CN116091136B - Telephone marketing method and device based on speaker - Google Patents

Telephone marketing method and device based on speaker Download PDF

Info

Publication number
CN116091136B
CN116091136B CN202310042456.3A CN202310042456A CN116091136B CN 116091136 B CN116091136 B CN 116091136B CN 202310042456 A CN202310042456 A CN 202310042456A CN 116091136 B CN116091136 B CN 116091136B
Authority
CN
China
Prior art keywords
product
user
speaker
target user
target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202310042456.3A
Other languages
Chinese (zh)
Other versions
CN116091136A (en
Inventor
王一
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Renma Interactive Technology Co Ltd
Original Assignee
Shenzhen Renma Interactive Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Renma Interactive Technology Co Ltd filed Critical Shenzhen Renma Interactive Technology Co Ltd
Priority to CN202310042456.3A priority Critical patent/CN116091136B/en
Publication of CN116091136A publication Critical patent/CN116091136A/en
Application granted granted Critical
Publication of CN116091136B publication Critical patent/CN116091136B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0255—Targeted advertisements based on user history
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/5846—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using extracted text
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/761—Proximity, similarity or dissimilarity measures
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • General Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Library & Information Science (AREA)
  • Databases & Information Systems (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Multimedia (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application discloses a telemarketing method and device based on a speaker, wherein the method comprises the following steps: receiving a new product promotion request initiated by a brand manufacturer; determining product code information of a product code person of the product to be promoted based on the identification of the product to be promoted; determining a target user based on product speaker information and an identification of a brand to which a product to be promoted belongs; determining the fan attribute of the target user based on the identity information of the target user; determining the script style of the marketing script according to the vermicelli attribute; generating a target man-machine dialogue marketing script according to the script style and the product information of the product to be promoted; acquiring sound characteristics of a product substitution speaker; and according to the sound characteristics of the product speaker and the target man-machine dialogue marketing script, making a call to a target user through a man-machine dialogue engine so as to promote the product to be promoted. The method and the system are beneficial to improving the comprehensiveness and accuracy of creating the marketing script by the machine marketing server and improving the intelligence of telemarketing.

Description

Telephone marketing method and device based on speaker
Technical Field
The application relates to the technical field of general data processing in the Internet industry, in particular to a telephone marketing method and device based on a speaker.
Background
When a new product is available, the new product can be sold to consumers in a telephone marketing mode. Existing telemarketing typically generates a single marketing script by a machine marketing server for only product information of new products, and then calls users by the machine marketing server based on the single marketing script without distinction to promote the products. The marketing script generated in this way can only be used to generate different marketing scripts for different new products, the marketing scripts are limited to the product information of the new products, and no pertinence is provided when a call is made to a user.
Disclosure of Invention
The telemarketing method and device based on the speaker are beneficial to improving the comprehensiveness and accuracy of creating marketing scripts by a machine marketing server and improving the intelligence of telemarketing.
In a first aspect, the present application provides a telemarketing method based on a speaker, applied to a machine marketing server of a smart telemarketing system, the smart telemarketing system supporting a brand to log in through a merchant account, the smart telemarketing system including a machine marketing server, a terminal device, and a mall server, the machine marketing server being provided with a man-machine dialogue engine, man-machine dialogue logic of the man-machine dialogue engine being given by a marketing script, the method comprising: receiving a new product promotion request initiated by a brand merchant aiming at a product to be promoted of a product promotion interface of a smart phone marketing system, wherein the product to be promoted is a product in a product list of a pre-stored brand merchant, the product list is a product set synchronized by a mall server, and the new product promotion request comprises an identification of the product to be promoted and an identification of a brand to which the product to be promoted belongs; determining product code information of a product code person of the product to be promoted based on the identification of the product to be promoted; determining a target user from a user cluster of the brand to which the product to be promoted belongs, wherein the user cluster has purchased the brand to which the product to be promoted belongs, based on product speaker information, and the target user is a fan of the product speaker; determining a fan attribute of the target user based on the identity information of the target user, wherein the fan attribute refers to a fan category and is used for representing the favorite type of the target user for the product speaker, and the identity information of the target user comprises head portrait information of the target user and account name of the target user; determining script styles of marketing scripts according to the fan attributes, wherein the script styles comprise conversation styles, conversation mood and call to target users; generating a target man-machine dialogue marketing script according to the script style and the product information of the product to be promoted; acquiring sound characteristics of a product substitution speaker; and according to the sound characteristics of the product speaker and the target man-machine dialogue marketing script, making a call to a target user through a man-machine dialogue engine so as to promote the product to be promoted.
By the method, the vermicelli of the product speaker is used as a target user, and different recommendation strategies are generated according to different types of users, so that the generated man-machine dialogue marketing script is more various and flexible, the distance between the human-machine dialogue marketing script and the user is shortened when the product to be promoted is recommended, and the success rate of telephone marketing based on the speaker is improved.
In one possible implementation, determining a target user from a cluster of users who have purchased a brand to which a product to be promoted belongs based on product speaker information and an identification of the brand to which the product to be promoted belongs, includes: based on the product speaker information, obtaining a speaker picture library corresponding to the product speaker and a speaker word library corresponding to the product speaker; determining a user cluster which has purchased the brand to which the product to be promoted belongs based on the identification of the brand to which the product to be promoted belongs; matching head portrait information of a first user in the user cluster with pictures in a pronouncing person picture library, and matching account information of the first user with words in a pronouncing person word library, wherein the first user is any user in the user cluster; and if the pictures with the similarity to the head portrait information of the first user being greater than a first threshold value exist in the speaker picture library, and words with the similarity to the account information of the first user being greater than a second threshold value exist in the speaker word library, determining the first user as a target user.
By the method, whether the user is the fan of the product speaker or not is judged based on the head portrait and the name of the user, and the target user is accurately determined.
In one possible implementation, the method further comprises: if no picture with the similarity to the head portrait information of the first user being greater than a first threshold value exists in the speaker picture library, and no word with the similarity to the account information of the first user being greater than a second threshold value exists in the speaker word library, acquiring a purchase record of the first user in a preset time period; determining the times of historical purchasing of a target product by a first user based on the purchasing record, wherein the target product is a product of a product pronouncing person; determining a first duty ratio based on the number of times the first user has historically purchased the target product and the total number of times the first user has historically purchased the target product, the first duty ratio being a ratio of the number of times the first user has historically purchased the target product to the total number of times the first user has historically purchased the target product; if the first duty cycle is greater than the third threshold, the first user is determined to be the target user.
By the method, the target user is accurately determined based on the duty ratio of the product which is symbolized by the product symbolizer in the product purchased by the user history.
In one possible implementation, the method further comprises: classifying the pictures in the pronouncing person picture library according to styles to obtain a plurality of pronouncing person picture type libraries, wherein the pictures in the same pronouncing person picture type library are of the same type, and the pronouncing person picture type libraries have corresponding relations with the vermicelli attributes; classifying words in the pronouncing person word library according to styles to obtain a plurality of pronouncing person word type libraries, wherein the words in the same pronouncing person word type library are of the same type, and the pronouncing person word type libraries have corresponding relations with fan attributes; determining the fan attribute of the target user based on the identity information of the target user comprises the following steps: and determining the fan attribute of the target user based on the plurality of speaker picture type libraries, the plurality of speaker word type libraries and the identity information of the target user.
By the method, the fan type of the target user can be accurately determined based on different types of picture libraries and word libraries corresponding to the product speaker.
In one possible implementation, determining the fan attribute to which the target user belongs based on the plurality of speaker picture type libraries, the plurality of speaker word type libraries, and the identity information of the target user includes: matching the head portrait information of the target user with pictures in a plurality of speaker picture type libraries, and determining the picture with highest similarity with the head portrait information from the plurality of speaker picture type libraries; taking the fan attribute corresponding to the dialect picture type library to which the picture with the highest similarity belongs as a first fan attribute; matching the account name of the target user with words in the plurality of pronouncing person word type libraries, and determining the words with highest similarity to the account name from the plurality of pronouncing person word type libraries; taking the fan attribute corresponding to the dialect-person word type library to which the word with the highest similarity belongs as a second fan attribute; and determining the fan attribute of the target user based on the first fan attribute and the second fan attribute.
By the method, the fan type of the target user can be further accurately determined based on the head portrait style and the name style of the target user.
In one possible implementation, the human-machine dialogue marketing script comprises a departure script; the method further comprises the steps of: acquiring working state information of a product speaker in a preset time; the opening script is determined based on the working state information of the product speaker in a preset time.
By the method, the beginning script is determined based on the working state information of the product speaker, so that the goodness of the target user can be improved, and the probability of success of recommendation is improved.
In one possible implementation, the human-machine dialogue marketing script comprises a departure script; the method further comprises the steps of: acquiring historical purchase product information of a target user; wherein the play scenario is determined based on historical purchase product information of the target user.
By the method, the beginning script is determined based on the historical purchase product information of the user, so that curiosity of the user on the product to be promoted can be improved, and the probability of success in recommendation is improved.
In one possible implementation, a human-machine dialogue marketing script includes a plurality of different marketing routes; the method further comprises the steps of: determining a target marketing route from a man-machine dialogue marketing script comprising a plurality of different marketing routes based on feedback information of the target user on the opening script; and marketing the product to be promoted to the target user based on the target marketing route.
By the method, different target recommendation routes are determined based on different feedback information of the user, so that the recommendation strategy is more flexible.
In a second aspect, embodiments of the present application provide a sponsor-based telemarketing apparatus comprising means for performing the method of the first aspect described above.
In a third aspect, embodiments of the present application provide a machine marketing server comprising a memory for storing a computer program comprising program instructions and a processor configured to invoke the program instructions to perform the method of the first aspect described above, and one or more programs.
In a fourth aspect, the present application provides a computer readable storage medium having stored therein computer readable instructions which, when run on a communication device, cause the communication device to perform the method of the first aspect described above.
In a fifth aspect, the present application provides a computer program or computer program product comprising code or instructions which, when run on a computer, cause the computer to perform the method of the first aspect as described above.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of a system architecture of a speaker-based telemarketing method according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a telemarketing method based on a speaker according to an embodiment of the present application;
FIG. 3 is a schematic diagram of an interface for selecting products to be promoted by a brand vendor according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a telemarketing device based on a speaker according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a machine marketing server according to an embodiment of the present application.
Detailed Description
The following description of the technical solutions in the embodiments of the present application will be made clearly and completely with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terminology used in the following embodiments of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms as well, unless the context clearly indicates to the contrary. It should also be understood that the term "and/or" as used in this application refers to and encompasses any or all possible combinations of one or more of the listed items.
It should be noted that, in the description and claims of the present application and in the above figures, the terms "first," "second," "third," etc. are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the present application described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
The embodiment of the application provides a telephonic marketing method based on a speaker, which relates to Cloud technology (Cloud technology), wherein the Cloud technology is a hosting technology for integrating serial resources such as hardware, software, network and the like in a wide area network or a local area network to realize calculation, storage, processing and sharing of data.
In particular, the Cloud storage (Cloud storage) and Database (Database) in the Cloud technology are a new concept that extends and develops in the concept of Cloud computing, and the distributed Cloud storage system (hereinafter referred to as a storage system) refers to a storage system that integrates a large number of storage devices (storage devices are also referred to as storage nodes) of various types in a network through application software or application interfaces to cooperatively work together through functions such as cluster application, grid technology, and distributed storage file system. The database can be considered as an electronic filing cabinet, namely a place for storing electronic files, and a user can perform operations such as adding, inquiring, updating, deleting and the like on data in the files. A "database" is a collection of data stored together in a manner that can be shared with multiple users, with as little redundancy as possible, independent of the application.
In a possible embodiment, the speaker-based telemarketing method provided by the embodiment of the application can be implemented based on cloud data. The cloud storage and private cloud in the cloud data can be particularly related.
Referring to fig. 1, fig. 1 is a system architecture diagram of a speaker-based telemarketing system according to an embodiment of the present application. The method specifically comprises the following steps: a machine marketing server 101, a terminal device 102, and a mall server 103. The machine marketing server 101 and the terminal device 102 are in communication connection, the machine marketing server 101 and the mall server 103 are in communication connection, and the terminal device 102 and the mall server 103 are in communication connection. Wherein the machine marketing server 101 is provided with a human-machine dialog engine whose human-machine dialog logic is conferred by the marketing script. It should be noted that the terminal device 102 includes one or more terminal devices, and each terminal device establishes a connection with the machine marketing server 101 and the mall server 103.
Optionally, the machine marketing server 101 and the mall server 103 may be computing devices such as a server or a client, where the server may be an independent physical server, or may be a server cluster or a distributed system formed by multiple physical servers, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, and basic cloud computing services such as big data and an artificial intelligence platform. The management server may also be a node, but is not limited thereto.
Alternatively, the terminal device 102 may be an electronic device with communication functions, such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart voice interaction device, etc. Exemplary embodiments of the electronic device include, but are not limited to, portable electronic devices that are equipped with IOS systems, android systems, microsoft systems, or other operating systems.
The present application will be described in detail with reference to specific examples.
Referring to fig. 2, fig. 2 is a flow chart of a speaker-based telemarketing method provided in an embodiment of the present application, which is applied to a machine marketing server of a smart telemarketing system, the smart telemarketing system supports brands to log in through merchant accounts, the smart telemarketing system includes a machine marketing server, a terminal device and a mall server, the machine marketing server is provided with a man-machine dialogue engine, and man-machine dialogue logic of the man-machine dialogue engine is given by a marketing script; as shown in fig. 2, the speaker-based telemarketing method specifically includes steps 201-208. Wherein:
201. receiving a new product promotion request initiated by a brand merchant aiming at a product to be promoted of a product promotion interface of a smart phone marketing system, wherein the product to be promoted is a product in a product list of a pre-stored brand merchant, the product list is a product set synchronized by a mall server, and the new product promotion request comprises an identification of the product to be promoted and an identification of a brand to which the product to be promoted belongs.
The brand manufacturer may select a product to be promoted in the product recommendation interface through the terminal device, for example, as shown in fig. 3, a page shown in fig. 3 is a product recommendation interface, and after the brand manufacturer wants to use the product 4 as the product to be promoted, and triggers the promotion button 301 corresponding to the product 4, the terminal device sends a new product promotion request to the machine marketing server, where the new product promotion request includes an identifier of the product 4 and an identifier of a brand to which the product 4 belongs. The identification of the product to be promoted is used to determine the product to be promoted from the product list. In one possible embodiment, if the new product promotion request is sent by the brand company a, the brand to which the product to be promoted belongs is the brand a.
202. And determining the product code information of the product code person of the product to be promoted based on the identification of the product to be promoted.
The product speaker information of the product speaker comprises image information and name information of the product speaker. The image information may be a related picture of the product speaker (such as a poster, a script, etc. of the product speaker), and the name information may be a name of the product speaker, a nickname, a name of a fan group of the product speaker, etc.
In one possible embodiment, there are multiple products under the same merchant, with different products corresponding to different speakers. The identification of the product has a corresponding relation with the speaker. For example, product logo 1-product speaker 1, product logo 2-product speaker 2, product logo 3-product speaker 3. If the mark of the product to be promoted is the product mark 3, determining that the product speaker 3 corresponding to the product mark 3 is the product speaker of the product to be promoted.
203. And determining a target user from the user clusters of the brands to which the products to be promoted belong, wherein the target user is the vermicelli of the product speaker, based on the product speaker information and the identification of the brands to which the products to be promoted belong.
In one possible implementation, a user cluster of a brand to which a product to be promoted belongs is determined based on an identification of the brand to which the product to be promoted belongs; and determining target users from the user clusters of brands to which the products to be promoted belong based on the product speaker information. For example, brand a has a new product a on the market, and the speaker of brand a is speaker B, then it may be determined that the fan of speaker B among the users who purchased the product of brand a is the target user.
In one possible embodiment, determining the target user from the user cluster having purchased the brand to which the product to be promoted belongs based on the product speaker information and the identity of the brand to which the product to be promoted belongs comprises: based on the product speaker information, obtaining a speaker picture library corresponding to the product speaker and a speaker word library corresponding to the product speaker; determining a user cluster which has purchased the brand to which the product to be promoted belongs based on the identification of the brand to which the product to be promoted belongs; matching head portrait information of a first user in the user cluster with pictures in a pronouncing person picture library, and matching account information of the first user with words in a pronouncing person word library, wherein the first user is any user in the user cluster; and if the pictures with the similarity to the head portrait information of the first user being greater than a first threshold value exist in the speaker picture library, and words with the similarity to the account information of the first user being greater than a second threshold value exist in the speaker word library, determining the first user as a target user.
That is, according to the head portrait information and the correlation degree between the account name and the product speaker of the first user, whether the first user is the fan of the product speaker is determined, and whether the first user is a target user is further determined.
The first threshold may be a preset threshold, or may be a threshold that is flexibly changed according to the recommended success rate of the product to be promoted in a period of time, and if the recommended success rate of the product to be promoted in a period of time is higher than the preset threshold, the first threshold may be appropriately reduced to expand the range of the target user. That is, the number of target users can be appropriately enlarged while ensuring the recommended success rate of the product to be promoted. Similarly, if the recommended success rate of the product to be promoted is lower than the preset threshold value within a period of time, the first threshold value can be properly raised, so that the determined target user is more accurate. For example, the recommended success rate of the product to be promoted is higher than 80% (preset threshold) within one month, the initial first threshold is 80%, and the first threshold is reduced to 75% in order to expand the range of the target user. Otherwise, the recommended success rate of the product to be promoted is lower than 80% (preset threshold value) within one month, the initial first threshold value is 80%, and in order to ensure the recommended success rate of the product to be promoted, the first threshold value is increased to 85%.
The second threshold may be a preset threshold, or a threshold that is flexibly changed according to the recommended success rate of the product to be promoted in a period of time, and the specific change rule may refer to the description of the first threshold in the above description, which is not repeated herein.
Illustratively, the first threshold is 80% and the second threshold is 75%. Acquiring account information of three users in a user set: user 1 (header information 1 and account name 1), user 2 (header information 2 and account name 2), and user 3 (header information 3 and account name 3). And comparing the head portrait information of the three users with the pictures in the speaker picture library, wherein the similarity of the picture with the highest similarity of the head portrait information corresponding to the user 1 in the speaker picture library is 70%, the similarity of the picture with the highest similarity of the head portrait information corresponding to the user 2 in the speaker picture library is 85%, and the similarity of the picture with the highest similarity of the head portrait information corresponding to the user 3 in the speaker picture library is 90%. The similarity of the words with the highest similarity of the account names corresponding to the user 1 in the pronouncing word library is 70%, the similarity of the words with the highest similarity of the account names corresponding to the user 2 in the pronouncing word library is 90%, and the similarity of the words with the highest similarity of the account names corresponding to the user 3 in the pronouncing word library is 50%. As can be seen, there is no picture with similarity greater than the first threshold value with the head portrait information of the user 1 in the speaker picture library, so the user 1 is not a target user; as can be seen, there is a picture with similarity greater than the first threshold value with the head portrait information of the user 3 in the speaker picture library, but there is no word with similarity greater than the second threshold value with the account information of the user 3 in the speaker word library, so the user 3 is not a target user; the pronouncing person picture library contains pictures with the similarity to the head portrait information of the user 2 being greater than a first threshold value, and the pronouncing person word library contains words with the similarity to the account information of the user 2 being greater than a second threshold value, so that the user 2 is determined as a target user.
In one possible embodiment, it may be determined whether a picture with similarity to the head portrait information of the first user greater than a first threshold exists in the speaker picture library, and then whether a word with similarity to the account information of the first user greater than a second threshold exists in the speaker word library. Or judging whether the words with the similarity to the account information of the first user being greater than a second threshold value exist in the pronouncing word stock, and judging whether the pictures with the similarity to the head portrait information of the first user being greater than the first threshold value exist in the pronouncing picture stock. The determination order is not limited herein.
The above manner is to determine whether the first user is a target user based on the head portrait information of the first user and the account name of the first user, and in a possible embodiment, whether the first user is a target user may also be determined based on the head portrait information of the first user only, which specifically is: based on the product speaker information, acquiring a speaker picture library corresponding to the product speaker; matching head portrait information of a first user in the user cluster with pictures in a speaker picture library; and if the pictures with the similarity with the head portrait information of the first user larger than the first threshold value exist in the speaker picture library, determining the first user as a target user.
In another possible embodiment, it may also be determined whether the user is a target user based on only the user account name, specifically: based on the product speaker information, obtaining a speaker word library corresponding to the product speaker; matching the account name of the first user in the user cluster with words in the pronouncing word stock; and if the words with the similarity with the account name of the first user being greater than the second threshold value exist in the word stock of the words, determining the first user as the target user.
Through the head portrait information and account name of the first user, the pronouncing person picture library and the pronouncing person word library of the product pronouncing person, whether the first user is a target user can be accurately judged.
In a possible embodiment, if no picture with the similarity to the head portrait information of the first user being greater than a first threshold value exists in the speaker picture library and no word with the similarity to the account information of the first user being greater than a second threshold value exists in the speaker word library, acquiring a purchase record of the first user in a preset time period; determining the times of historical purchasing of a target product by a first user based on the purchasing record, wherein the target product is a product of a product pronouncing person; determining a first duty ratio based on the number of times the first user has historically purchased the target product and the total number of times the first user has historically purchased the target product, the first duty ratio being a ratio of the number of times the first user has historically purchased the target product to the total number of times the first user has historically purchased the target product; if the first duty cycle is greater than the third threshold, the first user is determined to be the target user.
That is, when the fan of the product speaker cannot be determined based on the head portrait information and the account name of the first user, whether the first user is the target user may be determined based on the duty ratio of the product speaker in the products historically purchased by the first user.
The purchase record may be a record that the first user purchased the products of the brands in a preset time period, a record that the first user purchased the products of all brands in a preset time period, a record that the first user purchased the same type of products (such as snack type, daily necessities type, electric appliances type, etc.) in a preset time period, or other purchase records, which are not limited herein.
The third threshold may be a preset threshold, or may be a threshold that is flexibly changed according to the recommended success rate of the product to be promoted in a period of time, and if the recommended success rate of the product to be promoted in a period of time is higher than the preset threshold, the third threshold may be appropriately reduced to expand the range of the target user to be judged. That is, the number of judgment target users can be appropriately enlarged on the premise of ensuring the success rate of recommendation of the product to be promoted. Similarly, if the recommended success rate of the product to be promoted is lower than the preset threshold value within a period of time, the third threshold value can be properly increased, so that the determined target user is more accurate, and the recommended success rate of the product to be promoted is improved.
Illustratively, the third threshold is 75% and the product is referred to as product 1. Obtaining purchase records of three users (first users) in a user cluster of brands to which products to be promoted belong in a month (preset time period), wherein the number of times of purchasing the products 1 by the user 1 in the month is 3 times, the number of times of purchasing the products 2 is 5 times, the number of times of purchasing the products 3 is 1 time, the first ratio of purchasing the products 1 by the user 1 is 3/(3+5+1) =33%, the first ratio (33%) is smaller than a third threshold (75%), and the user 1 is not a target user. The number of times of purchase of the product 1 by the user 2 in one month is 8, the number of times of purchase of the product 2 is 2, and the number of times of purchase of the product 3 is 0, the first ratio of purchase of the user 2 is 8/(8+2+0) =80%, the first ratio (80%) is greater than the third threshold (75%), and the user 2 is determined as the target user. The number of times of purchase of the product 1 by the user 3 is 10 times, the number of purchase of the product 2 is 1 time, the number of times of purchase of the product 3 is 2 times, the first ratio of purchase of the user 3 is 10/(10+1+2) =77%, the first ratio (77%) is greater than the third threshold (75%), and the user 3 is determined as the target user.
The above manner is that the target user is determined by the ratio of the products of the product code in the products purchased by the first user history, in one possible embodiment, the target user is determined based on the number of times of the products of the product code in the products purchased by the first user history, specifically: the first user purchases records in a preset time; determining the times of historical purchase of a target product of a product speaker by a first user based on the purchase record; and if the number of times that the first user purchases the target product historically is greater than a fourth threshold value, determining the first user as the target user.
The fourth threshold is, for example, 5 times. Acquiring purchase records of three users (first users) in a user cluster of a brand to which a product to be promoted belongs within one month (preset time period), wherein the times of purchasing the product of a product pronounder pronouncing in one month by the user 1 are 3 times; the number of times the user 2 purchases the product of the product code person code in one month is 8; the number of times the user 3 purchases the product of the product code person code within one month is 0. Since the number of times the user 2 purchases the product of the product code exceeds the fourth threshold, the user 2 is determined to be the target user.
When the head portrait information and the account name of the first user do not meet the judging conditions of the fan of the product speaker, the first user performs supplementary judgment through the historical purchasing record of the first user, so that the missing of the target user is avoided, and the judged target user range is larger and more accurate.
204. And determining the fan attribute of the target user based on the identity information of the target user, wherein the fan attribute refers to a fan category and is used for representing the favorite type of the target user on the product speaker, and the identity information of the target user comprises the head portrait information of the target user and the account name of the target user.
The style of the head portrait information of the target user may be a lovely style, or may be Gao Lengfeng grids, for example, if the head portrait of the target user is a cartoon head portrait, the style of the head portrait information of the target user is considered to be a lovely style. The account name style of the target user can be a lovely style, and if the account name of the target user contains sweet heart, baby and other contents, the account name of the target user is considered to be a lovely style. The vermicelli category includes "first vermicelli", "second vermicelli", etc.
In a possible embodiment, classifying the pictures in the speaker picture library according to styles to obtain a plurality of speaker picture type libraries, wherein the pictures in the same speaker picture type library are of the same type, and the speaker picture type libraries have a corresponding relationship with the vermicelli attributes; classifying words in the pronouncing person word library according to styles to obtain a plurality of pronouncing person word type libraries, wherein the words in the same pronouncing person word type library are of the same type, and the pronouncing person word type libraries have corresponding relations with fan attributes; determining the fan attribute of the target user based on the identity information of the target user comprises the following steps: and determining the fan attribute of the target user based on the plurality of speaker picture type libraries, the plurality of speaker word type libraries and the identity information of the target user.
The styles of the pictures in the pronouncing person picture library can be lovely styles, gentle styles, cool styles and the like, and the styles of the words in the pronouncing person word library can be lovely styles, gentle styles, cool styles and the like. One speaker picture type library corresponds to a fan attribute, for example, a lovely-style speaker picture type library corresponds to a fan attribute 1, a gentle-style speaker picture type library corresponds to a fan attribute 2, and similarly, one speaker word library type library also corresponds to a fan attribute. It should be noted that, the attribute of the dialect picture type library and the vermicelli attribute may be in one-to-one correspondence, or the attribute of the plurality of dialect picture type libraries and the attribute of the vermicelli attribute may be in one-to-one correspondence, or the attribute of the plurality of dialect word type libraries and the attribute of the vermicelli attribute may be in one-to-one correspondence.
For example, the speaker picture library has the following five pictures: picture 1 (lovely style), picture 2 (lovely style), picture 3 (gentle style), picture 4 (lovely style), picture 5 (gentle style). Classifying the speaker picture library according to styles to obtain two speaker picture type libraries, wherein the speaker picture type library 1 comprises the following three pictures: picture 1, picture 2, picture 4; the speaker picture type library 2 includes two pictures as follows: picture 3 and picture 5. It can be seen that the pictures in the same speaker picture type library are of the same type.
The pronouncing word stock has the following five words: word 1 (gentle style), word 2 (lovely style), word 3 (gentle style), word 4 (lovely style), word 5 (gentle style). Classifying the pronouncing words and phrases library according to styles to obtain two pronouncing words and phrases type libraries, wherein the pronouncing words and phrases type library 1 comprises the following three words and phrases: word 2, word 4; the pronouncing person word type library 2 includes two words as follows: word 1, word 3, word 5. It can be seen that the words in the same pronouncing person word type library are of the same type.
In one possible implementation, determining the fan attribute to which the target user belongs based on the plurality of speaker picture type libraries, the plurality of speaker word type libraries and the identity information of the target user specifically includes: matching the head portrait information of the target user with pictures in a plurality of speaker picture type libraries, and determining the picture with highest similarity with the head portrait information from the plurality of speaker picture type libraries; taking the fan attribute corresponding to the dialect picture type library to which the picture with the highest similarity belongs as a first fan attribute; matching the account name of the target user with words in the plurality of pronouncing person word type libraries, and determining the words with highest similarity to the account name from the plurality of pronouncing person word type libraries; taking the fan attribute corresponding to the dialect-person word type library to which the word with the highest similarity belongs as a second fan attribute; and determining the fan attribute of the target user based on the first fan attribute and the second fan attribute.
The first fan-out attribute is a fan-out attribute determined based on the head portrait information of the target user, the second fan-out attribute is a fan-out attribute determined based on the account name of the target user, and the fan-out attribute is a fan-out attribute of the target user which is finally determined. The first vermicelli attribute and the second vermicelli attribute may be the same vermicelli attribute or different vermicelli attributes, and the following description will be made respectively for the case where the first vermicelli attribute and the second vermicelli attribute may be the same vermicelli attribute and the case where the first vermicelli attribute and the second vermicelli attribute may be different vermicelli attributes.
In case one, the first fan attribute and the second fan attribute are the same fan attribute.
At this time, the fan attribute to which the target user belongs is the same as the first fan attribute and is also the same as the second fan attribute, for example, the first fan attribute and the second fan attribute are both the first type fan, and the fan attribute to which the target user belongs is the first type fan.
Illustratively, the speaker picture type library 1 includes a picture 1, a picture 2, and a picture 3, and the speaker picture type library 2 includes a picture 4 and a picture 5. Wherein, the speaker picture type library 1 corresponds to the first type vermicelli, and the speaker picture type library 2 corresponds to the second type vermicelli. And if the head portrait information of the target user has the highest similarity with the picture 3, the first fan attribute of the target user is a first type fan. The pronouncing person word type library 1 comprises words 1, 2 and 3, and the pronouncing person word type library 2 comprises words 4 and 5. Wherein, the word type library 1 of the dialect people corresponds to the first type of vermicelli, and the word type library 2 of the dialect people corresponds to the second type of vermicelli. And if the similarity between the account name of the target user and the word 2 is highest, the second fan attribute of the target user is the first fan. The fan attribute to which the target user belongs is a first type of fan.
And in the second case, the first vermicelli attribute and the second vermicelli attribute are different vermicelli attributes.
At this time, the fan attribute to which the target user belongs is the same as the first fan attribute or the same as the second fan attribute, for example, the first fan attribute is the first type fan, the second fan attribute is the second type fan, and the fan attribute to which the target user belongs is the first type fan or the second type fan.
In one possible embodiment, a first weight corresponding to a first vermicelli attribute is obtained, a second weight corresponding to a second vermicelli attribute is obtained, and if the first weight is greater than or equal to the second weight, the first vermicelli attribute is used as a vermicelli attribute to which the target user belongs; otherwise, if the second weight is greater than the first weight, the second fan attribute is taken as the fan attribute to which the target user belongs.
Illustratively, the speaker picture type library 1 includes a picture 1, a picture 2, and a picture 3, and the speaker picture type library 2 includes a picture 4 and a picture 5. Wherein, the speaker picture type library 1 corresponds to the first type vermicelli, and the speaker picture type library 2 corresponds to the second type vermicelli. And if the head portrait information of the target user has the highest similarity with the picture 3, the first fan attribute of the target user is a first type fan. The pronouncing person word type library 1 comprises words 1, 2 and 3, and the pronouncing person word type library 2 comprises words 4 and 5. Wherein, the word type library 1 of the dialect people corresponds to the first type of vermicelli, and the word type library 2 of the dialect people corresponds to the second type of vermicelli. And if the similarity between the account name of the target user and the word 5 is highest, the second fan-out attribute of the target user is a second fan-out. The first weight corresponding to the first vermicelli attribute is 0.7, the second weight corresponding to the second vermicelli attribute is 0.3, and if the first weight is larger than the second weight, the vermicelli attribute to which the target user belongs is the first type vermicelli (first vermicelli attribute). That is, the avatar information of the target user at this time is dominant in judging the fan attribute to which the target user belongs.
The first weight may be a preset fixed value, or a value that flexibly varies according to the historical recommended success rate, and similarly, the second weight may be a preset fixed value, or a value that flexibly varies according to the historical recommended success rate. For example, the initial first weight is 0.7, and the second weight is 0.3, that is, the style of the head portrait information of the target user accounts for a larger proportion of the total style, and the style of the account name of the target user accounts for a smaller proportion of the total style. The success rate of recommendation under the specific gravity is not high, that is, when the head portrait information of the target user is dominant, the judged fan attribute of the target user is not accurate enough, the first weight is changed to 0.3, and the second weight is changed to 0.7, so that the account name of the target user is taken as the dominant of judgment.
And flexibly changing the first weight and the second weight according to the historical recommendation success rate, so that the accuracy of judging the fan attribute of the target user is improved.
205. And determining the script style of the marketing script according to the fan attribute, wherein the script style comprises the conversation style, the conversation mood and the call to the target user.
The conversation style includes words and the like during conversation, the conversation mood includes warm mood, high cold mood and the like, and the call of the target user includes loving and the like.
In one possible embodiment, there is a mapping between fan type and call style, call mood, and call to the target user. For example, the following table shows:
Figure SMS_1
that is, if the fan type is fan type 1, it may be determined that the call style is call style 1, the call mood is call mood 1, and the title of the target user is title 1; if the vermicelli type is vermicelli type 2, determining that the conversation style is conversation style 2, and the conversation mood is conversation mood 2, and calling the target user as 2; if the vermicelli type is vermicelli type 3, the conversation style can be determined to be conversation style 3, the conversation mood is conversation mood 3, and the name of the target user is 3.
By the method, different recommendation strategies can be generated according to different vermicelli types, so that the distance between the target user and the target user is shortened, and the success rate of recommendation is improved.
206. And generating a target man-machine dialogue marketing script according to the script style and the product information of the product to be promoted.
The product information of the product to be promoted can be the functional information of the product, the technical parameters of the product, the improvement of the product compared with the product on the market, and the like. For example, if the product to be promoted is a mobile phone, the product information may be the pixel parameter, the screen resolution parameter, the chip used, and the duration of the mobile phone. It should be noted that the above product information is only an example for easy understanding, and the product information may also include other information, not limited to the above information, and is not limited herein.
In order to further shorten the distance between the target users, the success rate of recommendation is improved, and the man-machine dialogue marketing script also comprises a beginning script, namely a starting white, which is used for carrying out cold talk with the target users after the telephone is connected. Two ways of determining the beginning scenario of the recommended strategy are explained below:
firstly, acquiring working state information of a product speaker in preset time; the opening script is determined based on the working state information of the product speaker in a preset time.
That is, after the working state information of the product speaker within the preset time is acquired, the beginning scenario is generated based on the working state information of the product speaker within the preset time.
The working state information of the product speaker in the preset time can be a new song recently released by the product speaker, a film and television work recently developed by the product speaker, and the like. Illustratively, acquiring a new album in the recent period by a product speaker, the generated beginning scenario is a query of the target user as to whether the target user has heard a song in the new album recently released by the product speaker, or takes the chorus portion of the song as the beginning scenario.
Obtaining historical purchase product information of a target user; wherein the beginning scenario is determined based on historical purchase product information of the target user.
That is, after the history purchase product information of the target user is acquired, the beginning scenario is generated based on the history purchase product information of the target user.
Wherein, the historical purchase product information of the target user comprises common problems of the purchased product, or problems raised by other users in the near term, and the like. For example, if a certain electric appliance in a product recently purchased by a target user has a charging failure, the generated beginning scenario is a question asking the target user whether the charging failure exists.
In one possible embodiment, the human-machine dialogue marketing script comprises a plurality of different recommended routes; the method further comprises the steps of: determining a target recommended route from a human-computer dialogue marketing script comprising a plurality of different recommended routes based on feedback information of a target user on the script; recommending the product to be promoted to the target user based on the target recommended route.
Wherein, different recommended routes correspond to different dialogue contents, and the feedback information is the answer of the target user to the opening script. The after-market scenario may be after-market inquiry information, where the after-market inquiry information is used to inquire whether a problem exists in a product historically purchased by the target user, if the target user answers the problem, the dialogue content in the determined target recommended route mainly surrounds improvement on the problem of the product to be promoted, and if the target user answers the problem does not exist, the dialogue content in the determined target recommended route mainly surrounds and fully introduces the product to be promoted to the target user. For example, if the target user answers the problem that the historically purchased product A has high power consumption, the dialogue content in the determined target recommended route mainly surrounds the improvement of the product to be promoted on the aspect of electric quantity, so that the cruising is more durable; if the target user answers the history purchased product A and does not have the problem of high power consumption, the dialogue content in the determined target recommended route mainly surrounds the high-new technology, the design idea and the like adopted by the product to be promoted.
207. And acquiring the sound characteristics of the product speaker.
208. And according to the sound characteristics of the product speaker and the target man-machine dialogue marketing script, making a call to a target user through a man-machine dialogue engine so as to promote the product to be promoted.
In one possible implementation, mail can also be sent to the target user through the human-machine conversation engine based on the recommendation strategy to recommend the product to be promoted; or a short message can be sent to the target user through the man-machine conversation engine based on the recommendation strategy so as to recommend the product to be promoted; or a message can be sent to the account of the chat application of the target user through the man-machine conversation engine based on the recommendation strategy so as to recommend the product to be promoted. It should be noted that, the above three ways can be recommended through text description of the product to be promoted, picture description of the product to be promoted, and graphic combination description of the product to be promoted.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a telemarketing device based on a speaker according to an embodiment of the present application. The speaker-based telemarketing apparatus may be used to perform some or all of the functions of the server in the method embodiments described above. The device may be a server, a device in a server, or a device that can be used in cooperation with a server. The speaker-based telemarketing device may also be a chip system. The speaker-based telemarketing apparatus shown in fig. 4 includes a receiving unit 401 and a processing unit 402. Wherein:
The receiving unit 401 is configured to receive a new product promotion request initiated by a brand merchant for a product to be promoted of a product promotion interface of the smart telemarketing system, where the product to be promoted is a product in a product list of a pre-stored brand merchant, the product list is a product set synchronized by a mall server, and the new product promotion request includes an identifier of the product to be promoted and an identifier of a brand to which the product to be promoted belongs;
a processing unit 402, configured to determine product speaker information of a product speaker of the product to be promoted based on the identification of the product to be promoted;
the processing unit 402 is further configured to determine, based on the product speaker information and the identifier of the brand to which the product to be promoted belongs, a target user from a user cluster of the brand to which the product to be promoted belongs has been purchased, where the target user is a fan of the product speaker;
the processing unit 402 is further configured to determine, based on identity information of the target user, a fan attribute to which the target user belongs, where the fan attribute refers to a fan category, and is used to characterize a favorite type of the target user for a product speaker, and the identity information of the target user includes head portrait information of the target user and an account name of the target user;
the processing unit 402 is further configured to determine a script style of the marketing script according to the fan attribute, where the script style includes a conversation style, a conversation mood, and a call to the target user;
The processing unit 402 is further configured to generate a target man-machine dialogue marketing scenario according to the scenario style and the product information of the product to be promoted;
the processing unit 402 is further configured to obtain a sound feature of the product speaker;
the processing unit 402 is further configured to make a call to the target user through the human-machine dialogue engine according to the sound feature of the product speaker and the target human-machine dialogue marketing script, so as to promote the product to be promoted.
In a possible embodiment, the processing unit 402 is further configured to obtain a speaker picture library corresponding to the product speaker and a speaker word library corresponding to the product speaker based on the product speaker information; the processing unit 402 is further configured to determine, based on the identifier of the brand to which the product to be promoted belongs, a user cluster that has purchased the brand to which the product to be promoted belongs; the processing unit 402 is further configured to match header information of a first user in the user cluster with a picture in the pronouncing person picture library, and match account information of the first user with a word in the pronouncing person word library, where the first user is any user in the user cluster; the processing unit 402 is further configured to determine the first user as the target user if a picture with similarity to the head portrait information of the first user being greater than a first threshold exists in the speaker picture library and a word with similarity to the account information of the first user being greater than a second threshold exists in the speaker word library.
In a possible embodiment, if there is no picture with similarity to the head portrait information of the first user greater than the first threshold in the speaker picture library and there is no word with similarity to the account information of the first user greater than the second threshold in the speaker word library, the receiving unit 401 is further configured to obtain a purchase record of the first user in a preset time period; the processing unit 402 is further configured to determine, based on the purchase record, a number of times the first user historically purchases a target product, where the target product is a product of a product code person code; determining a first duty ratio based on the number of times the first user has historically purchased the target product and the total number of times the first user has historically purchased the target product, the first duty ratio being a ratio of the number of times the first user has historically purchased the target product to the total number of times the first user has historically purchased the target product; if the first duty cycle is greater than the third threshold, the first user is determined to be the target user.
In a possible embodiment, the processing unit 402 is further configured to classify the pictures in the speaker picture library according to styles to obtain a plurality of speaker picture type libraries, where the pictures in the same speaker picture type library are of the same type, and the speaker picture type libraries have a correspondence with the fan attributes; classifying words in the pronouncing person word library according to styles to obtain a plurality of pronouncing person word type libraries, wherein the words in the same pronouncing person word type library are of the same type, and the pronouncing person word type libraries have corresponding relations with fan attributes; determining the fan attribute of the target user based on the identity information of the target user comprises the following steps: and determining the fan attribute of the target user based on the plurality of speaker picture type libraries, the plurality of speaker word type libraries and the identity information of the target user.
In a possible embodiment, the processing unit 402 is further configured to match the avatar information of the target user with pictures in the plurality of speaker picture type libraries, and determine a picture with highest similarity to the avatar information from the plurality of speaker picture type libraries; taking the fan attribute corresponding to the dialect picture type library to which the picture with the highest similarity belongs as a first fan attribute; matching the account name of the target user with words in the plurality of pronouncing person word type libraries, and determining the words with highest similarity to the account name from the plurality of pronouncing person word type libraries; taking the fan attribute corresponding to the dialect-person word type library to which the word with the highest similarity belongs as a second fan attribute; and determining the fan attribute of the target user based on the first fan attribute and the second fan attribute.
In a possible embodiment, the receiving unit 401 is further configured to obtain working state information of the product speaker within a preset time; the opening script is determined based on the working state information of the product speaker in a preset time.
In a possible embodiment, the receiving unit 401 is further configured to obtain historical purchase product information of the target user; wherein the play scenario is determined based on historical purchase product information of the target user.
In a possible embodiment, the processing unit 402 is further configured to determine, based on feedback information of the target user on the opening script, a target marketing route from a man-machine dialogue marketing script including a plurality of different marketing routes; and marketing the product to be promoted to the target user based on the target marketing route.
Referring to fig. 5, fig. 5 is a schematic structural diagram of a machine marketing server according to an embodiment of the present invention. The machine marketing server 500 may include a memory 501, a processor 502. Optionally, a communication interface 503 is also included. The memory 501, processor 502, and communication interface 503 are connected by one or more communication buses. Wherein the communication interface 503 is controlled by the processor 502 to transmit and receive information.
Memory 501 may include read only memory and random access memory and provides instructions and data to processor 502. A portion of memory 501 may also include non-volatile random access memory.
The communication interface 503 is used to receive or transmit data.
The processor 502 may be a central processing unit (Central Processing Unit, CPU), and the processor 502 may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor, but in the alternative, the processor 502 may be any conventional processor or the like. Wherein:
Memory 501 for storing program instructions.
A processor 502 for invoking program instructions stored in memory 501.
The processor 502 invokes the program instructions stored in the memory 501 to cause the machine marketing server 500 to perform the methods of the method embodiments described above.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present application are all or partially produced. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired or wireless means. The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
The embodiment of the application also provides a computer storage medium, where the computer storage medium stores a computer program for electronic data exchange, where the computer program causes a computer to execute part or all of the steps of any one of the methods described in the embodiments of the method, where the computer includes an electronic device.
Embodiments of the present application also provide a computer program product comprising a computer program operable to cause a computer to perform part or all of the steps of any one of the methods described in the method embodiments above.
The computer program product may be a software installation package, said computer comprising an electronic device.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
In the several embodiments provided in the present application, it should be understood that the disclosed method, apparatus, and system may be implemented in other manners. For example, the device embodiments described above are merely illustrative; for example, the division of the units is only one logic function division, and other division modes can be adopted in actual implementation; for example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units 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 units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may be physically included separately, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in hardware plus software functional units.
The integrated units implemented in the form of software functional units described above may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium, and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform 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 (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Although the present invention is disclosed above, the present invention is not limited thereto. Variations and modifications, including combinations of the different functions and implementation steps, as well as embodiments of the software and hardware, may be readily apparent to those skilled in the art without departing from the spirit and scope of the invention.
It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present application is not limited by the order of acts described, as some acts may, in accordance with the present application, occur in other orders and concurrently. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required in the present application.
The descriptions of the embodiments provided in the present application may be referred to each other, and the descriptions of the embodiments are focused on, and for the part that is not described in detail in a certain embodiment, reference may be made to the related descriptions of other embodiments. For convenience and brevity of description, for example, reference may be made to the related descriptions of the method embodiments of the present application for the functions and operations performed by the devices and apparatuses provided by the embodiments of the present application, and reference may also be made to each other, combined or cited between the method embodiments, and between the device embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

Claims (7)

1. A speaker-based telemarketing method, characterized by being applied to a machine marketing server of a smart telemarketing system, the smart telemarketing system supporting branding to log in through a merchant account, the smart telemarketing system including the machine marketing server, a terminal device, and a mall server, the machine marketing server being provided with a man-machine dialogue engine, man-machine dialogue logic of the man-machine dialogue engine being conferred by a marketing script, the method comprising:
receiving a new product promotion request initiated by a brand merchant aiming at a product to be promoted of a product promotion interface of the intelligent telemarketing system, wherein the product to be promoted is a product in a pre-stored product list of the brand merchant, the product list is a product set synchronized by the mall server, and the new product promotion request comprises an identification of the product to be promoted and an identification of a brand to which the product to be promoted belongs;
Determining product code information of a product code of the product to be promoted based on the identification of the product to be promoted;
based on the product speaker information, acquiring a speaker picture library corresponding to the product speaker and a speaker word library corresponding to the product speaker;
determining a user cluster which has purchased the brand to which the product to be promoted belongs based on the identification of the brand to which the product to be promoted belongs;
matching head portrait information of a first user in the user cluster with pictures in the speaker picture library and matching account information of the first user with words in the speaker word library, wherein the first user is any user in the user cluster;
if a picture with the similarity to the head portrait information of the first user being larger than a first threshold value exists in the pronouncing person picture library, and words with the similarity to the account information of the first user being larger than a second threshold value exist in the pronouncing person word library, the first user is determined to be a target user, and the target user is the vermicelli of the product pronouncing person;
if no picture with the similarity to the head portrait information of the first user being greater than a first threshold value exists in the pronouncing person picture library, and no word with the similarity to the account information of the first user being greater than a second threshold value exists in the pronouncing person word library, acquiring a purchase record of the first user in a preset time period;
Determining the times of historical purchasing of a target product by the first user based on the purchasing record, wherein the target product is a product of the product code person code;
determining a first duty ratio based on the number of times the first user has historically purchased the target product and the total number of times the first user has historically purchased, the first duty ratio being a ratio of the number of times the first user has historically purchased the target product to the total number of times the first user has historically purchased;
if the first duty ratio is larger than a third threshold value, the first user is determined to be a target user;
classifying the pictures in the speaker picture library according to styles to obtain a plurality of speaker picture type libraries, wherein the pictures in the same speaker picture type library are of the same type, and the speaker picture type library has a corresponding relation with the vermicelli attribute;
classifying words in the pronouncing herringbone word library according to styles to obtain a plurality of pronouncing words type libraries, wherein words in the same pronouncing words type library are of the same type, and the pronouncing words type library has a corresponding relation with the fan attribute;
determining a fan attribute of the target user based on the plurality of speaker picture type libraries, the plurality of speaker word type libraries and identity information of the target user, wherein the fan attribute refers to a fan category and is used for representing a favorite type of the target user for the product speaker, and the identity information of the target user comprises head portrait information of the target user and account name of the target user;
Determining the script style of the marketing script according to the vermicelli attribute, wherein the script style comprises a conversation style, a conversation mood and a call to the target user;
generating a target man-machine dialogue marketing script according to the script style and the product information of the product to be promoted;
acquiring sound characteristics of the product speaker;
and calling the target user through the man-machine dialogue engine according to the sound characteristics of the product speaker and the target man-machine dialogue marketing script so as to promote the product to be promoted.
2. The method of claim 1, wherein the determining the fan attribute to which the target user belongs based on the plurality of claim picture type libraries, the plurality of claim word type libraries, and the identity information of the target user comprises:
matching the head portrait information of the target user with the pictures in the plurality of speaker picture type libraries, and determining the picture with the highest similarity with the head portrait information from the plurality of speaker picture type libraries;
taking the vermicelli attribute corresponding to the dialect picture type library to which the picture with the highest similarity belongs as a first vermicelli attribute;
Matching the account name of the target user with words in the plurality of dialect word type libraries, and determining the word with the highest similarity with the account name from the plurality of dialect word type libraries;
taking the fan attribute corresponding to the dialect person word type library to which the word with the highest similarity belongs as a second fan attribute;
and determining the fan attribute of the target user based on the first fan attribute and the second fan attribute.
3. The method of claim 1, wherein the human-machine dialogue marketing script comprises a kefir script;
the method further comprises the steps of:
acquiring working state information of the product speaker in a preset time;
the opening script is determined based on the working state information of the product speaker in a preset time.
4. A method according to any one of claims 1-3, wherein the human-machine dialogue marketing script comprises a kefir script;
the method further comprises the steps of:
acquiring historical purchase product information of the target user;
wherein the play scenario is determined based on historical purchase product information of the target user.
5. The method of claim 4, wherein the human-machine dialogue marketing script comprises a plurality of different marketing routes;
the method further comprises the steps of:
determining a target marketing route from a plurality of different marketing routes in the man-machine conversation marketing script based on feedback information of the target user on the departure script;
and marketing the product to be promoted to the target user based on the target marketing route.
6. A speaker-based telemarketing apparatus, characterized by a machine marketing server applied to a smart telemarketing system supporting branding to log in by a merchant account, the smart telemarketing system including the machine marketing server, a terminal device, and a mall server, the machine marketing server being provided with a man-machine dialogue engine whose man-machine dialogue logic is conferred by a marketing script, the apparatus comprising:
the receiving unit is used for receiving a new product promotion request initiated by a brand merchant aiming at a product to be promoted of a product promotion interface of the intelligent telemarketing system, wherein the product to be promoted is a product in a pre-stored product list of the brand merchant, the product list is a product set synchronized by the mall server, and the new product promotion request comprises an identification of the product to be promoted and an identification of a brand to which the product to be promoted belongs;
The processing unit is used for determining product code information of a product code person of the product to be promoted based on the identification of the product to be promoted;
the processing unit is further used for acquiring a pronouncing person picture library corresponding to the product pronouncing person and a pronouncing person word library corresponding to the product pronouncing person based on the product pronouncing person information;
the processing unit is further configured to determine, based on the identifier of the brand to which the product to be promoted belongs, a user cluster that has purchased the brand to which the product to be promoted belongs;
the processing unit is further configured to match head portrait information of a first user in the user cluster with a picture in the dialect people picture library and match account information of the first user with words in the dialect people word library, where the first user is any user in the user cluster;
the processing unit is further configured to determine, if a picture with similarity to the head portrait information of the first user being greater than a first threshold exists in the pronouncing person picture library and a word with similarity to the account information of the first user being greater than a second threshold exists in the pronouncing person word library, the first user as a target user, and the target user as a fan of the product pronouncing person;
The processing unit is further configured to obtain a purchase record of the first user in a preset time period if no picture with similarity to the head portrait information of the first user being greater than a first threshold exists in the pronouncing person picture library and no word with similarity to the account information of the first user being greater than a second threshold exists in the pronouncing person word library;
the processing unit is further configured to determine, based on the purchase record, a number of times the first user historically purchases a target product, where the target product is a product that is a product pronouncing person;
the processing unit is further configured to determine a first duty ratio based on the number of times the first user has historically purchased the target product and the total number of times the first user has historically purchased, where the first duty ratio is a ratio of the number of times the first user has historically purchased the target product to the total number of times the first user has historically purchased;
the processing unit is further configured to determine the first user as a target user if the first duty ratio is greater than a third threshold;
the processing unit is further configured to classify the pictures in the speaker picture library according to styles to obtain a plurality of speaker picture type libraries, wherein the pictures in the same speaker picture type library are of the same type, and the speaker picture type libraries have a corresponding relationship with the vermicelli attributes;
The processing unit is further used for classifying the words in the pronouncing word stock according to styles to obtain a plurality of pronouncing word type libraries, the words in the same pronouncing word type library are of the same type, and the pronouncing word type library has a corresponding relation with the fan attribute; the processing unit is further configured to determine a fan attribute to which the target user belongs based on the plurality of speaker picture type libraries, the plurality of speaker word type libraries, and identity information of the target user, where the fan attribute is a fan category, and is used to characterize a favorite type of the target user for the product speaker, and the identity information of the target user includes head portrait information of the target user and an account name of the target user;
the processing unit is further used for determining the script style of the marketing script according to the vermicelli attribute, wherein the script style comprises a conversation style, a conversation mood and a call to the target user;
the processing unit is further used for generating a target man-machine dialogue marketing script according to the script style and the product information of the product to be promoted;
the processing unit is also used for acquiring the sound characteristics of the product speaker;
And the processing unit is also used for calling the target user through the man-machine dialogue engine according to the sound characteristics of the product speaker and the target man-machine dialogue marketing script so as to promote the product to be promoted.
7. A machine marketing server comprising a processor, a memory, and one or more programs stored in the memory and configured for execution by the processor, the programs comprising instructions for performing the steps of the method of any of claims 1-5.
CN202310042456.3A 2023-01-28 2023-01-28 Telephone marketing method and device based on speaker Active CN116091136B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310042456.3A CN116091136B (en) 2023-01-28 2023-01-28 Telephone marketing method and device based on speaker

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310042456.3A CN116091136B (en) 2023-01-28 2023-01-28 Telephone marketing method and device based on speaker

Publications (2)

Publication Number Publication Date
CN116091136A CN116091136A (en) 2023-05-09
CN116091136B true CN116091136B (en) 2023-06-23

Family

ID=86186563

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310042456.3A Active CN116091136B (en) 2023-01-28 2023-01-28 Telephone marketing method and device based on speaker

Country Status (1)

Country Link
CN (1) CN116091136B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116932798B (en) * 2023-09-15 2023-11-21 星河视效科技(北京)有限公司 Virtual speaker generation method, device, equipment and storage medium

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014087417A1 (en) * 2012-12-06 2014-06-12 Vikram Raju Sayyaparaju System and method to provide real-time live interaction between celebrity and audience
EP3136265A1 (en) * 2015-08-28 2017-03-01 Yandex Europe AG Method and apparatus for generating a recommended content list
CN107894833A (en) * 2017-10-26 2018-04-10 北京光年无限科技有限公司 Multi-modal interaction processing method and system based on visual human
CN109660871A (en) * 2018-12-17 2019-04-19 北京爱奇艺科技有限公司 A kind of barrage Role Information determines method, device and equipment
KR20200042139A (en) * 2018-10-15 2020-04-23 김용대 Famous people donation brokerage service system and method
CN111432226A (en) * 2020-03-27 2020-07-17 广州酷狗计算机科技有限公司 Live broadcast recommendation method and device, server, terminal and storage medium
CN111770370A (en) * 2020-07-28 2020-10-13 聚好看科技股份有限公司 Display device, server and media asset recommendation method
CN112115398A (en) * 2019-06-20 2020-12-22 脉冲股份有限公司 Virtual space providing system, virtual space providing method, and program
CN114549118A (en) * 2022-01-20 2022-05-27 钻技(上海)信息科技有限公司 Commodity recommendation method and device
CN115212580A (en) * 2022-09-21 2022-10-21 深圳市人马互动科技有限公司 Method and related device for updating game data based on telephone interaction
CN115329206A (en) * 2022-10-13 2022-11-11 深圳市人马互动科技有限公司 Voice outbound processing method and related device
CN115410601A (en) * 2022-11-01 2022-11-29 深圳市人马互动科技有限公司 Voice interaction method based on scene recognition in man-machine conversation scene

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090112680A1 (en) * 2007-10-25 2009-04-30 Ido Dovrath System for interaction with celebrities
US11471774B2 (en) * 2020-04-16 2022-10-18 The Generational Project, LLC Mixed reality competitions involving real and virtual participants
US11962854B2 (en) * 2021-06-06 2024-04-16 Apple Inc. Providing content recommendations for user groups
WO2022261613A1 (en) * 2021-06-06 2022-12-15 Apple Inc. User interfaces for displaying content recommendations for a group of users

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014087417A1 (en) * 2012-12-06 2014-06-12 Vikram Raju Sayyaparaju System and method to provide real-time live interaction between celebrity and audience
EP3136265A1 (en) * 2015-08-28 2017-03-01 Yandex Europe AG Method and apparatus for generating a recommended content list
CN107894833A (en) * 2017-10-26 2018-04-10 北京光年无限科技有限公司 Multi-modal interaction processing method and system based on visual human
KR20200042139A (en) * 2018-10-15 2020-04-23 김용대 Famous people donation brokerage service system and method
CN109660871A (en) * 2018-12-17 2019-04-19 北京爱奇艺科技有限公司 A kind of barrage Role Information determines method, device and equipment
CN112115398A (en) * 2019-06-20 2020-12-22 脉冲股份有限公司 Virtual space providing system, virtual space providing method, and program
CN111432226A (en) * 2020-03-27 2020-07-17 广州酷狗计算机科技有限公司 Live broadcast recommendation method and device, server, terminal and storage medium
CN111770370A (en) * 2020-07-28 2020-10-13 聚好看科技股份有限公司 Display device, server and media asset recommendation method
CN114549118A (en) * 2022-01-20 2022-05-27 钻技(上海)信息科技有限公司 Commodity recommendation method and device
CN115212580A (en) * 2022-09-21 2022-10-21 深圳市人马互动科技有限公司 Method and related device for updating game data based on telephone interaction
CN115329206A (en) * 2022-10-13 2022-11-11 深圳市人马互动科技有限公司 Voice outbound processing method and related device
CN115410601A (en) * 2022-11-01 2022-11-29 深圳市人马互动科技有限公司 Voice interaction method based on scene recognition in man-machine conversation scene

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
Marketing the Entrepreneurial Artist in the Innovation Age: Aesthetic Labor, Artistic Subjectivity, and the Creative Industries;Thet Shein Win;Anthropology of Work Review;第35卷(第1期);2-13 *
电视剧集在短视频平台的营销分析――以《亲爱的,热爱的》官方抖音宣传为例;蔡斐然;新媒体研究;第6卷(第17期);41-44 *
社交媒体时代的"粉丝经济"及其营销创新;杨莹;营销界;第2020年卷(第21期);28-29 *

Also Published As

Publication number Publication date
CN116091136A (en) 2023-05-09

Similar Documents

Publication Publication Date Title
US9462440B2 (en) Community interaction using mobile communication devices
US8423392B2 (en) Trusted participants of social network providing answers to questions through on-line conversations
US20070243887A1 (en) Platform for telephone-optimized data and voice services
US20100129065A1 (en) Content request, storage and/or configuration systems and methods for live content or events
JP2011227892A (en) Method and system for characterizing and utilizing relationship from a user's social networks
WO2018045915A1 (en) Method and apparatus for adjusting service voice playback sequence
US20160094491A1 (en) Pattern-controlled automated messaging system
US10078692B2 (en) Method and system for providing a social service based on music information
WO2015196987A1 (en) Natural language supported data query method, open platform and user terminal
US20140089397A1 (en) Method, server, and client for pushing and displaying splash screen
WO2019100986A1 (en) Information sending method and apparatus
CN116091136B (en) Telephone marketing method and device based on speaker
CN102158541A (en) Shared information acquisition method, device, mobile terminal and server
CN112507218A (en) Business object recommendation method and device, electronic equipment and storage medium
CN104717131A (en) Information interaction method and server
US10134057B2 (en) Targeting offerings to a customer based on psychographic information
US20090100024A1 (en) Multi-modal mobile platform
WO2016107278A1 (en) Method, device, and system for labeling user information
CN111523030B (en) Newspaper disc information recommendation method and device and computer readable storage medium
US9721270B2 (en) Integrating communications services with personalized social networks
CN116051201B (en) Voice outbound data processing method and device, electronic equipment and storage medium
CN111831925A (en) Backup method based on information sharing of other people, electronic equipment and readable storage medium
WO2023282890A1 (en) Real-time micro-profile generation using a dynamic tree structure
CN114898739A (en) Voice call response processing method and device, computer equipment and storage medium
CN113839790A (en) Data processing method, electronic device and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant