SMS marketing method and system

Abstract

The present invention relates to the field of e-commerce technology, and discloses a text message marketing method and system, the method comprising: obtaining text message marketing area information, and obtaining a target phone number based on the text message marketing area information; obtaining marketing text message information, analyzing the marketing text message information, and determining the marketing type; and matching the anti-shielding words corresponding to the marketing type in a pre-configured word library based on the marketing type; based on the anti-shielding words, regenerating the marketing text message information through a pre-trained natural language processing model to obtain an anti-shielding marketing text message; and sending the anti-shielding marketing short message to the target phone number. The present invention can effectively prevent text messages from being intercepted by mobile phone operators or mobile phone systems, and the anti-shielding rate of text messages is greatly improved, ensuring that marketing information can be successfully delivered to the target audience, increasing the exposure and conversion rate of marketing activities, and improving marketing effects.

Description

Technical Field

[0001] The present invention relates to the technical field of e-commerce, and in particular to a short message marketing method and system. Background Art

[0002] With the popularity of smart phones and the explosive growth of the number of mobile phone users in China, mobile phones have become an indispensable communication tool and digital assistant in people's daily lives, and mobile commerce has also increasingly penetrated into people's lives. It is a new e-commerce model that uses mobile communication networks to transmit data and use mobile terminals to carry out various business operations.

[0003] SMS marketing is a form of mobile commerce. It is achieved by having customers choose to follow a store when purchasing items in a merchant's store and then subscribe to the store's SMS messages to carry out marketing in the form of SMS. The content of this SMS marketing is to send product promotion information via SMS after the customer subscribes to the store. However, with the development of intelligent mobile phones, smartphones of various brands will have information blocking functions, and generally use a unified template-based information blocking function, which means that even if the customer actively subscribes to the store, the subscribed marketing SMS will still be blocked, which prevents the user from receiving or seeing the relevant marketing SMS, greatly reducing the success rate of SMS marketing.

[0004] Therefore, how to provide a new SMS marketing method and system to prevent marketing SMS from being blocked is a problem that needs to be solved urgently. Summary of the invention

[0005] The present invention provides a short message marketing method and system to solve the above technical problems in the prior art.

[0006] According to a first aspect of the present invention, a text message marketing method is provided.

[0007] The SMS marketing method includes:

[0008] Obtaining SMS marketing area information, and obtaining a target phone number based on the SMS marketing area information;

[0009] Acquire marketing SMS information, analyze the marketing SMS information, determine the marketing type; and match the anti-blocking words corresponding to the marketing type in a pre-configured word library according to the marketing type;

[0010] Based on the anti-blocking words, the marketing SMS information is regenerated through a pre-trained natural language processing model to obtain an anti-blocking marketing SMS;

[0011] The anti-shielding marketing short message is sent to the target phone number.

[0012] Furthermore, the marketing SMS information is analyzed to determine the marketing type including:

[0013] The marketing SMS information is analyzed by a pre-trained text classification model to determine the marketing type, wherein the text classification model is a neural network model obtained based on training samples; the training samples are historical marketing SMS information marked with marketing types, wherein the marketing types include event promotions, event discounts, and event orders.

[0014] Further, according to the marketing type, matching the anti-blocking words corresponding to the marketing type in the pre-configured word library includes:

[0015] According to the marketing type, a corresponding type phrase is selected from a predetermined configured vocabulary; the vocabulary stores anti-shielding words generated according to the information shielding rules of each mobile phone manufacturer, and shielding words of the same type constitute corresponding type phrases; intent recognition is performed on the marketing SMS information to obtain an intent recognition result; according to the intent recognition result, anti-shielding words corresponding to the intent information are matched in the phrase.

[0016] Furthermore, the marketing SMS message is subjected to intent recognition, and the intent recognition result obtained includes:

[0017] Perform feature extraction on the marketing SMS information to obtain text features; and input the text features into a target intent recognition model to obtain intent recognition results; wherein, when performing feature extraction on the marketing SMS information to obtain text features, performing feature extraction on the marketing SMS information to obtain text features is performed using a bag-of-words model or a TF-IDF model; the target intent recognition model is an NLU language model obtained based on training samples, and the training samples are historical marketing SMS information annotated with intent labels.

[0018] Further, based on the anti-blocking words, the marketing SMS information is regenerated through a pre-trained natural language processing model, and the anti-blocking marketing SMS includes:

[0019] According to the intention recognition result, the marketing SMS information is segmented, and placeholders are generated according to the segment positions; according to the placeholders and the anti-blocking words, the placeholders and the anti-blocking words are inserted into the marketing SMS information through the NLG language model and the text is regenerated to obtain the anti-blocking marketing SMS containing the anti-blocking words.

[0020] According to a second aspect of the present invention, a short message marketing system is provided.

[0021] The SMS marketing system includes:

[0022] The marketing number acquisition module is used to acquire the SMS marketing area information and acquire the target phone number based on the SMS marketing area information;

[0023] The anti-blocking word processing module is used to obtain marketing SMS information, analyze the marketing SMS information, determine the marketing type; and according to the marketing type, match the anti-blocking word corresponding to the marketing type in a pre-configured word library;

[0024] An anti-shielding SMS generation module is used to regenerate the marketing SMS information based on the anti-shielding words through a pre-trained natural language processing model to obtain an anti-shielding marketing SMS;

[0025] The marketing SMS sending module is used to send the anti-shielding marketing SMS to the target phone number.

[0026] Furthermore, the anti-blocked word processing module includes: an SMS type analysis module, which is used to analyze the marketing SMS information to determine the marketing type, and when analyzing the marketing SMS information to determine the marketing type, the marketing SMS information is analyzed by a pre-trained text classification model to determine the marketing type, and the text classification model is a neural network model obtained based on training samples; the training samples are historical marketing SMS information marked with marketing types, and the marketing types include event promotions, event discounts, and event orders.

[0027] Further, the anti-shielding word processing module includes: an anti-shielding word generating module, the anti-shielding word generating module is used to match the anti-shielding word corresponding to the marketing type in a pre-configured word library according to the marketing type;

[0028] The anti-shielding word generation module includes a phrase selection module, an intention recognition module and a word matching module; wherein the phrase selection module is used to select a corresponding type phrase in a predetermined configured vocabulary according to the marketing type; the vocabulary stores anti-shielding words generated according to the information shielding rules of each mobile phone manufacturer, and shielded words of the same type constitute corresponding type phrases; the intention recognition module is used to perform intention recognition on the marketing SMS information to obtain an intention recognition result; the word matching module is used to match the anti-shielding words corresponding to the intention information in the phrase according to the intention recognition result.

[0029] Furthermore, when the intent recognition module performs intent recognition on the marketing SMS information and obtains the intent recognition result, it extracts features from the marketing SMS information to obtain text features; and inputs the text features into the target intent recognition model to obtain the intent recognition result;

[0030] Among them, when feature extraction is performed on the marketing SMS information to obtain text features, feature extraction is performed on the marketing SMS information through a bag-of-words model or a TF-IDF model to obtain text features; the target intent recognition model is an NLU language model obtained based on training samples, and the training samples are historical marketing SMS information marked with intent labels.

[0031] Furthermore, the anti-shielding SMS generation module regenerates the marketing SMS information based on the anti-shielding words through a pre-trained natural language processing model to obtain the anti-shielding marketing SMS. Then, the marketing SMS information is segmented according to the intention recognition result, and placeholders are generated according to the segment positions; based on the placeholders and the anti-shielding words, the placeholders and the anti-shielding words are inserted into the marketing SMS information through the NLG language model and the text is regenerated to obtain the anti-shielding marketing SMS containing the anti-shielding words.

[0032] The technical solution provided by the present invention may include the following beneficial effects:

[0033] The present invention can effectively prevent text messages from being intercepted by mobile phone operators or mobile phone systems, greatly improve the text message anti-shielding rate, ensure that marketing information can be successfully delivered to the target audience, increase the exposure and conversion rate of marketing activities, and improve marketing effects.

[0034] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0036] Figure 1 is a flowchart of a text message marketing method according to an exemplary embodiment;

[0037] Figure 2 is a structural block diagram of a short message marketing system according to an exemplary embodiment;

[0038] Figure 3 It is a schematic diagram showing the structure of a computer device according to an exemplary embodiment. DETAILED DESCRIPTION

[0039] The following description and accompanying drawings fully illustrate the specific embodiments of this article so that those skilled in the art can practice them. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. The scope of the embodiments of this article includes the entire scope of the claims, as well as all available equivalents of the claims. Herein, the terms "first", "second", etc. are only used to distinguish one element from another, without requiring or implying any actual relationship or order between these elements. In fact, the first element can also be called the second element, and vice versa. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the structure, device or equipment including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also include elements inherent to such structure, device or equipment. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the structure, device or equipment including the elements. Each embodiment is described in a progressive manner herein, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the embodiments can be referred to each other.

[0040] The terms "longitudinal", "lateral", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. in this document indicate the orientation or position relationship based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing this document and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In the description of this document, unless otherwise specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a mechanical connection or an electrical connection, it can also be the internal communication of two elements, it can be a direct connection, or it can be an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0041] As used herein, the term "plurality" means two or more than two, unless otherwise specified.

[0042] In this document, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B.

[0043] In this article, the term "and / or" is a description of the association relationship between objects, indicating that three relationships may exist. For example, A and / or B means: A or B, or, A and B.

[0044] It should be understood that, although the various steps in the flow chart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0045] Each module in the device or system of the present application can be implemented in whole or in part by software, hardware, or a combination thereof. The above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above modules.

[0046] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0047] Figure 1 An embodiment of a short message marketing method of the present invention is shown.

[0048] In this optional embodiment, the SMS marketing method includes:

[0049] Step S101, obtaining SMS marketing area information, and obtaining a target phone number based on the SMS marketing area information;

[0050] Step S103, obtaining marketing SMS information, analyzing the marketing SMS information, determining the marketing type; and matching the anti-blocking words corresponding to the marketing type in a pre-configured word library according to the marketing type;

[0051] Step S105, based on the anti-blocking words, the marketing SMS information is regenerated by a pre-trained natural language processing model to obtain an anti-blocking marketing SMS;

[0052] Step S107, sending the anti-shielding marketing short message to the target phone number.

[0053] In this optional embodiment, when analyzing the marketing SMS information to determine the marketing type, the marketing SMS information is analyzed by a pre-trained text classification model to determine the marketing type, and the text classification model is a neural network model obtained based on training samples; the training samples are historical marketing SMS messages marked with marketing types, and the marketing types include event promotions, event discounts, and event orders.

[0054] In this optional embodiment, when matching anti-shielding words corresponding to the marketing type in a preconfigured vocabulary based on the marketing type, a corresponding type phrase group can be selected in the preconfigured vocabulary based on the marketing type; the vocabulary base stores anti-shielding words generated according to information shielding rules of each mobile phone manufacturer, and shielding words of the same type constitute corresponding type phrase groups; intent recognition is performed on the marketing SMS information to obtain an intent recognition result; based on the intent recognition result, anti-shielding words corresponding to the intent information are matched in the phrase.

[0055] In this optional embodiment, when performing intent recognition on the marketing SMS information and obtaining the intent recognition result, feature extraction is performed on the marketing SMS information to obtain text features; and the text features are input into a target intent recognition model to obtain the intent recognition result; wherein, when performing feature extraction on the marketing SMS information to obtain text features, feature extraction is performed on the marketing SMS information through a bag-of-words model or a TF-IDF model to obtain text features; the target intent recognition model is an NLU (Natural Language Understanding) language model obtained based on training samples, and the training samples are historical marketing SMS information annotated with intent labels.

[0056] In this optional embodiment, when the marketing SMS information is regenerated based on the anti-blocking words through a pre-trained natural language processing model to obtain the anti-blocking marketing SMS, the marketing SMS information can be segmented according to the intention recognition result, and placeholders are generated according to the segment positions; based on the placeholders and the anti-blocking words, the placeholders and the anti-blocking words are inserted into the marketing SMS information through an NLG (Natural Language Generation) language model and the text is regenerated to obtain the anti-blocking marketing SMS containing the anti-blocking words.

[0057] Figure 2 An embodiment of a short message marketing system of the present invention is shown.

[0058] In this optional embodiment, the SMS marketing system includes:

[0059] The marketing number acquisition module 201 is used to acquire the SMS marketing area information and acquire the target phone number according to the SMS marketing area information;

[0060] The anti-blocking word processing module 203 is used to obtain marketing SMS information, analyze the marketing SMS information, determine the marketing type; and match the anti-blocking word corresponding to the marketing type in a pre-configured word library according to the marketing type;

[0061] The anti-shielding SMS generation module 205 is used to regenerate the marketing SMS information based on the anti-shielding words through a pre-trained natural language processing model to obtain an anti-shielding marketing SMS;

[0062] The marketing SMS sending module 207 is used to send the anti-shielding marketing SMS to the target phone number.

[0063] In this optional embodiment, the anti-shielding word processing module 203 includes: a text message type analysis module (not shown in the figure) and an anti-shielding word generation module (not shown in the figure), the text message type analysis module is used to analyze the marketing text message information to determine the marketing type, and when analyzing the marketing text message information to determine the marketing type, the marketing text message information is analyzed by a pre-trained text classification model to determine the marketing type, and the text classification model is a neural network model obtained based on training samples; the training samples are historical marketing text message information marked with marketing types, and the marketing types include event promotions, event discounts, and event orders. The anti-shielding word generation module is used to match the anti-shielding words corresponding to the marketing type in a pre-configured word library according to the marketing type;

[0064] In this optional embodiment, the anti-shielding word generation module includes a phrase selection module (not shown in the figure), an intention recognition module (not shown in the figure), and a word matching module (not shown in the figure);

[0065] The phrase selection module is used to select a corresponding type phrase from a predetermined word library according to the marketing type; the word library stores anti-blocking words generated according to the information blocking rules of each mobile phone manufacturer, and the same type of blocked words constitute a corresponding type phrase;

[0066] Among them, the intent recognition module is used to perform intent recognition on the marketing SMS information and obtain intent recognition results; and when the intent recognition module performs intent recognition on the marketing SMS information and obtains intent recognition results, it extracts features from the marketing SMS information to obtain text features; and inputs the text features into the target intent recognition model to obtain intent recognition results; when extracting features from the marketing SMS information to obtain text features, it extracts features from the marketing SMS information through a bag-of-words model or a TF-IDF model to obtain text features; the target intent recognition model is an NLU language model obtained based on training samples, and the training samples are historical marketing SMS information marked with intent labels.

[0067] Among them, the word matching module is used to match the anti-shielding words that are compatible with the intention information in the phrase according to the intention recognition result.

[0068] Among them, when feature extraction is performed on the marketing SMS information to obtain text features, feature extraction is performed on the marketing SMS information through a bag-of-words model or a TF-IDF model to obtain text features; the target intent recognition model is an NLU language model obtained based on training samples, and the training samples are historical marketing SMS information marked with intent labels.

[0069] In this optional embodiment, the anti-shielding SMS generation module 205 regenerates the marketing SMS information based on the anti-shielding words through a pre-trained natural language processing model to obtain the anti-shielding marketing SMS. Then, according to the intention recognition result, the marketing SMS information is segmented, and placeholders are generated according to the segment positions; according to the placeholders and the anti-shielding words, the placeholders and the anti-shielding words are inserted into the marketing SMS information through the NLG language model and the text is regenerated to obtain the anti-shielding marketing SMS containing the anti-shielding words.

[0070] Figure 3 An embodiment of a computer device of the present invention is shown. The computer device may be a server, and the computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store static information and dynamic information data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the steps in the above method embodiment are implemented.

[0071] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0072] In addition, the present invention also provides a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiment when executing the computer program.

[0073] In addition, the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiment are implemented.

[0074] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0075] The present invention is not limited to the structures which have been described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A SMS marketing method, characterized in that: include: Obtaining SMS marketing area information, and obtaining a target phone number based on the SMS marketing area information; Obtain marketing SMS information, analyze the marketing SMS information, and determine the marketing type; and according to the marketing type, matching the anti-blocking words corresponding to the marketing type in a pre-configured word library; Based on the anti-blocking words, the marketing SMS information is regenerated through a pre-trained natural language processing model to obtain an anti-blocking marketing SMS; Sending the anti-shielding marketing SMS to the target phone number; Wherein, according to the marketing type, matching the anti-shielding words corresponding to the marketing type in the pre-configured word library includes: selecting a corresponding type phrase in the pre-configured word library according to the marketing type; the word library stores anti-shielding words generated according to information shielding rules of each mobile phone manufacturer, and shielding words of the same type constitute corresponding type phrases; performing intent recognition on the marketing SMS information to obtain an intent recognition result; according to the intent recognition result, matching the anti-shielding words corresponding to the intent information in the word group; Performing intent recognition on the marketing SMS information to obtain the intent recognition result includes: performing feature extraction on the marketing SMS information to obtain text features; and inputting the text features into a target intent recognition model to obtain the intent recognition result; wherein, when performing feature extraction on the marketing SMS information to obtain text features, performing feature extraction on the marketing SMS information to obtain text features through a bag-of-words model or a TF-IDF model; the target intent recognition model is an NLU language model obtained based on a training sample, and the training sample is historical marketing SMS information annotated with intent labels; Based on the anti-blocking words, the marketing SMS information is regenerated through a pre-trained natural language processing model to obtain the anti-blocking marketing SMS, including: according to the intention recognition result, the marketing SMS information is segmented, and placeholders are generated according to the segment positions; according to the placeholders and the anti-blocking words, the placeholders and the anti-blocking words are inserted into the marketing SMS information through the NLG language model and the text is regenerated to obtain the anti-blocking marketing SMS containing the anti-blocking words.

2. The SMS marketing method according to claim 1, characterized in that: Analyze the marketing SMS information to determine the marketing type, including: The marketing SMS information is analyzed by a pre-trained text classification model to determine the marketing type, wherein the text classification model is a neural network model obtained based on training samples; the training samples are historical marketing SMS information marked with marketing types, wherein the marketing types include event promotions, event discounts, and event orders.

3. A short message marketing system, characterized in that: include: The marketing number acquisition module is used to acquire the SMS marketing area information and acquire the target phone number based on the SMS marketing area information; The anti-blocking word processing module is used to obtain marketing SMS information, analyze the marketing SMS information, and determine the marketing type; and according to the marketing type, matching the anti-blocking words corresponding to the marketing type in a pre-configured word library; An anti-shielding SMS generation module is used to regenerate the marketing SMS information based on the anti-shielding words through a pre-trained natural language processing model to obtain an anti-shielding marketing SMS; A marketing SMS sending module, used to send the anti-shielding marketing SMS to the target phone number; The anti-shielding word processing module includes: an anti-shielding word generation module, which is used to match the anti-shielding words corresponding to the marketing type in a pre-configured word library according to the marketing type; and the anti-shielding word generation module includes a phrase selection module, an intention recognition module and a word matching module; wherein the phrase selection module is used to select the corresponding type phrase in the pre-configured word library according to the marketing type; the word library stores anti-shielding words generated according to the information shielding rules of each mobile phone manufacturer, and shielding words of the same type constitute corresponding type phrases; the intention recognition module is used to perform intention recognition on the marketing SMS information to obtain an intention recognition result; the word matching module is used to match the anti-shielding words corresponding to the intention information in the phrase according to the intention recognition result; When the intent recognition module performs intent recognition on the marketing SMS information and obtains the intent recognition result, it extracts features from the marketing SMS information to obtain text features; and inputs the text features into the target intent recognition model to obtain the intent recognition result; wherein, when extracting features from the marketing SMS information to obtain text features, the text features are extracted from the marketing SMS information using a bag-of-words model or a TF-IDF model; the target intent recognition model is an NLU language model obtained based on a training sample, and the training sample is historical marketing SMS information annotated with intent labels; The anti-shielding SMS generation module regenerates the marketing SMS information based on the anti-shielding words through a pre-trained natural language processing model to obtain the anti-shielding marketing SMS. Then, according to the intention recognition result, the marketing SMS information is segmented, and placeholders are generated according to the segment positions; according to the placeholders and the anti-shielding words, the placeholders and the anti-shielding words are inserted into the marketing SMS information through the NLG language model and the text is regenerated to obtain the anti-shielding marketing SMS containing the anti-shielding words.

4. The SMS marketing system according to claim 3, characterized in that: The anti-blocked word processing module includes: an SMS type analysis module, which is used to analyze the marketing SMS information to determine the marketing type, and when analyzing the marketing SMS information to determine the marketing type, the marketing SMS information is analyzed by a pre-trained text classification model to determine the marketing type, and the text classification model is a neural network model obtained based on training samples; the training samples are historical marketing SMS information marked with marketing types, and the marketing types include event promotions, event discounts, and event orders.

Images