Short message management method, device, electronic device, storage medium and program product

Abstract

The present invention relates to a short message management method, device, electronic device, storage medium and program product, including receiving a short message sending request sent by a short message sender, the short message sending request carrying a target short message and a target short message recipient corresponding to the target short message; determining the category label of the target short message and the purpose label of the target short message; obtaining the category of short messages willing to be received corresponding to the target short message recipient and the short message port registration purpose corresponding to the short message sender; and determining whether to send the target short message to the target short message recipient according to the category label of the target short message and the purpose label of the target short message, as well as the category of short messages willing to be received and the registration purpose of the short message port. In this method, the target short message is classified by the category label of the target short message and the purpose label of the target short message, and whether to send the target short message to the target short message recipient is determined in combination with the category of short messages willing to be received and the registration purpose of the short message port, thereby improving the accuracy of short message management.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a text message management method, device, electronic equipment, storage medium and program product. Background Art

[0002] In the field of SMS business, the SMS services provided by operators to users or service providers include point-to-point SMS and industry SMS. Industry SMS plays a key role in many fields of modern society, from notifications and reminders, verification and security, to marketing promotion, customer service, etc. At the same time, they also provide enterprises with a low-cost and efficient customer communication channel, and are an indispensable business tool.

[0003] Typically, operators need to monitor and manage industry text messages to prevent users from receiving spam text messages. Existing text message management methods only screen industry text messages based on industry text message signatures and then decide whether to send them to users. This management method has low accuracy. Summary of the invention

[0004] The present invention is intended to provide a text message management method, device, electronic device, storage medium and program product to solve the deficiencies in the prior art. The technical problem to be solved by the present invention is achieved through the following technical solutions.

[0005] According to a first aspect of the present disclosure, a method for managing short messages is provided, the method comprising:

[0006] Receiving a text message sending request sent by a text message sender, the text message sending request carrying a target text message and a target text message recipient corresponding to the target text message;

[0007] Determining a category label of the target text message and a purpose label of the target text message;

[0008] Acquire the SMS category corresponding to the target SMS recipient and the SMS port registration purpose corresponding to the SMS sender;

[0009] According to the category label of the target SMS and the purpose label of the target SMS, as well as the category of the SMS to be received and the registration purpose of the SMS port, it is determined whether to send the target SMS to the target SMS recipient.

[0010] Further, the determining the category label of the target short message and the purpose label of the target short message includes:

[0011] In the case where the signature of the target short message is stored in a database, determining the category label of the target short message according to the corresponding relationship between the signature and the category label stored in the database;

[0012] The text message content of the target text message is input into the trained first model to determine the purpose label of the target text message.

[0013] Furthermore, when the signature of the target SMS is stored in the database, before determining the category label of the target SMS according to the corresponding relationship between the signature and the category label stored in the database, the method further includes:

[0014] Fine-tune the second model using part of the sample SMS data until the accuracy of the output result of the second model is greater than a preset threshold, the output result of the second model including the category label of the part of the sample SMS data and the purpose label of the part of the sample SMS data;

[0015] Inputting the remaining sample SMS data in the sample SMS data except the part of the sample SMS data into the fine-tuned second model to obtain the category label of the remaining sample SMS data and the purpose label of the remaining sample SMS data;

[0016] The corresponding relationship between the signature of the remaining sample SMS data and the category label of the remaining sample SMS data is stored in a database;

[0017] The first model is trained using the usage labels of the remaining sample SMS data.

[0018] Furthermore, before fine-tuning the second model using part of the sample SMS data, the method further includes:

[0019] Get historical SMS data;

[0020] Deduplication of the historical text message data according to the signature of the historical text message data;

[0021] The historical SMS data after deduplication is desensitized to obtain sample SMS data.

[0022] Furthermore, the method further comprises:

[0023] In the case that the signature of the target text message is not stored in the database, the signature of the target text message is input into the fine-tuned second model to determine the category label of the target text message.

[0024] Further, the determining whether to send the target SMS to the target SMS recipient according to the category label of the target SMS and the purpose label of the target SMS, as well as the category of the SMS to be received and the registered purpose of the SMS port includes:

[0025] When the category tag of the target SMS matches the category of the SMS to be received and the purpose tag of the target SMS matches the purpose registered in the SMS port, the target SMS is sent to the target SMS recipient;

[0026] In the case that the category tag of the target SMS does not match the category of the SMS to be received and / or the purpose tag of the target SMS does not match the purpose registered in the SMS port, the target SMS is intercepted.

[0027] According to a second aspect of the present disclosure, a short message management device is provided, the device comprising:

[0028] A first receiving module, configured to receive a text message sending request sent by a text message sender, wherein the text message sending request carries a target text message and a target text message recipient corresponding to the target text message;

[0029] A first determination module, used to determine the category label of the target short message and the purpose label of the target short message;

[0030] The first acquisition module is used to acquire the SMS category corresponding to the target SMS recipient and the SMS port registration purpose corresponding to the SMS sender;

[0031] The second determination module is used to determine whether to send the target SMS to the target SMS recipient according to the category label of the target SMS and the purpose label of the target SMS, as well as the category of the SMS to be received and the registered purpose of the SMS port.

[0032] According to a third aspect of the present disclosure, an electronic device is provided. The electronic device includes: a memory and a processor, wherein a computer program is stored in the memory, and the method is implemented when the processor executes the computer program.

[0033] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program implements the method when executed by a processor.

[0034] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising computer instructions, which implement the method when executed by a processor.

[0035] The embodiments of the present invention include the following advantages:

[0036] The SMS management method, device, electronic device, storage medium and program product provided by the embodiment of the present invention include receiving a SMS sending request sent by a SMS sender, the SMS sending request carries a target SMS and a target SMS recipient corresponding to the target SMS; determining the category label of the target SMS and the purpose label of the target SMS; obtaining the SMS category corresponding to the target SMS recipient and the SMS port registration purpose corresponding to the SMS sender; and determining whether to send the target SMS to the target SMS recipient based on the category label of the target SMS and the purpose label of the target SMS, as well as the SMS category and the SMS port registration purpose. In this embodiment, the target SMS is classified by the category label of the target SMS and the purpose label of the target SMS, and whether to send the target SMS to the target SMS recipient is determined in combination with the SMS category corresponding to the target SMS recipient and the SMS port registration purpose corresponding to the SMS sender, thereby improving the accuracy of SMS management. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is one of the flow charts of steps of an embodiment of a method for managing short messages of the present invention;

[0038] Figure 2 This is the second step flow chart of an embodiment of a text message management method of the present invention;

[0039] Figure 3 It is a structural schematic diagram of an embodiment of a short message management device of the present invention;

[0040] Figure 4 It is a structural schematic diagram of an electronic device of the present invention. DETAILED DESCRIPTION

[0041] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0042] Figure 1 The flowchart of the SMS management method 100 according to the embodiment of the present disclosure is shown. Specifically, the method 100 includes:

[0043] S101, receiving a text message sending request sent by a text message sender, wherein the text message sending request carries a target text message and a target text message recipient corresponding to the target text message;

[0044] In some embodiments, the server on the operator side (it should be noted that the execution subject of the embodiment of the present application is not limited to the server on the operator side, and can also be the server of other institutions that can provide the same service as the operator) receives the SMS sending request sent by the SMS sender, and the SMS sender can be a bank, an e-commerce platform, an educational institution, etc. The SMS sending request carries the target SMS and the target SMS recipient corresponding to the target SMS. For example, when the SMS sender is a bank, the target SMS may be a SMS related to interest rates or financial investment, etc., and the target SMS recipient may be a user who has opened a corresponding bank account.

[0045] S102, determining a category label of the target short message and a purpose label of the target short message;

[0046] In some embodiments, determining the category label of the target text message and the purpose label of the target text message includes:

[0047] In the case where the signature of the target short message is stored in a database, determining the category label of the target short message according to the corresponding relationship between the signature and the category label stored in the database;

[0048] The text message content of the target text message is input into the trained first model to determine the purpose label of the target text message.

[0049] The signature of the target SMS is generally the real application name, website name or company name of the SMS sender, and the Chinese brackets "[]" need to be added at the beginning and end of the signature, such as [A Bank]. Category tags can include finance, e-commerce retail, online games, education and training, real estate agencies, stocks and securities, medical care, headhunting recruitment, tourism, Internet social communications, Internet entertainment, life services, Internet tools, logistics services and transportation, etc. The corresponding relationship between signatures and category labels will be pre-stored in the database. For example: A Bank-Finance, B Game Company-Games, C Maternal and Child Store-Life Services, etc. According to the signature of the target SMS and the corresponding relationship between the signature and the category label stored in the database, the category label of the target SMS is determined. For example: when the signature of the target SMS is [A Certain Game Company], the category label of the target SMS is determined to be game.

[0050] The purpose labels may include public welfare, business management, service, and commercial marketing. The first model may be trained using SMS data with known labels. The SMS content of the target SMS is input into the trained first model to determine the purpose label of the target SMS. For example, when the SMS content of the target SMS is "Dear customer, your credit card has been charged, please repay in time." Using the trained first model, the purpose label of the target SMS is determined to be "business management".

[0051] In the above embodiment, the category label of the target SMS is determined according to the signature of the target SMS and the corresponding relationship between the signature and the category label stored in the database; and the SMS content of the target SMS is input into the trained first model to determine the purpose label of the target SMS. This can improve the accuracy and efficiency of label recognition of the target SMS.

[0052] In some embodiments, when the signature of the target SMS is stored in the database, before determining the category label of the target SMS according to the corresponding relationship between the signature and the category label stored in the database, the method further includes:

[0053] Fine-tune the second model using part of the sample SMS data until the accuracy of the output result of the second model is greater than a preset threshold, the output result of the second model including the category label of the part of the sample SMS data and the purpose label of the part of the sample SMS data;

[0054] Inputting the remaining sample SMS data in the sample SMS data except the part of the sample SMS data into the fine-tuned second model to obtain the category label of the remaining sample SMS data and the purpose label of the remaining sample SMS data;

[0055] The corresponding relationship between the signature of the remaining sample SMS data and the category label of the remaining sample SMS data is stored in a database;

[0056] The first model is trained using the usage labels of the remaining sample SMS data.

[0057] The corresponding relationship between the signature and the category label stored in the database is obtained based on the sample SMS data and the second model. For fine-tuning the second model, the fine-tuning of the second model on a specific task can be achieved in the form of a system prompt, which can help the second model better understand and perform specific tasks without the need to retrain the entire second model on a large scale. First, the system prompt is adjusted using part of the sample SMS data in the sample SMS data, and then the accuracy of the output result of the fine-tuned second model is manually tested. When the accuracy is greater than the preset threshold, the remaining sample SMS data in the sample SMS data is input into the fine-tuned second model to obtain the category label of the remaining sample SMS data and the purpose label of the remaining sample SMS data. The corresponding relationship between the signature of the remaining sample SMS data and its category label is solidified in the database, so that the corresponding label can be directly queried for the signature existing in the database later.

[0058] Then, the purpose labels of the remaining sample SMS data are used to train the first model. The specific training process includes segmenting the SMS content of the remaining sample SMS data, removing stop words, extracting unigram features and bigram features, and vectorizing the text after segmentation. The training algorithms that can be used include the Long Short-Term Memory (LSTM) algorithm, etc. In addition, the training sample data of the first model can also come from manually annotated sample data, that is, the first model is trained by the purpose labels of manually annotated SMS data, which is not limited here.

[0059] In the above embodiment, by fine-tuning the second model on a specific task or a specific data set, the performance of the model on the task can be greatly improved. Compared with training a model from scratch, fine-tuning the model can save a lot of time and computing resources. Using the known usage labels of the remaining sample SMS data to train the first model can not only improve the performance, robustness and generalization ability of the first model, but also make full use of existing data resources to save costs and time.

[0060] In some embodiments, the first model is a large model, and the second model is a text multi-classification model or a deep learning model.

[0061] Since the content of SMS signatures varies, strong language understanding and background knowledge are required. The first model is suitable for using a large model, which can be fine-tuned to adapt to specific tasks and combined with manual online query and other means to achieve accurate processing. Since the purpose of SMS is relatively fixed and the content is highly structured, it is suitable to use traditional text multi-classification models or deep learning models, which can efficiently perform automatic classification using fixed-pattern data.

[0062] In some embodiments, the method further comprises:

[0063] In the case that the signature of the target text message is not stored in the database, the signature of the target text message is input into the fine-tuned second model to determine the category label of the target text message.

[0064] It should be noted that if the signature of the target SMS does not exist in the database, the signature of the target SMS can be directly input into the fine-tuned second model to obtain the category label of the target SMS, and then the correspondence between the signature of the target SMS and the category label of the target SMS is stored in the database.

[0065] In some embodiments, before fine-tuning the second model using part of the sample SMS data, the method further includes:

[0066] Get historical SMS data;

[0067] Deduplication of the historical text message data according to the signature of the historical text message data;

[0068] The historical SMS data after deduplication is desensitized to obtain sample SMS data.

[0069] Sample SMS data can be obtained based on historical SMS data, such as SMS data from the past month. Considering data security, historical SMS data can be deduplicated based on the signature of the historical SMS data, that is, SMS data with the same signature is deleted, and only one SMS data with each signature is retained. Then, sensitive information in the deduplicated historical SMS data is replaced to protect the privacy of users, such as replacing numbers with fixed characters, replacing names with fixed characters, etc.

[0070] Another way to obtain sample SMS data is as follows:

[0071] Get historical SMS data;

[0072] Desensitizing the historical SMS data;

[0073] The desensitized historical SMS data is deduplicated according to its signature and SMS content to obtain sample SMS data.

[0074] This implementation mainly takes into account the training effect of the second model, and can make the category label and purpose label output by the second model more accurate. For example, [A bank] may send an account arrival reminder or a marketing activity. According to the signature [A bank], it can be determined that the category label is financial, but only through the signature [A bank], it cannot be determined whether the purpose label is business reminder or marketing.

[0075] In the above embodiments, the deduplication operation can effectively clean up duplicate information, and the desensitization process can remove or blur sensitive information (such as name, phone number, account information, etc.), which can protect user privacy and ensure the security of data during use.

[0076] S103, obtaining the SMS category corresponding to the target SMS recipient and the SMS port registration purpose corresponding to the SMS sender;

[0077] In some embodiments, the target SMS recipient can register with the Ministry of Industry and Information Technology, Security Manager and other departments to choose the category of willingness to receive SMS, and the operator server can then obtain it from the database of the Ministry of Industry and Information Technology, Security Manager and other departments through the corresponding application programming interface (Application Programming Interface, API); the SMS sender also needs to pre-register the purpose of the SMS port it will send and store it in the database on the operator side to prevent the actual purpose of the SMS sent by the subsequent SMS sender from being inconsistent with the pre-registered purpose.

[0078] S104: Determine whether to send the target SMS to the target SMS recipient according to the category label of the target SMS and the purpose label of the target SMS, as well as the category of the SMS to be received and the registered purpose of the SMS port.

[0079] In some embodiments, the information about the willingness to receive text messages includes the category of the text messages that are willing to be received and the purpose of the text messages that are willing to be received;

[0080] The step of determining whether to send the target SMS to the target SMS recipient according to the category label of the target SMS and the purpose label of the target SMS, as well as the category of the SMS to be received and the registered purpose of the SMS port, comprises:

[0081] When the category tag of the target SMS matches the category of the SMS to be received and the purpose tag of the target SMS matches the purpose registered in the SMS port, the target SMS is sent to the target SMS recipient;

[0082] In the case that the category tag of the target SMS does not match the category of the SMS to be received and / or the purpose tag of the target SMS does not match the purpose registered in the SMS port, the target SMS is intercepted.

[0083] If the category tag of the target SMS matches the category of the SMS to be received and the purpose tag of the target SMS matches the purpose registered on the SMS port, the operator server can send the target SMS to the target SMS recipient;

[0084] If the category label of the target SMS does not match the category of the SMS to be received and the purpose label of the target SMS does not match the registered purpose of the SMS port, the operator server can intercept the target SMS and not send it to the target SMS recipient.

[0085] In the above embodiment, by combining the category label and purpose label of the target SMS, as well as the SMS category corresponding to the target SMS recipient and the SMS port registration purpose corresponding to the SMS sender, it is possible to accurately determine whether to send the SMS to the target SMS provider, thereby reducing harassment to the target SMS provider.

[0086] See also Figure 2 In some embodiments, the server on the operator side first performs relevant data processing on the historical SMS data to obtain sample SMS data. Then, the second model is fine-tuned using part of the sample SMS data until the accuracy of the output result of the second model is greater than a preset threshold. The remaining sample SMS data in the sample SMS data is then input into the fine-tuned second model to obtain the category label of the remaining sample SMS data and the purpose label of the remaining sample SMS data; the corresponding relationship between the signature of the remaining sample SMS data and the category label of the sample SMS data is stored in the database; and the purpose label of the remaining sample SMS data is used to train the first model.

[0087] Then, the server on the operator side receives the SMS sending request sent by the SMS sender, which carries the target SMS and the target SMS recipient corresponding to the target SMS. Then, the category label of the target SMS is determined based on the signature of the target SMS and the corresponding relationship between the signature and the category label stored in the database; if the signature of the target SMS does not exist in the database, the signature of the target SMS can be directly input into the fine-tuned second model to obtain the category label of the target SMS, and then the corresponding relationship between the signature of the target SMS and the category label of the target SMS is stored in the database. The SMS content of the target SMS is input into the trained first model to determine the purpose label of the target SMS.

[0088] The target SMS recipient can pre-register with the Ministry of Industry and Information Technology, Security Manager and other departments to choose the category of SMS receiving intention. The SMS sender also needs to pre-register the purpose of the SMS port it will send and store it in the operator's database to prevent the actual purpose of the SMS sent by the subsequent SMS sender from being inconsistent with the pre-registered purpose.

[0089] When making the comparison, the server on the operator side needs to obtain the target SMS recipient's SMS category from the Ministry of Industry and Information Technology, Security Manager and other departments through the corresponding API interface, and obtain the SMS sender's SMS port registration purpose from the operator's database. When the target SMS category label matches the SMS category and the target SMS purpose label matches the SMS port registration purpose, the target SMS is sent to the target SMS recipient;

[0090] As long as the category label of the target SMS does not match the category of the SMS to be received and the purpose label of the target SMS does not match the purpose registered in the SMS port, the target SMS will be intercepted.

[0091] According to an embodiment of the present disclosure, a text message sending request sent by a text message sender is received, the text message sending request carries a target text message and a target text message recipient corresponding to the target text message; the category label of the target text message and the purpose label of the target text message are determined; the category of the text message that is willing to be received corresponding to the target text message recipient and the text message port registration purpose corresponding to the text message sender are obtained, and the text message port registration information includes the category of the text message that the target text message recipient is willing to receive and the purpose of the text message; according to the category label of the target text message and the purpose label of the target text message, as well as the category of the text message that is willing to be received and the purpose of the text message port registration, it is determined whether to send the target text message to the target text message recipient. In this embodiment, the target text message is classified by the category label of the target text message and the purpose label of the target text message, and whether to send the target text message to the target text message recipient is determined in combination with the category of the text message that is willing to be received corresponding to the target text message recipient and the purpose of the text message port registration corresponding to the text message sender, thereby improving the accuracy of text message management.

[0092] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present disclosure is not limited by the order of the actions described, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

[0093] The above is an introduction to the method embodiment. The following is a further explanation of the scheme disclosed in the present invention through an apparatus embodiment.

[0094] Figure 3 A block diagram of a short message management device 300 according to an embodiment of the present disclosure is shown, and the device 300 includes:

[0095] The first receiving module 301 is used to receive a text message sending request sent by a text message sender, wherein the text message sending request carries a target text message and a target text message recipient corresponding to the target text message;

[0096] A first determination module 302, configured to determine a category label of the target SMS and a purpose label of the target SMS;

[0097] The first acquisition module 303 is used to acquire the SMS category corresponding to the target SMS recipient and the SMS port registration purpose corresponding to the SMS sender;

[0098] The second determination module 304 is used to determine whether to send the target SMS to the target SMS recipient according to the category label of the target SMS and the purpose label of the target SMS, as well as the category of the SMS to be received and the registered purpose of the SMS port.

[0099] Furthermore, the first determining module includes:

[0100] A first determining unit, configured to determine the category label of the target short message according to the corresponding relationship between the signature and the category label stored in the database when the signature of the target short message is stored in the database;

[0101] The second determination unit is used to input the SMS content of the target SMS into the trained first model to determine the purpose label of the target SMS.

[0102] Furthermore, the device also includes:

[0103] A first processing module, used to fine-tune the second model using part of the sample SMS data in the sample SMS data until the accuracy of the output result of the second model is greater than a preset threshold, and the output result of the second model includes a category label of the part of the sample SMS data and a purpose label of the part of the sample SMS data;

[0104] A second processing module is used to input the remaining sample SMS data in the sample SMS data except the part of the sample SMS data into the fine-tuned second model to obtain the category label of the remaining sample SMS data and the purpose label of the remaining sample SMS data;

[0105] A first storage module, configured to store the corresponding relationship between the signature of the remaining sample SMS data and the category label of the remaining sample SMS data in a database;

[0106] The first training module is used to train a first model using the usage labels of the remaining sample SMS data.

[0107] Furthermore, the device also includes:

[0108] The first acquisition module is used to acquire historical SMS data;

[0109] A first deduplication module, configured to dedupe the historical SMS data according to the signature of the historical SMS data;

[0110] The third processing module is used to perform desensitization processing on the historical SMS data after deduplication to obtain sample SMS data.

[0111] Furthermore, the device also includes:

[0112] The third determination module is used to input the signature of the target text message into the fine-tuned second model to determine the category label of the target text message when the signature of the target text message is not stored in the database.

[0113] Furthermore, the second determining module includes:

[0114] A first sending unit, configured to send the target SMS to the target SMS recipient if the category tag of the target SMS matches the category of the SMS to be received and the purpose tag of the target SMS matches the purpose registered in the SMS port;

[0115] The first interception unit is used to intercept the target SMS when the category tag of the target SMS does not match the category of the SMS to be received and / or the purpose tag of the target SMS does not match the purpose registered in the SMS port.

[0116] Figure 4 An example of a physical structure diagram of an electronic device is shown. The electronic device may be a smart terminal, and its internal structure diagram may be as follows: Figure 4 As shown. The electronic device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above-mentioned SMS management method is implemented.

[0117] On the other hand, the present invention further provides a computer storage medium storing a computer program, which implements the above-mentioned SMS management method when executed by a processor.

[0118] In another aspect, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and when the processor executes the computer instructions, the above-mentioned SMS management method is implemented.

[0119] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments 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 non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory.

[0120] By way of illustration and not limitation, Random Access Memory (RAM) is available in many forms, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), Rambus Direct RAM (RDRAM), Direct Rambus Dynamic RAM (DRDRAM), and Rambus Dynamic RAM (RDRAM).

[0121] It should be noted that the above detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present application belongs.

[0122] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should also be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0123] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.

[0124] In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or inherent to these processes, methods, products, or apparatuses.

[0125] For ease of description, spatially relative terms, such as "above", "above", "on the upper surface of", "above", etc., may be used herein to describe the spatial positional relationship between a device or feature and other devices or features as shown in the figure. It should be understood that spatially relative terms are intended to include different orientations of the device in use or operation in addition to the orientation described in the figure. For example, if the device in the accompanying drawings is inverted, the device described as "above other devices or structures" or "above other devices or structures" will be positioned as "below other devices or structures" or "below other devices or structures". Thus, the exemplary term "above" may include both "above" and "below". The device may also be positioned in other different ways, such as rotated 90 degrees or in other orientations, and the spatially relative descriptions used herein are interpreted accordingly.

[0126] In the above detailed description, reference is made to the accompanying drawings, which form a part of this document. In the accompanying drawings, similar symbols typically identify similar components unless the context indicates otherwise. The illustrated embodiments described in the detailed description, drawings, and claims are not meant to be limiting. Other embodiments may be used, and other changes may be made, without departing from the spirit or scope of the subject matter presented herein.

[0127] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for managing short messages, characterized in that: The method comprises: Receiving a text message sending request sent by a text message sender, the text message sending request carrying a target text message and a target text message recipient corresponding to the target text message; Determining a category label of the target text message and a purpose label of the target text message; Acquire the SMS category corresponding to the target SMS recipient and the SMS port registration purpose corresponding to the SMS sender; Determine whether to send the target SMS to the target SMS recipient according to the category label of the target SMS and the purpose label of the target SMS, as well as the category of the SMS to be received and the registration purpose of the SMS port; The determining of the category label of the target short message and the purpose label of the target short message includes: In the case where the signature of the target short message is stored in a database, determining the category label of the target short message according to the corresponding relationship between the signature and the category label stored in the database; Inputting the SMS content of the target SMS into the trained first model to determine the purpose label of the target SMS; The step of determining whether to send the target SMS to the target SMS recipient according to the category label of the target SMS and the purpose label of the target SMS, as well as the category of the SMS to be received and the registered purpose of the SMS port, comprises: When the category tag of the target SMS matches the category of the SMS to be received and the purpose tag of the target SMS matches the purpose registered in the SMS port, the target SMS is sent to the target SMS recipient; In the case that the category tag of the target SMS does not match the category of the SMS to be received and / or the purpose tag of the target SMS does not match the purpose registered in the SMS port, the target SMS is intercepted.

2. The method for managing short messages according to claim 1, characterized in that: In the case where the signature of the target short message is stored in the database, before determining the category label of the target short message according to the corresponding relationship between the signature and the category label stored in the database, the method further includes: Fine-tune the second model using part of the sample SMS data until the accuracy of the output result of the second model is greater than a preset threshold, the output result of the second model including the category label of the part of the sample SMS data and the purpose label of the part of the sample SMS data; Inputting the remaining sample SMS data in the sample SMS data except the part of the sample SMS data into the fine-tuned second model to obtain the category label of the remaining sample SMS data and the purpose label of the remaining sample SMS data; The corresponding relationship between the signature of the remaining sample SMS data and the category label of the remaining sample SMS data is stored in a database; The first model is trained using the usage labels of the remaining sample SMS data.

3. The method for managing short messages according to claim 2, characterized in that: Before fine-tuning the second model using part of the sample SMS data, the method further includes: Get historical SMS data; Deduplication of the historical text message data according to the signature of the historical text message data; The historical SMS data after deduplication is desensitized to obtain sample SMS data.

4. The method for managing short messages according to claim 2, characterized in that: The method further comprises: In the case that the signature of the target text message is not stored in the database, the signature of the target text message is input into the fine-tuned second model to determine the category label of the target text message.

5. A short message management device, characterized in that: The device is used to implement the SMS management method according to any one of claims 1 to 4, and the device includes: A first receiving module, configured to receive a text message sending request sent by a text message sender, wherein the text message sending request carries a target text message and a target text message recipient corresponding to the target text message; A first determination module, used to determine the category label of the target short message and the purpose label of the target short message; The first acquisition module is used to acquire the SMS category corresponding to the target SMS recipient and the SMS port registration purpose corresponding to the SMS sender; The second determination module is used to determine whether to send the target SMS to the target SMS recipient according to the category label of the target SMS and the purpose label of the target SMS, as well as the category of the SMS to be received and the registered purpose of the SMS port.

6. An electronic device, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the short message management method as claimed in any one of claims 1 to 4 when executed by the processor.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the short message management method according to any one of claims 1 to 4 are implemented.

8. A computer program product, characterized in that The method comprises computer instructions, which, when executed by a processor, implement the steps of the short message management method according to any one of claims 1 to 4.

Images