, and taking the vector relevance indexes of the first summary information vector and each second summary information vector as relevance indexes of the product pushing information set and each online product pushing information set.

acquiring product introduction information of the product push information set and product introduction information of each online product push information set;

performing vector extraction on the product introduction information of the product push information set to obtain a first product introduction information vector related to the product push information set;

performing vector extraction on the product introduction information of each online product push information set one by one to obtain a second product introduction information vector related to each online product push information set;

and determining vector relevance indexes of the first product introduction information vector and each second product introduction information vector one by one, and taking the vector relevance indexes of the first product introduction information vector and each second product introduction information vector as relevance indexes of the product push information set and each online product push information set.

As an embodiment, the identifying, from the at least one already-on-line product push information set, at least one pending product push information set whose relevance index meets a preset relevance index includes:

determining at least one online product push information set according to the product push information sets and the relevance indexes of all online product push information sets, wherein the relevance indexes of the online product push information sets accord with preset relevance indexes;

and taking the online product push information set with the relevance index meeting a preset relevance index as an undetermined product push information set with the relevance index meeting the preset relevance index.

As an implementation manner, the obtaining of the target product push information set in which the at least one to-be-determined product push information set and the product push information set are subclasses of a consistent product push information set includes one of the following manners:

acquiring first product push information set portrait information of the product push information set and second product push information set portrait information of each pending product push information set; comparing the first product push information set portrait information with each second product push information set portrait information to obtain a comparison value of the first product push information set portrait information and each second product push information set portrait information; taking the push information set of the undetermined product corresponding to the second product push information set image information with the comparison value meeting the preset comparison value as a target product push information set which is consistent with the product push information set and is a subclass of the product push information set;

or mining summary information carried by the product pushing information set to obtain a first summary block cluster related to the product pushing information set; performing information mining on summary information carried by the pushing information sets of the products to be determined one by one to obtain second summary block clusters related to the pushing information sets of the products to be determined; determining summary block matching results between the first summary block clusters and the second summary block clusters one by one; taking the to-be-determined product push information set corresponding to a second summary block cluster with the summary block matching result reaching the preset matching result as a target product push information set which is a consistent product push information set subclass with the product push information set;

or mining summary information carried by the product pushing information set to obtain a first summary block cluster related to the product pushing information set; performing information mining on summary information carried by each to-be-determined product push information set one by one to obtain a second summary block cluster related to each to-be-determined product push information set; determining preset unified summary blocks between the first summary block clusters and each second summary block cluster and the coverage range of the preset unified summary blocks in the second summary block clusters one by one; and taking the to-be-determined product push information set corresponding to the preset unified summary block with the coverage range exceeding the preset range as a target product push information set which is a subclass of the product push information set and is consistent with the product push information set.

As an embodiment, the establishing a product push information set sequence associated with the product push information set subclass includes one of the following ways:

under the condition that the number of the target product push information sets is multiple, the product push information sets and the online time of each target product push information set are obtained one by one; classifying the product push information sets and all the target product push information sets according to the passing relation of the online time to obtain a first product push information set list; establishing a product push information set sequence associated with the subclass of the product push information set according to the first product push information set list;

or under the condition that the number of the target product push information sets is multiple, acquiring first summary information carried by the product push information sets and second summary information carried by each target product push information set; identifying product series identification indication information aiming at the first summary information to obtain a first product series identification of the product push information set; identifying product series identification indication information of each second summary information to obtain a second product series identification of a target product pushing information set, wherein the product series identification indication information is configured to represent the online time of the corresponding product pushing information set; classifying the product push information set and the plurality of target product push information sets according to identification indication rules of the first product series identification and the second product series identification to obtain a second product push information set list; and establishing a product push information set sequence associated with the subclass of the product push information set according to the second product push information set list.

As an embodiment, the pushing the content associated with the product push information set sequence to the client includes: and pushing the content associated with the product push information set sequence to the client, wherein the associated content comprises a transmission path corresponding to the product push information set sequence and summary information of the product push information set sequence.

In a second aspect, the present application provides a data push AI system, including a server and a client communicatively connected to each other, where the server includes a processor and a memory, where the memory stores a computer program, and when the processor runs the program, the method as provided in the first aspect of the embodiments of the present application is implemented.

In the embodiment of the application, at least one online product push information set of the product category to which the product push information set belongs is obtained, at least one pending product push information set with the relevance index meeting the preset relevance index is identified from less than one online product push information set according to the relevance indexes between the product push information set and each online product push information set, and then a target product push information set which is a consistent product push information set subclass with the product push information set is identified from at least one pending product push information set. In the established product push information set sequence, the product push information sets correspond to the product types with consistency, the relevance indexes accord with preset relevance indexes and are consistent product push information set subclasses, and the matching degree between the obtained product push information sets is greatly improved compared with a simple comparison mode.

In the description that follows, additional features will be set forth, in part, in the description. These features will be in part apparent to those of ordinary skill in the art upon examination of the following and the accompanying drawings or may be learned by production or use. The features of the present application may be realized and attained by practice or use of various aspects of the methodologies, instrumentalities and combinations particularly pointed out in the detailed examples that follow.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

The methods, AI systems and/or procedures in the figures will be further described in accordance with example embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments in which reference numerals represent similar mechanisms throughout the various views of the drawings.

Fig. 1 is a block diagram of a data push AI system, shown in accordance with some embodiments of the present application.

FIG. 2 is a schematic diagram illustrating the hardware and software components in a server according to some embodiments of the present application.

FIG. 3 is a flow diagram illustrating a method of data push based on data analysis according to some embodiments of the present application.

Fig. 4 is a schematic structural diagram of a data pushing apparatus according to an embodiment of the present application.

Detailed Description

In order to better understand the technical solutions, the technical solutions of the present application are described in detail below with reference to the drawings and specific embodiments, and it should be understood that the specific features in the embodiments and examples of the present application are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application, and the technical features in the embodiments and examples of the present application may be combined with each other without conflict.

In the following detailed description, numerous specific details are set forth by way of examples in order to provide a thorough understanding of the relevant guidance. It will be apparent, however, to one skilled in the art that the present application may be practiced without these specific details. In other instances, well-known methods, procedures, AI systems, compositions and/or circuits have been described at a relatively high-level, without detail, in order to avoid unnecessarily obscuring aspects of the present application.

These and other features, functions, methods of execution, and combination of functions and elements of related elements in the structure and economies of manufacture disclosed in the present application may become more apparent upon consideration of the following description with reference to the accompanying drawings, all of which form a part of this application. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the application. It should be understood that the drawings are not to scale. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the application. It should be understood that the drawings are not to scale.

The flowchart is used herein to illustrate the execution process performed by the AI system according to an embodiment of the present application. It should be expressly understood that the processes performed by the flowcharts may be performed out of order. Rather, these implementations may be performed in the reverse order or simultaneously. In addition, at least one other implementation may be added to the flowchart. One or more implementations may be deleted from the flowchart.

Fig. 1 is a block diagram of an AI system architecture of a data-push AI system 300, shown according to some embodiments of the present application, which data-push AI system 300 may include a server 100 and a plurality of clients 200 in communication therewith. The client 200 is a device used by the target user when clicking and receiving the push information, and may be, for example, a personal computer, a notebook computer, a tablet computer, a smart phone, or the like with a network interaction function.

In some embodiments, please refer to fig. 2, which is a schematic diagram of an architecture of a server 100, wherein the server 100 includes a data pushing device 110, a memory 120, a processor 130 and a communication unit 140. The memory 120, processor 130, and communication unit 140 are electrically connected to each other, directly or indirectly, to enable data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The data pushing device 110 includes at least one software function module which may be stored in the memory 120 in the form of software or firmware (firmware) or solidified in an operating AI system (OS) of the server 100. The processor 130 is used for executing executable modules stored in the memory 120, such as software functional modules and computer programs included in the data pushing apparatus 110.

The Memory 120 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. The memory 120 is used for storing a program, and the processor 130 executes the program after receiving the execution instruction. The communication unit 140 is used to establish a communication connection between the server 100 and the client via the network, and to transceive data via the network.

The processor may be an integrated circuit chip having signal processing capabilities. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP)), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

It will be appreciated that the configuration shown in fig. 2 is merely illustrative and that server 100 may include more or fewer components than shown in fig. 2 or have a different configuration than shown in fig. 2. The components shown in fig. 2 may be implemented in hardware, software, or a combination thereof.

Fig. 3 is a flowchart of a data pushing method based on data analysis according to some embodiments of the present application, where the method is applied to the server 100 in fig. 1, and specifically may include the following steps S100 to S500. On the basis of the following steps S100 to S500, some alternative embodiments will be described, which should be understood as examples and should not be understood as technical features essential for implementing the present solution.

S100: and acquiring at least one online product push information set of the product category to which the product push information set belongs.

By establishing a product push information set sequence for a product push information set (an information set introducing pushed products, including multi-part product introduction information), the pertinence and accuracy of product push information set push are improved, and in the process of establishing the product push information set sequence for the product push information set, a plurality of online product push information sets of product categories to which the product push information sets belong can be obtained first. The product category is classification information to which the product push information set belongs, for example, if a product corresponding to the product push information set is bath lotion, the product category may be bath products, it should be noted that, the precision of the product classification here may be adaptively adjusted according to the requirement of the actual push range, for example, the precision is improved for refinement, the product category may be men (women, children) bath products, and if the precision is reduced, the product category may be daily products. It should be noted that the data and information related in the embodiments of the present application are obtained by legal and reasonable means and approaches.

As some possible embodiments, when the product push information set attribute corresponding to the product push information set sequence is a product push information set of the same series (having the same design theme element or the same efficacy or the same manufacturing process, such as an X series XX product, having multiple versions of V1, V2, etc.), at least one online product push information set of a product category to which the product push information set belongs may be obtained by using the following steps: the method comprises the steps of obtaining summary information carried by a product push information set, identifying the summary information through preset indication information to obtain preset indication information of the product push information set, then determining the product push information set attribute of the product push information set according to the preset indication information, and obtaining at least one online product push information set of the product category to which the product push information set belongs under the condition that the product push information set attribute shows that the product push information set is the same series of product push information sets.

Specifically, if the product push information set attribute corresponding to the established product push information set sequence is a product push information set of the same series, in other words, the product push information set attribute of the product push information set in the product push information set sequence is a product push information set of the same series, when an online product push information set of a product category to which the product push information set belongs is acquired, the product push information set attribute of the product push information set is discriminated first. For example, the following steps are involved: the method includes obtaining summary information carried by a product push information set, for example, information briefly described in advance for the product push information set, such as information including a product name, a product efficacy, a product bright spot, and the like, and summary information obtained by extracting target product introduction information (e.g., product introduction information at a preset position) included in the product push information set, then performing preset indication information recognition on the summary information carried by the product push information set to obtain preset indication information of the product push information set, and determining a product push information set attribute of the product push information set according to the preset indication information on the basis of the preset indication information, for example, if the summary information extracted from the product push information set includes preset indication information such as K9s, K9r, K9pro, first generation, second generation, enlarged version, mini version, and the like, the product push information set attribute of the product push information set may be determined to be of the same series, which is only used for reference, and is not used as a basis for limiting other embodiments.

After the product push information set attribute of the product push information set is obtained, if the product push information set attribute indicates that the product push information set is a same-series product push information set, the online product push information set of the product category to which the product push information set belongs can be obtained, and therefore a product push information set sequence of the same-series product push information set is established according to the product push information set. In addition, if the product push information set attribute indicates that the product push information set is not a product push information set of the same series, a product push information set sequence of the product push information sets of the same series cannot be established through the product push information set, and then the online product push information set of the product category to which the product push information set belongs does not need to be acquired.

S200: and determining relevance indexes of the product push information sets and all the online product push information sets one by one, and then identifying at least one undetermined product push information set of which the relevance indexes meet preset relevance indexes from at least one online product push information set.

In step S200, after obtaining a plurality of online product push information sets of the product category to which the product push information set belongs, relevance indexes (degree of forming a relevance) of the product push information sets and the online product push information sets are determined one by one, so that an undetermined product push information set, of which the relevance indexes meet a preset relevance index, is identified in the plurality of online product push information sets. As some possible embodiments, the preset relevance index may be a preset relevance index range, and an online product push information set with a relevance index in the relevance index range is regarded as an pending product push information set, for example, the relevance index range is a first relevance index S1 to a second relevance index S2, S1 < S2 is easy to understand, and then an online product push information set with a relevance index greater than S1 and smaller than S2 is regarded as a pending product push information set.

The online product push information set with the relevance index larger than the second relevance index can be regarded as the same product push information set as the product push information set, and can also be the periphery (sample and matched product) of the product push information set. The online product push information set of the product category may include local information of the current product push information set (such as gift information of the product push information set and associated supporting product information), or the current product push information set may be local information of a product push information set of a certain online product push information set. In this case, after obtaining the relevance index, if the relevance index of the current product push information set and the online product push information set meets a second relevance index, the online product push information set meeting the second relevance index with the current product push information set is taken as a target online product push information set, the information capacity of the current product push information set and the information capacity of the target online product push information set are obtained, then a capacity difference between the two information capacities is calculated, if the capacity difference reaches a preset condition, such as exceeding 20%, a product push information set with a larger information capacity in the current product push information set and the target online product push information set is taken as an undetermined product push information set, and conversely, if the capacity difference does not reach the preset condition, one of the current product push information set and the target online product push information set is randomly obtained as the undetermined product push information set.

As some possible embodiments, the relevance index of the product push information set and each online product push information set may be determined one by one in the following manner:

the method comprises the steps of obtaining first summary information carried by a product pushing information set and second summary information carried by each online product pushing information set, carrying out vector extraction on the first summary information to obtain first summary information vectors related to the product pushing information set, carrying out vector extraction on the second summary information carried by each online product pushing information set one by one to obtain second summary information vectors related to each online product pushing information set, determining vector relevance indexes of the first summary information vectors and each second summary information vector one by one, and taking the vector relevance indexes of the first summary information vectors and each second summary information vector as relevance indexes of the product pushing information set and each online product pushing information set.

In the above steps, when obtaining the relevance indexes of the product push information set and each online product push information set, the relevance indexes may be determined by the product push information set and summary information carried by each online product push information set, where the summary information may be, for example, information briefly described in advance for the product push information set, such as information including a product name, a product efficacy, a product highlight, and the like, and may also be, for example, summary information obtained by extracting target product introduction information (for example, product introduction information at a preset position) included in the product push information set.

For example, first summary information carried by a product push information set and second summary information carried by each online product push information set are obtained, vector extraction is performed on the first summary information to obtain first summary information vectors related to the product push information set, and vector extraction is performed on each second summary information to obtain second summary information vectors related to each online product push information set. The vector extraction process may operate using existing techniques, such as a general vector extraction model for decimation. After a first summary information vector related to the product push information set and a second summary information vector related to each online product push information set are obtained, vector relevance indexes of the first summary information vector and each second summary information vector are determined (for example, determined by calculating a distance or an included angle between vectors), and the vector relevance indexes of the first summary information vector and each second summary information vector are used as relevance indexes of the product push information set and each online product push information set.

As some possible embodiments, the following steps may be used to determine the relevance index of the product push information set and each online product push information set:

the method comprises the steps of obtaining product introduction information of a product push information set and product introduction information of each online product push information set, carrying out vector extraction on the product introduction information of the product push information set to obtain first product introduction information vectors related to the product push information set, carrying out vector extraction on the product introduction information of each online product push information set one by one to obtain second product introduction information vectors related to each online product push information set, determining vector relevance indexes of the first product introduction information vectors and the second product introduction information vectors one by one, and taking vector relevance indexes of the first product introduction information vectors and the second product introduction information vectors as relevance indexes of the product push information sets and the online product push information sets.

In the above step, in the process of obtaining the relevance index of the product push information set and each online product push information set, the relevance index may be determined according to the product push information set and product introduction information (including, but not limited to, price, online time, product details, evaluation, detail display, and the like) covered by each online product push information set, where the product introduction information may be all product introduction information covered by the product push information set or each online product push information set, or may be screened product introduction information.

The method comprises the steps of firstly obtaining product introduction information of a product push information set and product introduction information of each online product push information set, wherein the product introduction information can be multiple, then carrying out vector extraction on the product introduction information of the product push information set, namely carrying out vector extraction on each product introduction information to obtain an information vector of each product introduction information, carrying out vector extraction on each product introduction information to obtain a first product introduction information vector related to the product push information set, carrying out vector extraction on the product introduction information of each online product push information set, namely carrying out vector extraction on each product introduction information covered by each online product push information set to obtain an information vector of each product introduction information, and carrying out fusion on the information vectors of each product push information set to obtain a second product introduction information vector related to each online product push information set. After a first product introduction information vector related to the product push information set and a second product introduction information vector related to each on-line product push information set are obtained, vector relevance indexes between the first product introduction information vector and each second product introduction information vector are determined, and the vector relevance indexes of the first product introduction information vector and each second product introduction information vector are used as relevance indexes of the product push information set and each on-line product push information set.

As some possible embodiments, if the product push information set attribute corresponding to the product push information set sequence is a same-series product push information set, the following steps may be adopted to determine the relevance index of the product push information set and each online product push information set one by one, as follows:

obtaining summary information carried by the pushing information sets of the products which are on-line one by one, and identifying preset indication information of the summary information to obtain the preset indication information of the pushing information sets of the products which are on-line; according to the preset indication information, determining the product push information set attributes of all the online product push information sets one by one, identifying the obtained online product push information set attributes of the online product push information sets as online product push information sets of the same series of product push information sets, and determining the relevance indexes of the product push information sets and the online product push information sets of which the product push information set attributes are the same series of product push information sets one by one.

In the above step, if the product push information set attribute corresponding to the established product push information set sequence is a same-series product push information set, in other words, the product push information set attribute of the product push information set in the product push information set sequence is a same-series product push information set. When determining the relevance indexes of the product push information sets and the on-line product push information sets, the selection of the same series of product push information sets can be performed on the plurality of on-line product push information sets, and then the relevance indexes of the product push information sets and the on-line product push information sets with the identified product push information set attributes as the same series of product push information sets are calculated, so that the calculation consumption can be reduced, and the requirement on the calculation power is lowered.

As described in detail below, the product push information set attribute of the product push information set may be specifically picked up through the following steps:

the summary information carried by the product push information set is obtained, for example, the summary information is briefly described in advance for the product push information set, for example, the summary information may include information such as a product name, a product efficacy, a product bright spot, and the like, and is obtained by extracting target product introduction information (for example, product introduction information at a preset position) included in the product push information set, and then, preset indication information identification is performed on the summary information carried by the product push information set to obtain preset indication information of the product push information set, so that a product push information set attribute of the product push information set is determined according to the preset indication information. The foregoing has been exemplified and will not be repeated here.

As some possible embodiments, at least one set of push information of the pending product, of which the relevance index meets the preset relevance index, may be identified by:

determining at least one online product push information set according to the product push information sets and the relevance indexes of all online product push information sets, wherein the relevance indexes of the online product push information sets accord with preset relevance indexes, and taking the online product push information sets with the relevance indexes according with the preset relevance indexes as undetermined product push information sets with the relevance indexes meeting preset relevance indexes.

S300: and acquiring at least one target product push information set of which the push information set of the to-be-determined product and the product push information set are consistent to each other and are subclassed.

After the obtained at least one online product push information set is selected through the relevance index, the identified at least one pending product push information set can be further selected, namely, a target product push information set which is at least one pending product push information set and is in the same product push information set subclass with the product push information set is obtained.

As some possible embodiments, the following steps may be taken to obtain at least one target product push information set of which the push information set of the pending product is a subclass of the product push information set and the product push information set is consistent with the push information set of the pending product:

the method comprises the steps of obtaining first product push information set portrait information of a product push information set and second product push information set portrait information of each pending product push information set, comparing the first product push information set portrait information with the second product push information set portrait information respectively to obtain a comparison value of the first product push information set portrait information and the second product push information set portrait information, and using the pending product push information set corresponding to the second product push information set portrait information of which the comparison value meets a preset comparison value as a target product push information set which is consistent with the product push information set in subclass.

When the product push information set is generated, the product push information set can be portrayed to represent the user to which the product push information set is applicable, for example, corresponding product push information set portrayal information (such as a descriptive label) is attached. When a target product push information set which is not less than one undetermined product push information set and is consistent with the product push information set in subclass with the product push information set is obtained, first product push information set portrait information of the product push information set and second product push information set portrait information of each undetermined product push information set are obtained, then the first product push information set portrait information and each second product push information set portrait information are compared respectively to obtain a comparison value of the first product push information set portrait information and each second product push information set portrait information, and the undetermined product push information set corresponding to the second product push information set portrait information with the comparison value meeting a preset comparison value is used as the target product push information set which is consistent with the product push information set in subclass with the product push information set.

As some possible embodiments, at least one target product push information set of the pending product push information set, which is a subclass of the product push information set that is consistent with the product push information set, may be obtained by:

the method comprises the steps of carrying out information mining on summary information carried by a product push information set to obtain first summary block clusters related to the product push information set, carrying out information mining on the summary information carried by each to-be-determined product push information set one by one to obtain second summary block clusters related to each to-be-determined product push information set, and determining summary block matching results between the first summary block clusters and each second summary block cluster one by one; and taking the to-be-determined product push information set corresponding to the second summary block cluster with the summary block matching result reaching the preset matching result as a target product push information set which is consistent with the product push information set and is a subclass of the product push information set.

In addition, the target product push information sets of a plurality of pending product push information sets and product push information sets which are consistent with the product push information sets (lower-level classification than the above product classification, for example, the subclass under the bath product is a child bath product) can be obtained by analyzing the product push information sets and the summary information of the product push information sets.

Specifically, summary information carried by a product push information set is subjected to information mining to obtain a first summary block cluster related to the product push information set, the first summary block cluster comprises a plurality of summary blocks (each word block obtained after the summary information is split), then summary information carried by each to-be-determined product push information set is subjected to information mining to obtain a second summary block cluster related to each to-be-determined product push information set, the second summary block cluster also comprises a plurality of summary blocks, then summary block matching results of the first summary block cluster and each second summary block cluster are determined one by one, for example, the percentage of the same summary block is obtained, then the to-be-determined product push information set corresponding to the second summary block cluster, of which the summary block matching results meet preset matching results, are determined from the to-be-determined product push information sets and serve as a target product push information set subclass which is consistent with the product push information set.

As some possible embodiments, the following steps may be further adopted to obtain at least one target product push information set in the pending product push information set, where the pending product push information set and the product push information set are a subclass of the consistent product push information set:

the method comprises the steps of carrying out information mining on summary information carried by a product push information set to obtain first summary block clusters related to the product push information set, carrying out information mining on the summary information carried by each undetermined product push information set one by one to obtain second summary block clusters related to each undetermined product push information set, determining preset uniform summary blocks between the first summary block clusters and each second summary block cluster and the coverage range of the preset uniform summary blocks in the second summary block clusters one by one, and using undetermined product push information sets corresponding to the preset uniform summary blocks with the coverage range exceeding the preset range as target product push information sets which are consistent with the product push information sets and are subclasses of the product push information sets.

In the above step, a plurality of target product push information sets, in which the to-be-determined product push information set and the product push information set are subclasses of a consistent product push information set, may be obtained by analyzing the summary information of the to-be-determined product push information set and the product push information set. For example, first, information mining is performed on summary information carried by a product push information set to obtain a first summary block cluster related to the product push information set, where the first summary block cluster has a plurality of summary blocks, then, information mining is performed on the summary information carried by each to-be-determined product push information set to obtain a second summary block cluster related to each to-be-determined product push information set, where the second summary block cluster also includes a plurality of summary blocks, and preset unified summary blocks between the first summary block cluster and each second summary block cluster (summary blocks appearing in the first summary block cluster and each second summary block cluster at the same time) are determined one by one, for example, a summary block with the largest length, and a coverage range (occupied percentage) of each preset unified summary block in the second summary block cluster is also obtained, and then, from the plurality of to-be-determined, a product push information set corresponding to the preset unified summary block whose coverage range exceeds the preset range is determined to be a product push information set that is consistent with the product push information set as a product push information set that is a subclass of the product push information set.

S400: and establishing a product push information set sequence of related product push information set subclasses.

In the present application, the product push information set sequence covers a product push information set and a target product push information set.

As some possible embodiments, the following steps may be taken to establish a product push information set sequence associated with a product push information set subclass:

the method comprises the steps of obtaining product push information sets and the online time of each target product push information set one by one under the condition that the number of the target product push information sets is multiple, classifying (sorting and sequencing) the product push information sets and the target product push information sets according to the hierarchical relation of the online time to obtain a first product push information set list, and establishing a product push information set sequence related to subclasses of the product push information sets according to the first product push information set list.

In the above step, in the process of establishing the product push information set sequence associated with the product push information set subclass according to the product push information set and the target product push information set, the product push information set and the target product push information set may be classified, for example, the product push information set sequence of the same series may be classified, for example, V1 and V2, according to the order of online, so as to facilitate the user to select the product push information set. For example, in the process of sorting and ranking the product push information sets and the target product push information sets, the online time of the product push information sets and the online time of each target product push information set can be obtained one by one, then the product push information sets and the target product push information sets are classified according to the hierarchical relation of the online time to obtain a first product push information set list, and finally a product push information set sequence is established through the first product push information set list.

As some possible embodiments, a product push information set sequence associated with a product push information set subclass may be established based on:

under the condition that the number of the target product push information sets is multiple, first summary information carried by the product push information sets and second summary information carried by each target product push information set are obtained, product series identification indication information identification is carried out on the first summary information to obtain first product series identifications of the product push information sets, then product series identification indication information identification is carried out on each second summary information to obtain second product series identifications of the corresponding target product push information sets, the product push information sets and the multiple target product push information sets are classified according to identification indication rules (such as sequence indication relation, size relation, containment relation and the like of the identifications) of the first product series identifications and the second product series identifications to obtain a second product push information set list, and a product push information set sequence of the subclass associated product push information sets is established through the second product push information set list. In the present application, the product series identification indication information is configured to represent the online time of the corresponding product push information set.

The above steps can be specifically sorted and classified through the product push information set and the summary information of the target product push information set. For example, first summary information carried by a product push information set and second summary information carried by each target product push information set are obtained, product series identification indication information identification is performed on the first summary information to obtain first product series identifications of the product push information set, product series identification indication information identification is performed on each second summary information to obtain second product series identifications of the corresponding target product push information sets, and then the product push information sets and the plurality of target product push information sets are sorted and classified according to identification indication rules of the first product series identifications and the second product series identifications to obtain a second product push information set list.

As some possible embodiments, a product push information set sequence associated with a product push information set subclass may be established by:

under the condition that the number of the target product push information sets is multiple, obtaining the product push information sets and the online time of each target product push information set one by one, determining the time interval of any two online times in each online time, if the determined time interval has the time interval smaller than the preset time interval, respectively identifying the product series identification indication information of the product push information sets and each target product push information set, obtaining the corresponding product series identification, classifying the product push information sets and each target product push information set according to the identification indication rule to obtain a third product push information set list, and establishing a product push information set sequence related to the subclass of the product push information sets according to the third product push information set list. The product series identification indication information is configured to represent the online time of the corresponding product push information set.

In the embodiment of the application, the online of the product push information set may not be performed according to the series sequence of the product push information set, for example, the second generation of the product push information set is online earlier than the first generation, and then the classification according to the online time is unreasonable. At this time, the online time and the summary information of the product push information set can be integrated for classification. For example, a product push information set and the online time of each target product push information set are obtained one by one, the time interval of any two online times in each online time is determined, if the determined time interval has a time interval smaller than a predetermined time interval, product series identification indication information identification is performed on the product push information set and each target product push information set respectively, corresponding product series identifications are obtained, the product push information sets and each target product push information set are classified according to identification indication rules to obtain a third product push information set list, and finally a product push information set sequence related to a product push information set subclass is established according to the third product push information set list.

As a possible situation, if there is no time interval smaller than the predetermined time interval, the product push information sets and the target product push information sets are directly classified according to the online time to obtain a fourth product push information set list, and a product push information set sequence associated with the product push information set subclasses is established.

S500: and when a pushing event triggering a product indicated by any product pushing information set in the product pushing information set sequence is detected, pushing content related to the product pushing information set sequence.

As some possible embodiments, it can be understood that the following steps are used to push the content associated with the product push information set sequence:

and pushing the content associated with the product push information set sequence to the client. The associated content comprises a transmission path corresponding to the product push information set sequence and summary information of the product push information set sequence.

In the above steps, when a user browses any product push information set in the product push information set sequence, the client responds to a request of the user, such as clicking, searching, and the like, to display contents, such as price, online time, product details, product evaluation, detail display, and the like, covered by any product push information set in the product push information set sequence, and sends a push trigger instruction to the server, and after the server obtains the push trigger instruction, the server pushes contents associated with the product push information set corresponding to the product push information set and the product push information set sequence to which the product push information set belongs, where the associated contents are contents for pushing the product push information set sequence, and may include introduction information of the product push information set sequence and a transmission path (the display form may be a link) corresponding to the product push information set sequence.

Further, after the product push information set sequence of the associated product push information set subclass is established through the above embodiment, if a new online product push information set of the same product category is obtained, a relevance index of the new online product push information set and any product push information set in the product push information set sequence is determined, if the relevance index meets a preset relevance index, it is determined whether the product push information set of the new online product push information set corresponds to the product push information set subclass of the product push information set sequence, and if so, the new online product push information set is merged into the established product push information set sequence.

The method comprises the steps of obtaining at least one online product push information set of a product category to which a product push information set belongs, identifying at least one undetermined product push information set of which the correlation index meets a preset correlation index from the less than one online product push information set according to the correlation index between the product push information set and each online product push information set, identifying a target product push information set of which the correlation index meets the preset correlation index from the at least one online product push information set, and establishing a product push information set sequence of a related product push information set subclass through the product push information set and the target product push information set.

In the embodiment of the application, because the product push information sets correspond to the product categories with consistency in the established product push information set sequence, and the relevance indexes meet the preset relevance indexes and are consistent product push information set subclasses, compared with a simple comparison mode, the matching degree between the obtained product push information sets is greatly improved, so that when a push event of a product which is indicated by any one of the product push information sets in the product push information set sequence is detected, the content related to the product push information set sequence is pushed, and during browsing the product push information sets by a user, the similar product push information sets which are highly matched with the product push information sets and are consistent product push information set subclasses can be continuously browsed through the related content, thereby enhancing the push pertinence and improving the product conversion rate.

Referring to fig. 4, which is a schematic structural diagram of a data pushing device 110 according to an embodiment of the present invention, the data pushing device 110 may be used for executing a data pushing method based on data analysis, wherein the data pushing device 110 includes:

the product push information set obtaining module 111 is configured to obtain at least one online product push information set of a product category to which the product push information set belongs.

The relevance index determining module 112 is configured to determine relevance indexes of the product push information sets and the push information sets of the online products one by one, and then identify at least one push information set of the pending products, of which the relevance indexes meet preset relevance indexes, from at least one push information set of the online products.

The target determining module 113 is used for acquiring at least one target product push information set of which the to-be-determined product push information set and the product push information set are subclasses of the same product push information set;

the establishing module 114 is used for establishing a product push information set sequence related to a product push information set subclass, wherein the product push information set sequence covers a product push information set and a target product push information set;

the pushing module 115, when detecting a pushing event of a product indicated by any product pushing information set in the product pushing information set sequence, pushes content associated with the product pushing information set sequence to the client.

The product push information set acquisition module 111 may be configured to perform step S100; the relevance indicator determining module 112 may be configured to perform step S200; the target determination module 113 may be configured to perform step S300; the establishing module 114 may be configured to perform step S400; the pushing module 115 may be configured to perform step S500.

Since the data pushing method based on data analysis provided in the embodiment of the present invention has been described in detail in the above embodiment, and the principle of the data pushing device 110 is the same as that of the method, the implementation principle of each module of the data pushing device 110 is not described herein again.

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

In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.

It should be understood that technical terms not nounced in the above-mentioned contents can be clearly determined by those skilled in the art from the above-mentioned disclosures. The above disclosure of the embodiments of the present application will be apparent to those skilled in the art from the above disclosure. It should be understood that the derivation and analysis of technical terms, which are not explained, by those skilled in the art based on the above disclosure are based on the contents described in the present application, and thus the above contents are not an inventive judgment of the overall scheme.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be considered merely illustrative and not restrictive of the broad application. Various modifications, improvements and adaptations to the present application may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present application and thus fall within the spirit and scope of the exemplary embodiments of the present application.

It should also be appreciated that in the foregoing description of embodiments of the present application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of at least one embodiment of the invention. However, this method of disclosure is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

Claims

1. A data pushing method based on data analysis is applied to a server, the server is in communication connection with a client, and the method comprises the following steps:

determining relevance indexes of the product push information sets and all the online product push information sets one by one, and then identifying at least one undetermined product push information set of which the relevance index meets a preset relevance index from the at least one online product push information set;

2. The method of claim 1, wherein when the product push information set attribute corresponding to the product push information set sequence is a same-series product push information set, the obtaining of not less than one online product push information set of a product category to which the product push information set belongs includes:

obtaining summary information carried by the product pushing information set;

3. The method according to claim 1, wherein when the product push information set attributes corresponding to the product push information set sequence are product push information sets of the same series, the determining the relevance index of the product push information set and each of the online product push information sets one by one includes:

and determining the relevance indexes of the product push information sets and the product push information sets with the attributes of the product push information sets being the online product push information sets of the same series of product push information sets one by one.

4. The method of claim 1, wherein the determining the relevance indicator of the product push information set and each of the online product push information sets comprises:

performing vector extraction on the first general information to obtain a first general information vector related to the product pushing information set;

5. The method of claim 1, wherein the determining the relevance indicator of the product push information set and each of the online product push information sets comprises:

6. The method of claim 1, wherein the identifying, from the at least one already-online product push information set, at least one pending product push information set whose relevance index meets a preset relevance index comprises:

7. The method of claim 1, wherein the obtaining the at least one pending product push information set and the target product push information set for which the product push information set is a subclass of consistent product push information sets comprises one of:

or mining summary information carried by the product pushing information set to obtain a first summary block cluster related to the product pushing information set; performing information mining on summary information carried by the pushing information sets of the products to be determined one by one to obtain second summary block clusters related to the pushing information sets of the products to be determined; determining summary block matching results between the first summary block clusters and the second summary block clusters one by one; the method comprises the steps that a to-be-determined product push information set corresponding to a second summary block cluster with a summary block matching result reaching a preset matching result is used as a target product push information set which is a subclass of a product push information set consistent with the product push information set;

or performing information mining on summary information carried by the product push information set to obtain a first summary block cluster related to the product push information set; performing information mining on summary information carried by each to-be-determined product push information set one by one to obtain a second summary block cluster related to each to-be-determined product push information set; determining preset unified summary blocks between the first summary block clusters and each second summary block cluster and the coverage range of the preset unified summary blocks in the second summary block clusters one by one; and taking the to-be-determined product push information set corresponding to the preset unified summary block with the coverage range exceeding the preset range as a target product push information set which is a subclass of the product push information set and is consistent with the product push information set.

8. The method of claim 1, wherein the establishing a sequence of product push information sets associated with the subclass of product push information sets comprises one of:

9. The method of claim 1, wherein said pushing the content associated with the product push information set sequence to the client comprises:

and pushing the content associated with the product push information set sequence to the client, wherein the associated content comprises a transmission path corresponding to the product push information set sequence and summary information of the product push information set sequence.

10. A data push AI system, comprising a server and a client communicatively connected to each other, the server comprising a processor and a memory, the memory storing a computer program which, when executed by the processor, implements the method of any one of claims 1 to 9.