CN114387061A

CN114387061A - Product pushing method and device, electronic equipment and readable storage medium

Info

Publication number: CN114387061A
Application number: CN202210033612.5A
Authority: CN
Inventors: 张焱
Original assignee: Ping An Puhui Enterprise Management Co Ltd
Current assignee: Ping An Puhui Enterprise Management Co Ltd
Priority date: 2022-01-12
Filing date: 2022-01-12
Publication date: 2022-04-22

Abstract

The invention relates to an artificial intelligence technology, and discloses a product pushing method, which comprises the following steps: obtaining historical voice data of a target user, identifying user emotion from the historical voice data according to a preset emotion identification model, extracting user attribute features and user behavior features from historical user information, constructing user figures according to the user emotion, the user attribute features and the user behavior features, clustering the user figures to obtain user clustering labels, performing text screening on product information to obtain product labels, performing similarity clustering processing on the user clustering labels and the product labels, performing relevance arrangement on clustering results, and performing product pushing on the target user according to arrangement results. Furthermore, the invention relates to a blockchain technique, the permutation result being storable in a node of the blockchain. The invention also provides a product pushing method and device, electronic equipment and a computer readable storage medium. The invention can solve the problem of low product pushing accuracy.

Description

Product pushing method and device, electronic equipment and readable storage medium

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to a product pushing method and device, electronic equipment and a computer readable storage medium.

Background

The intelligent recommendation method has the advantages that the intelligent recommendation method is applicable to scenes such as typical e-commerce, short videos and advertisements, information can be accurately pushed according to real-time characteristics and requirements of users, and the accuracy of information pushing can be improved. However, in some specific fields (such as financial fields), the processes have not been fully developed, for example, in a usage scenario of securities APPs, currently, mainstream securities APPs have complex pages, a large amount of data, articles and messages are accumulated, and a user needs to face massive information every day, but it is difficult for real attention and interested product information to be directly presented to the user, which results in inaccurate push of the messages of products, services and the like.

Disclosure of Invention

The invention provides a product pushing method, a product pushing device, product pushing equipment and a storage medium, and mainly aims to solve the problem of low product pushing accuracy.

In order to achieve the above object, the present invention provides a product pushing method, including:

acquiring historical voice data of a target user, performing voice separation on the historical voice data to obtain the voice data of the target user, and recognizing user emotion from the voice data according to a preset emotion recognition model;

acquiring historical user information of the target user, and extracting user attribute characteristics and user behavior characteristics from the historical user information;

constructing a user portrait of the target user according to the user emotion, the user attribute characteristics and the user behavior characteristics, and clustering the user portrait to obtain a user clustering label;

acquiring product information, and performing text screening on the product information to obtain a product label;

and performing similarity clustering processing on the user clustering labels and the product labels to obtain clustering results, performing relevance arrangement on the clustering results at least twice, and pushing products to the target users according to the arrangement results.

Optionally, the performing voice separation on the historical voice data to obtain the voice data of the target user includes:

performing sound channel judgment on the historical voice data, and extracting voice data of a target sound channel in the historical voice data;

and selecting an end point of the voice data of the target sound channel, and performing data cutting on the voice data according to a preset time length and the selected end point to obtain the voice data of the target user.

Optionally, before recognizing the user emotion from the voice data according to the preset emotion recognition model, the method further includes:

acquiring an original training set, and performing data enhancement processing on the original training set to obtain a standard training set;

training a pre-constructed first network model by using the standard training set to obtain an original model;

and taking the parameters of the original model as initialization parameters of a pre-constructed second network model, and training the second network model by using the standard training set to obtain the emotion recognition model.

Optionally, the extracting the user attribute features and the user behavior features from the historical user information includes:

acquiring a preset user attribute label and a user behavior label;

and taking the characteristics corresponding to the user attribute labels in the historical user information as the user attribute characteristics, and taking the characteristics corresponding to the user behavior labels in the historical user information as the user behavior characteristics.

Optionally, the clustering the user portraits to obtain a user clustering label includes:

performing vector mapping on the features in the user image by using a preset language model to obtain a feature vector set;

randomly selecting a preset number of user samples from the characteristic vector set as a clustering center;

sequentially calculating the distance from each user sample in the characteristic vector set to the clustering center, and classifying each user sample into the category corresponding to the clustering center with the minimum distance to obtain a plurality of category clusters;

and recalculating the clustering center of each category cluster, returning to the step of sequentially calculating the distance from each user sample in the characteristic vector set to the clustering center until the clustering centers of the plurality of category clusters converge, and taking the category corresponding to the converged category cluster as the user clustering label.

Optionally, the text screening of the product information to obtain a product tag includes:

performing word segmentation processing on the product information by using a preset word segmentation algorithm to obtain a product word segmentation text;

primarily screening the word segmentation texts of the products by using a preset special vocabulary table to obtain word segmentation screening texts;

and performing importance screening on the word segmentation texts in the word segmentation screening texts, and taking the word segmentation texts with the screened importance as the product labels.

Optionally, the performing similarity clustering processing on the user clustering labels and the product labels to obtain clustering results, performing at least two times of correlation arrangement on the clustering results, and performing product pushing on the target user according to the arrangement results includes:

taking the user clustering label as a user clustering center;

calculating the distance from the product label to the user clustering center, and taking the product label with the distance smaller than a preset distance threshold value as a clustering result of the user clustering center;

roughly arranging products corresponding to the product labels in the clustering results and target users corresponding to the user clustering labels to obtain a first related arrangement result;

performing fine ranking processing on the target users and the products in the first related ranking result to obtain a second related ranking result;

and selecting a preset number of products from the second correlation arrangement result and pushing the products to the target user in the second correlation arrangement result.

In order to solve the above problems, the present invention also provides a product pushing apparatus, comprising:

the user emotion recognition module is used for acquiring historical voice data of a target user, performing voice separation on the historical voice data to obtain the voice data of the target user, and recognizing user emotion from the voice data according to a preset emotion recognition model;

the user characteristic extraction module is used for acquiring historical user information of the target user and extracting user attribute characteristics and user behavior characteristics from the historical user information;

the label construction module is used for constructing a user portrait of the target user according to the user emotion, the user attribute characteristics and the user behavior characteristics, clustering the user portrait to obtain a user clustering label, acquiring product information, and performing text screening on the product information to obtain a product label;

and the product pushing module is used for carrying out similarity clustering processing on the user clustering labels and the product labels to obtain clustering results, carrying out relevance arrangement on the clustering results at least twice, and pushing products to the target users according to the arrangement results.

In order to solve the above problem, the present invention also provides an electronic device, including:

a memory storing at least one computer program; and

and the processor executes the computer program stored in the memory to realize the product pushing method.

In order to solve the above problem, the present invention also provides a computer-readable storage medium, in which at least one computer program is stored, and the at least one computer program is executed by a processor in an electronic device to implement the product push method described above.

According to the method, the user emotion of the target user is recognized from the user voice data through the preset emotion recognition model, the user portrait of the target user is constructed according to the user emotion, the user attribute characteristics and the user behavior characteristics, and the user characteristics in the user portrait are richer, so that the user portrait is clustered, and the target user can be classified more accurately. And moreover, the similarity clustering processing is carried out on the user clustering labels and the product labels, clustering is carried out from the two aspects of users and products, and at least two times of relevance arrangement is carried out on clustering results, so that the relevance of the users and the products is further improved, and the pushing of the products is more accurate. Therefore, the product pushing method, the product pushing device, the electronic equipment and the computer readable storage medium provided by the invention can solve the problem of low product pushing accuracy.

Drawings

Fig. 1 is a schematic flow chart of a product pushing method according to an embodiment of the present invention;

FIG. 2 is a functional block diagram of a product pushing apparatus according to an embodiment of the present invention;

fig. 3 is a schematic structural diagram of an electronic device implementing the product pushing method according to an embodiment of the present invention.

The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.

Detailed Description

It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

The embodiment of the application provides a product pushing method. The execution subject of the product pushing method includes, but is not limited to, at least one of electronic devices such as a server and a terminal, which can be configured to execute the method provided by the embodiments of the present application. In other words, the product push method may be performed by software or hardware installed in the terminal device or the server device, and the software may be a block chain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.

Fig. 1 is a schematic flow chart of a product pushing method according to an embodiment of the present invention.

In this embodiment, the product pushing method includes:

s1, obtaining historical voice data of a target user, carrying out voice separation on the historical voice data to obtain the voice data of the target user, and recognizing the emotion of the user from the voice data according to a preset emotion recognition model.

In the embodiment of the present invention, the historical voice data refers to voice data of a user and customer service during trading or after-sales service, for example, in the field of finance, the historical voice data may be voice data of the user about stock trading and communication between customer service staff, which are already available in a stock company. The target user may be a target group of people selected from the user information table, for example, 10 ten thousand people or a certain person selected from the user information table of a bank as the target user.

Specifically, the performing voice separation on the historical voice data to obtain the voice data of the target user includes:

In the embodiment of the present invention, the target channel may be a left channel or a right channel.

For example, in the banking field, since the historical speech data is a recording of a user and a customer service, only two parties are involved in a call, and the audio is a two-channel audio, where a left channel is a seat (customer service) audio and a right channel is a user audio, the right channel is directly selected as a target channel, and the right channel speech data is extracted.

Optionally, Voice endpoint Detection (VAD) technology may be used to perform Voice endpoint selection on the right channel Voice data, in practical applications, the Voice data to be detected often contains invalid sounds, such as noise and other speaking sounds, and the VAD technology may accurately locate the start and end points of the Voice from the noisy Voice, that is, remove the silence and the noise as interference signals from the original data.

In the embodiment of the present invention, the preset time length may be 1s, and the right channel speech data is cut into a plurality of pieces by taking 1s as a unit, wherein if the last piece of audio is less than 1s, the filling is performed based on the average value of the piece of audio until the length is 1 s.

In detail, before the user emotion is recognized from the voice data according to a preset emotion recognition model, the method further includes:

In an optional embodiment of the present invention, the original training set may be a CASIA chinese emotion corpus, and a mixed class (Mixup) enhancement method may be used to perform data enhancement on the original training set. The first network model may be a ResNet50 network and the second network model may be a modified ResNet50 network, the improvement being: the first layer and the last layer of the ResNet50 network are removed, a batch training (BatchNormal) layer, a convolutional layer (with an activation function of relu) and an average pooling layer are added before the ResNet50 network, and a full connection layer (with an activation function of relu), a batch training (BatchNormal) layer and a last full connection layer are added after the ResNet50 network.

S2, obtaining historical user information of the target user, and extracting user attribute features and user behavior features from the historical user information.

In the embodiment of the invention, the historical user information comprises the basic information and the transaction behavior information of the user.

In detail, the extracting user attribute features and user behavior features from the historical user information includes:

acquiring a preset user attribute label and a user behavior label;

In an alternative embodiment of the present invention, the user attribute tag is used to represent a social attribute of the user, for example, in the financial field, based on information when the user opens a security account, and the user attribute tag includes: gender, age, education, etc.

The user behavior tag is used to represent transaction attributes of a user, for example, in the financial field, and according to transaction data of the user, the user behavior tag includes: market segment preferences, transaction frequency, transaction amount, user risk preferences, and the like.

Optionally, for example, the user attribute features of the user a include: sex: male, age: 24. and (3) education degree: in this department, the user transaction characteristics include: market panel preferences: medical treatment and transaction frequency: high, trade limit: 1000. user risk preference: medium, etc.

S3, constructing the user portrait of the target user according to the user emotion, the user attribute characteristics and the user behavior characteristics, and clustering the user portrait to obtain a user clustering label.

In the embodiment of the invention, the user image comprises the emotional characteristics of the user, the attribute characteristics of the user and the behavior characteristics of the user, so that the description of the user is more accurate, and the accuracy of recommending products to the user can be improved.

Specifically, the clustering the user portrait to obtain a user clustering label includes:

In the embodiment of the present invention, the preset language model may be a bert model, a RoBERTa model, or the like. The distance may be an euclidean distance, a manhattan distance, a chebyshev distance, or the like.

In detail, the calculating the cluster center of each category cluster includes:

calculating the cluster center of each category cluster by the following clustering formula:

wherein E is_iIs the ith cluster center, C_iIs the ith category cluster, and x is the user sample in the category cluster.

In another optional embodiment of the present invention, the clustering process may also be performed using a mean shift clustering method, a density-based clustering method (DBSCAN), a maximum Expectation (EM) clustering method using a Gaussian Mixture Model (GMM), and the like. For example, in the financial field, the user cluster labels include love for new, love for short-line operations, love for stock of small-disk concepts, love for buying funds, and the like.

Furthermore, the user portrait comprises richer user characteristics, so that the users can be classified more accurately through clustering processing, and the accuracy of product pushing is improved.

And S4, acquiring product information, and performing text screening on the product information to obtain a product label.

In the embodiment of the present invention, the product information includes a product category, a product description, and the like.

Specifically, the text screening of the product information to obtain a product label includes:

In the embodiment of the present invention, the preset word segmentation algorithm may be any existing word segmentation method, such as NLPIR calculated by chinese academy, LTP of hadamard, tsulac of qinghua university, jiba word segmentation, stanford word segmentation, and the like.

Optionally, the preset proprietary vocabulary table may be a financial product proprietary vocabulary table arranged by a financial domain expert. And calculating the importance of each word in the word segmentation screening text by using a TF-IDF algorithm, sequencing the word segmentation texts according to the importance, and selecting the word segmentation texts in a preset proportion as the product labels.

In the embodiment of the invention, the word segmentation is carried out by the word segmentation algorithm, the primary screening is carried out by utilizing the special vocabulary table, and the importance screening is carried out by utilizing the TF-IDF algorithm, so that the accuracy of selecting the product label can be improved.

S5, carrying out similarity clustering processing on the user clustering labels and the product labels to obtain clustering results, carrying out relevance arrangement at least twice on the clustering results, and carrying out product pushing on the target users according to the arrangement results.

In the embodiment of the invention, the user and the product are matched according to the user clustering label and the product label, and the accuracy of product pushing can be improved by simultaneously clustering and correlatively arranging from two aspects of the user and the product.

Here, the relevance refers to the degree of association with the user cluster label. Specifically, the relevance arrangement refers to semantic understanding of the user clustering labels and the product labels, and the product labels with high relevance to the user clustering labels are arranged from large to small, so that the products can be pushed to the user from high to low according to the sequence of the relevance sizes, and the accuracy of product pushing is improved.

In detail, the clustering the similarity of the user clustering label and the product label to obtain a clustering result, performing at least two times of correlation arrangement on the clustering result, and performing product push on the target user according to the arrangement result includes:

taking the user clustering label as a user clustering center;

In the embodiment of the present invention, the rough ranking refers to roughly selecting a hundred-level number of products from ten-thousand-level products, for example, in an advertisement pushing scenario, because there are ten-thousand-level advertisement numbers, direct pushing is not only low in accuracy but also low in processing efficiency of a large amount of data, and therefore hundreds of target advertisements with high relevance need to be screened from the ten-thousand advertisements for arrangement. The rough ranking can be a depth model based on vector inner product, generally has a double-tower structure, user features and product features are respectively input at two sides, user vectors and product vectors are respectively output after depth network calculation, relevant ranking scores are obtained through inner product and other calculation, and first relevant sequence results of users and products are obtained according to the relevant ranking scores.

The fine ranking refers to further fine sequencing of the sequences after the coarse ranking, and the fine ranking can be arranged through algorithms such as LR, DT, SVM, CTR models and the like.

For example, the user cluster labels and their corresponding users include: label 1: user1, label 2: user2, label 3: user3 and label 4: user4, the product corresponding to the product label includes: and the item1, item2, item3 and item4 sequentially use the label1, label2, label3 and label4 as user clustering centers, and respectively calculate the distances (cosine distances and the like) from the item1, the item2, the item3 and the item4 to the four labels to obtain clustering results: label 1: item1, item2, item3, and item 4; label 2: item1, item2, item3, and item 4; label 3: item1, item2, item3, and item 4; label 4: the item1, item2, item3 and item4, roughly arrange the user clustering labels and the corresponding product labels in each clustering result, and the first related arrangement result after the rough arrangement processing is: user 1: item1, item2, item 3; user 2: item2, item3, item 4; user 3: item3, item4, item 1; user 4: item4, item1, item 2. And then, performing fine ranking on the user and the product labels in the first related ranking result, and performing more accurate product related ranking on the user through the fine ranking, for example, the second related ranking result after the fine ranking includes: user 1: item1, item 2; user 2: item2, item 3; user 3: item 3; user 4: item4, item 1. Then item1 or item2 can be pushed to user1, item2 or item3 to user2, item3 to user3, and item4 or item1 to user4, respectively.

In detail, the calculating the distance from the product label to the user cluster center includes:

taking the user clustering center as a target label, sequentially selecting any one of the product labels as a comparison label, and performing word segmentation processing on the target label and the comparison label to obtain a target list and a comparison list;

constructing a coding dictionary according to the target list and the comparison list;

vector coding is carried out on the target list and the comparison list by utilizing the coding dictionary to obtain a target vector and a comparison vector;

and calculating the target similarity of the target vector and the comparison vector by using a preset cosine similarity calculation formula, and determining the target similarity as the distance from the product label to the user clustering center.

In an alternative embodiment of the present invention, the similarity is calculated using the following formula:

wherein a is the target vector and b is the comparison vector.

In the embodiment of the invention, the clustering is carried out through the user clustering label and the product label, which is equivalent to the preliminary matching of the user and the product, so that the number of irrelevant products can be reduced, and the product recommendation speed is greatly improved. And the products and the users are subjected to correlation arrangement through a rough arrangement algorithm and a fine arrangement algorithm, so that the accuracy of product pushing is further improved.

According to the method, the user emotion of the target user is recognized from the user voice data through the preset emotion recognition model, the user portrait of the target user is constructed according to the user emotion, the user attribute characteristics and the user behavior characteristics, and the user characteristics in the user portrait are richer, so that the user portrait is clustered, and the target user can be classified more accurately. And moreover, the similarity clustering processing is carried out on the user clustering labels and the product labels, clustering is carried out from the two aspects of users and products, and at least two times of relevance arrangement is carried out on clustering results, so that the relevance of the users and the products is further improved, and the pushing of the products is more accurate. Therefore, the product pushing method provided by the invention can solve the problem of low product pushing accuracy.

Fig. 2 is a functional block diagram of a product pushing apparatus according to an embodiment of the present invention.

The product pushing device 100 of the present invention may be installed in an electronic device. According to the realized functions, the product pushing device 100 may include a user emotion recognition module 101, a user feature extraction module 102, a tag construction module 103, and a product pushing module 104. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.

In the present embodiment, the functions regarding the respective modules/units are as follows:

the user emotion recognition module 101 is configured to obtain historical voice data of a target user, perform voice separation on the historical voice data to obtain voice data of the target user, and recognize a user emotion from the voice data according to a preset emotion recognition model;

the user feature extraction module 102 is configured to obtain historical user information of the target user, and extract user attribute features and user behavior features from the historical user information;

the tag construction module 103 is configured to construct a user portrait of the target user according to the user emotion, the user attribute characteristics, and the user behavior characteristics, perform clustering processing on the user portrait to obtain a user clustering tag, obtain product information, and perform text screening on the product information to obtain a product tag;

the product pushing module 104 is configured to perform similarity clustering processing on the user clustering labels and the product labels to obtain clustering results, perform relevance arrangement on the clustering results at least twice, and perform product pushing on the target user according to the arrangement results.

In detail, the specific implementation of each module of the product pushing device 100 is as follows:

step one, obtaining historical voice data of a target user, carrying out voice separation on the historical voice data to obtain the voice data of the target user, and recognizing user emotion from the voice data according to a preset emotion recognition model.

And step two, acquiring historical user information of the target user, and extracting user attribute characteristics and user behavior characteristics from the historical user information.

acquiring a preset user attribute label and a user behavior label;

And step three, constructing a user portrait of the target user according to the user emotion, the user attribute characteristics and the user behavior characteristics, and clustering the user portrait to obtain a user clustering label.

And step four, acquiring product information, and performing text screening on the product information to obtain a product label.

And fifthly, carrying out similarity clustering processing on the user clustering labels and the product labels to obtain clustering results, carrying out relevance arrangement on the clustering results at least twice, and carrying out product pushing on the target users according to the arrangement results.

taking the user clustering label as a user clustering center;

wherein a is the target vector and b is the comparison vector.

According to the method, the user emotion of the target user is recognized from the user voice data through the preset emotion recognition model, the user portrait of the target user is constructed according to the user emotion, the user attribute characteristics and the user behavior characteristics, and the user characteristics in the user portrait are richer, so that the user portrait is clustered, and the target user can be classified more accurately. And moreover, the similarity clustering processing is carried out on the user clustering labels and the product labels, clustering is carried out from the two aspects of users and products, and at least two times of relevance arrangement is carried out on clustering results, so that the relevance of the users and the products is further improved, and the pushing of the products is more accurate. Therefore, the product pushing device provided by the invention can solve the problem of low product pushing accuracy.

Fig. 3 is a schematic structural diagram of an electronic device for implementing a product pushing method according to an embodiment of the present invention.

The electronic device may comprise a processor 10, a memory 11, a communication interface 12 and a bus 13, and may further comprise a computer program, such as a product push program, stored in the memory 11 and executable on the processor 10.

The memory 11 includes at least one type of readable storage medium, which includes flash memory, removable hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, for example a removable hard disk of the electronic device. The memory 11 may also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only to store application software installed in the electronic device and various types of data, such as codes of a product push program, but also to temporarily store data that has been output or will be output.

The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device by running or executing programs or modules (e.g., product push programs, etc.) stored in the memory 11 and calling data stored in the memory 11.

The communication interface 12 is used for communication between the electronic device and other devices, and includes a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), which are typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device and for displaying a visualized user interface.

The bus 13 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus 13 may be divided into an address bus, a data bus, a control bus, etc. The bus 13 is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.

Fig. 3 shows only an electronic device having components, and those skilled in the art will appreciate that the structure shown in fig. 3 does not constitute a limitation of the electronic device, and may include fewer or more components than those shown, or some components may be combined, or a different arrangement of components.

For example, although not shown, the electronic device may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management and the like are realized through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.

Further, the electronic device may further include a network interface, and optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a bluetooth interface, etc.), which are generally used to establish a communication connection between the electronic device and other electronic devices.

Optionally, the electronic device may further comprise a user interface, which may be a Display (Display), an input unit (such as a Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device and for displaying a visualized user interface.

It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.

The product push program stored in the memory 11 of the electronic device is a combination of instructions, which when executed in the processor 10, can implement:

Specifically, the specific implementation method of the instruction by the processor 10 may refer to the description of the relevant steps in the embodiment corresponding to the drawings, which is not described herein again.

Further, the electronic device integrated module/unit, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in a computer readable storage medium. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).

The present invention also provides a computer-readable storage medium, storing a computer program which, when executed by a processor of an electronic device, may implement:

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.

The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.

The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.

The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.

Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A product pushing method, the method comprising:

2. The product push method of claim 1, wherein the performing voice separation on the historical voice data to obtain the voice data of the target user comprises:

3. The product push method as claimed in claim 2, wherein before recognizing the user emotion from the voice data according to a preset emotion recognition model, the method further comprises:

4. The product pushing method according to claim 1, wherein the extracting user attribute features and user behavior features from the historical user information comprises:

acquiring a preset user attribute label and a user behavior label;

5. The product push method of claim 4, wherein said clustering said user representations to obtain user cluster labels comprises:

6. The product pushing method of claim 1, wherein the text filtering of the product information to obtain a product label comprises:

7. The product pushing method according to claim 1, wherein the clustering the similarity of the user clustering labels and the product labels to obtain clustering results, performing at least two times of relevance arrangement on the clustering results, and pushing the product to the target user according to the arrangement results comprises:

taking the user clustering label as a user clustering center;

8. A product pusher device, characterized in that it comprises:

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the product push method of any one of claims 1 to 7.

10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, implements a product push method according to any one of claims 1 to 7.