AI-based short message platform intelligent operation method and system

Abstract

Embodiments of the present specification relate to the field of information technology, in particular to an AI-based short message platform intelligent operation method and system. The method comprises the steps of: intercepting short messages sent to a user's mobile phone based on the user's registration; identifying the content semantics of the short messages, and identifying the category of the short messages according to the content semantics; according to the preset instant sending category, instantaneously sending the short messages of the instant sending category to the user's mobile phone; grouping the short messages of the notification category according to the content semantics, extracting the abstract of all short messages of the notification category within a period according to a preset period, generating a link for viewing all short messages within the group, and sending the abstract and the link to the user's mobile phone; and in response to the user's operation, showing or sending the selected short messages to the user.

Description

TECHNICAL FIELD

[0001] Embodiments of the present specification relate to the field of information technology, in particular to an AI-based short message platform intelligent operation method and system. BACKGROUND

[0002] As a basic and stable communication method, short messages still play an irreplaceable role in financial transactions, identity verification, system alarms, logistics notifications, etc. However, the number of short messages received by users every day is increasing, and a large number of them are repetitive notifications, reminders, or aggregable information. The existing short message receiving mechanism generally adopts a one-by-one pushing method, lacks semantic understanding and intelligent aggregation capabilities, resulting in the user's mobile phone being frequently brushed by irrelevant or low-value short messages. Not only does this interfere with normal communication and consume attention resources, but it can also miss truly urgent or important content due to information overload. In addition, some short messages contain the intention to guide users to open a specific App or query public information, but due to the limitations of short message format and interaction capabilities, manual copying, jumping, and searching are often required, resulting in a fragmented experience and low efficiency. Therefore, further research on short message communication technology is needed. SUMMARY

[0003] The embodiments of the present specification describe an AI-based short message platform intelligent operation method and system.

[0004] In a first aspect, the embodiments of the present specification provide an AI-based short message platform intelligent operation method, comprising the steps of:

[0005] intercepting short messages sent to the user's mobile phone based on the user's registration;

[0006] identifying the content semantics of the short messages and identifying the categories of the short messages according to the content semantics;

[0007] sending short messages of instant sending categories to the user's mobile phone instantaneously according to preset instant sending categories;

[0008] grouping short messages of the notification category according to content semantics, extracting summaries of all short messages of the notification category within a preset period, generating a link for viewing all short messages within the group, and sending the summaries and the link to the user's mobile phone;

[0009] in response to the user's operation, showing or sending the selected short messages to the user.

[0010] In a second aspect, the embodiments of the present specification provide an AI-based short message platform intelligent operation system, comprising:

[0011] an intercepting module that intercepts short messages sent to the user's mobile phone based on the user's registration;

[0012] an identifying module that identifies the content semantics of the short messages and identifies the categories of the short messages according to the content semantics;

[0013] The sending module instantaneously sends the short message of the instant sending category to the user's mobile phone according to the preset instant sending category;

[0014] The notification module groups the short messages of the notification category according to content semantics, extracts an abstract of all short messages of the notification category in a preset period according to a preset period, generates a link for viewing all short messages in the group, and sends the abstract and the link to the user's mobile phone;

[0015] The display module displays or sends the selected short message to the user in response to the user's operation.

[0016] In a third aspect, the embodiments of the present specification provide an electronic device, comprising a processor and a memory;

[0017] The processor is connected with the memory;

[0018] The memory is used for storing executable program codes;

[0019] The processor runs a program corresponding to the executable program codes by reading the executable program codes stored in the memory, so as to execute the method of any one of the above aspects.

[0020] In a fourth aspect, the embodiments of the present specification provide a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method of any one of the above aspects.

[0021] In a fifth aspect, the embodiments of the present specification provide a computer program product, comprising a computer program, and the computer program is executed by a processor to implement the method of any one of the above aspects.

[0022] The technical solutions provided by some embodiments of the present specification have at least the following beneficial effects:

[0023] In the AI-based short message platform intelligent operation method and system provided in the embodiments of the present specification, the short messages are subjected to semantic recognition, classification and periodic aggregation, the notification category short messages are combined into structured abstracts, the number of short messages received by the user's mobile phone is reduced, frequent disturbances are avoided, and information reading efficiency is significantly improved. The preset instant sending category ensures that high-priority short messages are directly pushed, and the information is simplified and the real-time performance of key short messages is considered. The AI is used to identify the intention of the short message, and whether the semantic information of guiding to open the App or involving public information is detected, and then a calling instruction or an abstract of supplementary public information is automatically generated, so as to reduce the user's manual operation and improve the reading efficiency.

[0024] Other features and advantages of the embodiments of the present specification will be further disclosed in the following specific embodiments and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present specification, the drawings required to be used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description only constitute some embodiments of the present specification, and other drawings can also be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0026] Figure 1 The short message platform running schematic diagram provided for the embodiments of the present specification.

[0027] Figure 2 The short message platform intelligent running method flow schematic diagram provided for the embodiments of the present specification.

[0028] Figure 3 The extended abstract generation schematic diagram provided for the embodiments of the present specification.

[0029] Figure 4 The short message platform intelligent running system schematic diagram provided for the embodiments of the present specification.

[0030] Figure 5 The electronic device schematic diagram provided for the embodiments of the present specification. DETAILED DESCRIPTION

[0031] The technical solutions of the embodiments of the present specification will be explained and described in combination with the drawings of the embodiments of the present specification. However, the following embodiments are only preferred embodiments of the present specification, and not all. Based on the embodiments in the embodiments, other embodiments obtained by those skilled in the art without creative effort are within the protection scope of the present specification.

[0032] In the present specification, the terms “first”, “second”, “third” and the like in the specification and claims and the above-mentioned drawings are used to distinguish different objects, and are not used to describe a specific order. In addition, the terms “include” and “have” and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed or can optionally include other steps or units inherent to the process, method, product or device.

[0033] In the following description, the appearance of terms such as “inner”, “outer”, “upper”, “lower”, “left”, “right” and the like indicating the orientation or position relationship are only for the convenience of describing the embodiments and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present specification.

[0034] The data involved in the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0035] Before introducing the technical solutions recorded in the present specification, the application scenarios of the technical solutions and related technologies are introduced.

[0036] Short Message Service (SMS) is a text communication protocol based on GSM, CDMA and other cellular mobile communication networks. It relies on the signaling channel to transmit short text information and only requires basic cellular signals to complete sending and receiving. The SMS system architecture includes the SMS center, mobile switching center, home location register, etc., to ensure message storage, forwarding and delivery. Due to its protocol standardization, high device compatibility, wide network coverage and high delivery success rate, SMS has become the first information service carrier to achieve end-to-end reliable communication.

[0037] SMS is independent of Internet applications and can effectively defend against "man-in-the-middle attacks" or "session hijacking". SMS does not rely on specific App or account system and covers all mobile phone users. When the user's mobile phone 20 is invaded or the App is uninstalled, SMS can still be used as a secure communication channel. Moreover, SMS has the feature of forced delivery, so even if the user does not turn on the data or does not install a specific App, it can still be received. The delivery success rate is as high as 99% or more, much higher than push notifications or emails. It has strong legal effect and is often used as an effective basis for delivery in the fields of justice and finance. Therefore, although instant messaging Apps and rich media messages are increasingly popular, in some key scenarios, SMS still has irreplaceable technical advantages and practical effects. For example, bank login, payment confirmation, App registration, two-factor authentication (2FA), government service platform identity verification, etc.

[0038] For example, IT system administrators or operation and maintenance engineers often need to receive alarm SMS from server monitoring, network equipment, security systems, etc. (such as downtime, insufficient disk space, login exceptions, etc.). E-commerce platform operators or operators receive a large number of order notifications, marketing activity registration notifications, refund application reminders, etc. every day. Public service personnel may receive a large number of user feedback, complaints, appointment notifications, etc. In the absence of unified hosting and sorting services, users have difficulty effectively managing these SMS. This results in users spending more time processing SMS. And important SMS can be overwhelmed and not processed in time. For this reason, please refer to the attached Figure 1The present specification provides an AI-based short message platform intelligent operation method and system. By intercepting short messages sent to user mobile phones 20 and identifying categories, the short messages are processed according to the categories. For instant categories, the short messages are instantly sent to user mobile phones 20. For example, identity verification category short messages, verification code short messages, financial transaction confirmation and risk blocking prompt short messages, emergency warning and system security category short messages (for example, your ECS server (ID: i-abc123) CPU usage rate has been 100% for more than 5 minutes, suspected of being attacked), key process triggering and operation confirmation category short messages (for example, your submitted application has entered the audit link, please upload supplementary materials within 24 hours), and legal documents or official mandatory notification category short messages. The short messages 12 of the notification category are grouped according to the content semantics 14, the abstracts are extracted according to the preset period, the link for viewing all short messages in the group is generated, and the abstracts 13 and the link are sent to the user mobile phones 20.

[0039] Specifically, an AI-based short message platform intelligent operation method, please refer to the attached Figure 2 , comprising the steps of:

[0040] Step S1) Intercepting short messages sent to user mobile phones 20 based on user registration.

[0041] Before the short messages arrive at the user mobile phones 20, the system (server / sms gateway) actively intercepts all short messages that should be directly delivered to the mobile phone according to the user's pre-registered authorization or configuration, and imports them into the background processing platform, providing data basis for subsequent AI semantic recognition, classification, aggregation, intelligent distribution and other operations. The user first completes the "registration" or "authorization" to enable the short message interception and intelligent management service provided by the short message platform. The exemplary registration methods include: binding the mobile phone number in the App or Web platform, authorizing the system to collect short messages; or, through the operator cooperation channel (such as short message forwarding API, virtual number service) to route the short messages to the platform. In the present specification, the short message content is stored and transmitted by encryption, so that the processing of the short message conforms to the relevant management regulations.

[0042] Step S2) Identifying the content semantics 14 of the short message, and identifying the category of the short message according to the content semantics 14. The intercepted short messages are subjected to semantic analysis and classified into predefined categories. Specifically, it comprises the steps of:

[0043] Reading a preset keyword classification table, which records a plurality of keywords corresponding to the category of each short message;

[0044] When the short message or the content semantics 14 of the short message has a matching keyword, the category of the short message is set to the category corresponding to the matching keyword;

[0045] reading a preset category description, respectively calculating the matching degree of the content semantics 14 of the remaining short message and the category description;

[0046] obtaining the category of the short message according to the matching degree.

[0047] constructing and maintaining a structured mapping table, for example, the categories of short messages include "verification code category", "transaction notification category", "logistics notification category", "system alarm category", "marketing promotion category", "government notification category", etc. A set of key words or phrases with clear direction and high discrimination is configured under each category. For example, explicit trigger words ("verification code", "payment success", "your order", "server downtime"); institution identification words (such as "[XX bank]", "[XX express]", "[XX cloud]"); action verbs (such as "please confirm", "charged", "will expire soon", "abnormal login"); specific symbols (such as containing "￥", "# number#", "[emergency] structured mark"). If the key word matching is successful, the short message is directly classified into the corresponding category.

[0048] For short messages that do not match any key words, semantic understanding-based classification is performed. By calculating the semantic similarity between the content of the short message and the category semantic description, classification is realized. A semantic description text is constructed for each short message category to represent the core semantic boundary and typical intent of the category. For example, the category semantic description of "verification code category" is: "a one-time digital string used for identity verification, usually sent by the system when the user logs in, registers, or pays, and requires the user to input within a limited time."

[0049] The category semantic description of "system alarm category" is: "a notification reflecting the abnormal state of IT infrastructure, application program or device operation, usually containing error code, resource index, timestamp, and requiring administrator intervention."

[0050] The original text or content semantics 14 of the short message is input into the pre-accessed semantic encoder to generate a fixed-dimensional semantic vector, and the category semantic description is also encoded into a semantic vector. The similarity (such as cosine similarity, Euclidean distance calculation) between the semantic vector corresponding to the short message and the semantic vector corresponding to each category semantic description is calculated. If the highest similarity exceeds a preset threshold (such as 0.75), the short message is classified into the corresponding category. If all similarities are below the threshold, it is marked as "unknown category" or "to be manually reviewed", or a default category. Short messages that do not match the category can also be immediately sent to the user's mobile phone 20.

[0051] Step S3) According to the preset instant sending category, the instant sending short message 11 is instantaneously sent to the user mobile phone 20. Whether the category to which the short message belongs exists in the "instant sending category" is inquired, if the matching is successful, the short message is marked as "instant sending object", and the short message is instantaneously sent to the user mobile phone 20.

[0052] Step S4) The notification category short message 12 is grouped according to the content semantics 14, the abstract of all notification category short messages 12 in the period is extracted according to the preset period, the link for viewing all short messages in the group is generated, and the abstract 13 and the link are sent to the user mobile phone 20.

[0053] The non-instant, aggregable and low-urgency notification category short messages (such as marketing push, logistics update, system log, subscription reminder, bill summary, etc.) are subjected to semantic clustering, periodic abstract extraction 13 and the like, so as to realize the reduction of the information interference frequency on the mobile phone end and the improvement of the information processing efficiency on the premise of guaranteeing the right to know of the user.

[0054] For all short messages classified as notification category, instead of being sorted by sender or time, automatic clustering grouping is performed based on the internal consistency of the semantic level. The preset period type can adopt a fixed time window, such as "every 6 hours", "every morning 10 o'clock" or "every Monday 9:00". Or it can be triggered by an event, such as "triggered after 5 cumulative updates of the same order", "summarized after 10 notifications of the same App". Different periods can be set for different categories of short messages. Or different periods can be set for different short message sending subjects.

[0055] For all short messages in each semantic group, text abstract generation is performed, and highly summarized and readable abstract text is output. The "contribution degree" of each short message in the group to the overall semantics is calculated (such as TF-IDF weight, semantic centrality, information entropy, etc.).

[0056] For example, the same status update is automatically identified and merged (such as multiple "order processing" only keeping the latest one). The numerical information such as amount, quantity and times is automatically summed, counted and extreme value extracted (such as "5 refunds are received in total, with a total of ￥892.50"). The multi-time point event is compressed into "start-end interval + key node" (such as "service interruption from 14:00 to 17:30, with 3 restarts during the period"). The structure of the link for viewing all short messages in the group includes unique identification, permission control and short chain service. The unique identification includes "period ID + semantic group ID + user Token". Token is used to verify the user identity and access permission to prevent unauthorized access; short chain compression URL is used to save short message characters. The link points to a Web page or an embedded WebView in an App, which dynamically renders all original short messages in the group.

[0057] For example, according to the setting of an operator, at 3:00 pm, the received summary 13 and the link are: "In the past 6 hours, 12 alarms have been received: 8 have been automatically recovered (CPU / memory fluctuations); 3 are pending: DB master-slave delay > 5s (db-prod-01), disk usage rate 98% (log-svr-07), API 5xx error rate surge. Complete SMS viewing link: {link}". The operator can thereby reduce the number of SMS received, i.e. the number of interruptions, and immediately start processing db-prod-01, log-svr-07 and API 5xx.

[0058] Step S5) in response to the operation of the user, the selected SMS is displayed or sent to the user. Specifically, it includes:

[0059] The contribution of each SMS to the summary 13 is calculated;

[0060] When the user clicks on the link, all the SMSs in the group are displayed to the user, and the SMSs are arranged in descending order of the contribution;

[0061] A trigger link is added after each SMS, and when the trigger link is clicked, the corresponding SMS is sent to the user's mobile phone 20.

[0062] The contribution is a quantitative indicator that measures the role of an original SMS in generating the current summary 13, which is used for subsequent sorting and priority display to ensure that the user first sees the most critical and representative content.

[0063] The clustering center of the SMSs in the active group is calculated, and the distance between the semantic vector of the SMS and the clustering center of the semantic group is calculated as the semantic center degree. The closer the SMS to the clustering center, the stronger the common characteristics of the group, and the higher the initial contribution is set. The rarity of the keywords or semantic fragments contained in the SMS in the group is calculated, and the SMS containing unique information such as "abnormal state", "error code", "numerical extreme value", etc. The contribution is increased. The SMS with high repetition or strong template (such as "processing…") reduces the contribution. The SMS close to the period cutoff time increases the contribution. The final contribution is obtained.

[0064] On the other hand, in another embodiment, the SMS platform intelligent operation method further includes the steps of:

[0065] Before the SMS is sent to the user's mobile phone 20, it is judged whether the content semantics 14 of the SMS includes semantics for guiding the opening of a specified APP;

[0066] When the semantics for guiding the opening of a specified APP is included, an instruction code 31 for calling the specified APP is generated, and the relevant calling parameters are attached to the instruction code 31, and the instruction code 31 is embedded in the corresponding position of the SMS.

[0067] When the user clicks the link in the summary message, the Token or Session carried in the URL is parsed, the user's identity and access rights are verified, and it is checked whether the user has the authorization to view the group message (to prevent unauthorized access). A "send to mobile phone" trigger link is embedded after each message entry. Thus, the user is no longer a passive recipient, but can choose which to view and which to send.

[0068] On the other hand, in another embodiment, the intelligent operation method of the short message platform further comprises the steps of:

[0069] determining whether the content semantics 14 of the notification category short message 12 includes semantics related to public information 32;

[0070] when the semantics related to public information 32 is included, searching the public information 32 on the network;

[0071] generating a summary 13 of the public information 32 as an extended summary according to the content semantics 14 of the short message and the public information 32;

[0072] embedding the extended summary in the corresponding position of the short message.

[0073] The method of generating a summary 13 of the public information 32 as an extended summary according to the content semantics 14 of the short message and the public information 32 comprises:

[0074] extracting the value-related 41 and value-pursuit tendency 42 of the content semantics 14 of the short message;

[0075] calculating the matching degree of the searched public information 32 and the value-related 41, and selecting the public information 32 according to the matching degree;

[0076] excluding the public information 32 with a matching degree lower than a preset reference value, and dividing the remaining public information 32 into two groups according to the value-pursuit tendency 42;

[0077] extracting the summary 13 of the public information 32 in each group respectively, and merging the summaries 13 of the two groups as an extended summary.

[0078] By actively searching public information 32 on the network and generating an extended summary, the extended summary is embedded in the short message or the summary 13, so that the short message is upgraded from "notification" to "decision support tool", the user does not need to search manually, and the key external information is embedded by the short message platform, providing the user with a more convenient short message use experience. Please refer to the attached Figure 3, the value-related value 41 and the value pursuit tendency 42 are extracted using the value intention recognition model (obtained based on BERT fine-tuning). The value-related value 41 represents the core interest points that the user is most concerned about in the short message scenario, such as "saving costs" (promotions, discounts, refunds), "improving efficiency" (business processes, system updates, operation guidelines), and the like.

[0079] The value pursuit tendency 42 is the behavior tendency of the user when facing the value represented by the content semantics 14 of the short message. It is usually divided into two categories: positive pursuit, which hopes to obtain, participate in, or utilize the information (such as "grabbing" or "registering"); and negative avoidance, which hopes to avoid, defend against, or evade the losses caused by the information.

[0080] For each piece of searched public information 32 (web page summary 13, policy provisions, news title, data card, etc.), after semantic vectorization, the cosine similarity with the value-related value 41 is calculated or scored using a Cross-Encoder model (0-1). Only information with a similarity not less than a preset reference value (such as 0.65) is retained, and irrelevant or low-relevance results are filtered out.

[0081] The filtered public information 32 is divided into two groups according to the consistency of its content tendency and the value pursuit tendency 42. Exemplarily, they are the support group and the conflict group. The support group represents the consistency of the content tendency and the user's value pursuit (such as the user wanting to "avoid restrictions", and the information providing "alternative routes" or "subway operation times"). Or providing a solution to "how to achieve a positive value" (such as "how to get a coupon" or "best buy timing analysis"). The conflict group represents the inconsistency of the content tendency and the user's value pursuit or provides risk warnings (such as "the promotion activity has hidden terms" or "the road segment will be more congested tomorrow"). Or providing "negative examples", "cautions", or "exceptional cases". A natural language reasoning model is used to determine the "implication", "contradiction", or "neutral" relationship between the information and the user's tendency.

[0082] On the other hand, the present specification provides an AI-based short message platform intelligent operation system, please refer to the attached Figure 4 , comprising:

[0083] The interception module 100 intercepts the short message sent to the user's mobile phone 20 based on the user's registration;

[0084] The recognition module 200 recognizes the content semantics 14 of the short message and identifies the category of the short message according to the content semantics 14;

[0085] The sending module 300 instantaneously sends the short message of the instantaneously sent category to the user's mobile phone 20 according to the pre-set instantaneously sent category;

[0086] The notification module 400 groups the notification category short messages 12 according to the content semantics 14, extracts the abstracts 13 of all the notification category short messages 12 in a preset period according to the preset period, generates a link for viewing all the short messages in the group, and sends the abstracts 13 and the link to the user's mobile phone 20.

[0087] The display module 500 displays or sends the selected short message to the user in response to the user's operation.

[0088] Referring to Figure 5 An electronic device structure diagram is shown in the embodiment of the present specification.

[0089] As Figure 5 The electronic device 1100 can include at least one processor 1101, at least one network interface 1104, a user interface 1103, a memory 1105, and at least one communication bus 1102. The communication bus 1102 can be used to realize the connection and communication of the above-mentioned components. The user interface 1103 can include a key, and the optional user interface can also include a standard wired interface, a wireless interface. The network interface 1104 can include, but is not limited to, a Bluetooth module, an NFC module, a Wi-Fi module, etc. The processor 1101 can include one or more processing cores. The processor 1101 connects various parts in the entire electronic device 1100 through various interfaces and lines, executes various functions of the routing device and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 1105, and calling data stored in the memory 1105. Optionally, the processor 1101 can be realized by at least one of DSP, FPGA, and PLA. The processor 1101 can integrate CPU, GPU, and modem, etc. The CPU is mainly used to process operating systems, user interfaces, and application programs, etc.; the GPU is used to render and draw the content required to be displayed on the display screen; and the modem is used to process wireless communication.

[0090] It can be understood that the above-mentioned modem can also not be integrated into the processor 1101, but be realized by a separate chip.

[0091] The memory 1105 can include a RAM and can also include a ROM. Optionally, the memory 1105 includes a non-transitory computer-readable medium. The memory 1105 can be used for storing instructions, programs, codes, code sets, or instruction sets. The memory 1105 can include a program storage area and a data storage area, wherein the program storage area can store the instructions for implementing the operating system, the instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), the instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area can store the data involved in the above-mentioned various method embodiments, etc. The memory 1105 can also be at least one storage device located away from the aforementioned processor 1101. The memory 1105, as a computer storage medium, can include an operating system, a network communication module, a user interface module, and an application program. The processor 1101 can be used to invoke the application program stored in the memory 1105 and execute the method in the above-mentioned embodiments.

[0092] The embodiments of the present specification also provide a computer-readable storage medium, which stores instructions, and when the instructions run on a computer or a processor, the computer or the processor executes the steps in the above-mentioned embodiments. The various component modules of the above-mentioned electronic device, if realized in the form of software function units and sold or used as independent products, can be stored in the computer-readable storage medium.

[0093] The embodiments of the present specification also provide a computer program product, which includes a computer program, and the computer program is executed by a processor to realize the steps in the above-mentioned embodiments.

[0094] The technical features in the embodiments and the implementation forms can be combined arbitrarily without conflict.

[0095] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes a plurality of computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present specification are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in or transmitted by a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through a wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. integrated with a plurality of available media. The available media can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a digital versatile disc (DVD)), or a semiconductor medium (for example, a solid state disk (SSD)) and the like.

[0096] When implemented by hardware or firmware, the foregoing method processes are programmed into a hardware circuit to obtain a corresponding hardware circuit structure, and the corresponding functions are implemented. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is an integrated circuit whose logic function is determined by the user programming the device. A digital system is "integrated" on a PLD by the designer himself programming, without having to ask the chip manufacturer to design and manufacture a special integrated circuit chip. Moreover, instead of manually making integrated circuit chips, such programming is now mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing programs, and the original code to be compiled must also be written in a specific programming language, which is called a hardware description language (HDL), and there are many HDLs. Those skilled in the art should also understand that only the method processes need to be logically programmed in the above-mentioned several hardware description languages and programmed into integrated circuits to easily obtain hardware circuits that implement the logical method processes.

[0097] The above-described embodiments are merely exemplary diagnostic description rather than limitations on the scope of the present specification. Any modifications, equivalent replacements, and improvements made to the technical solutions of the present specification by those of ordinary skill in the art, without departing from the design spirit of the present specification, shall fall within the protective scope of the claims of the present specification.

Claims

1. An AI-based short message platform intelligent operation method, characterized in that, The method comprises the steps of: intercepting the short message sent to the user's mobile phone based on the user's registration; identifying the content semantics of the short message and identifying the category of the short message according to the content semantics; immediately sending the short message of the instant sending category to the user's mobile phone according to the preset instant sending category; grouping the short messages of the notification category according to the content semantics, extracting the abstract of all short messages of the notification category within a period according to the preset period, generating a link for viewing all short messages in the group, and sending the abstract and the link to the user's mobile phone; in response to the user's operation, showing or sending the selected short message to the user; The method further comprises the steps of: determining whether the content semantics of the short message of the notification category includes semantics related to public information; when the semantics related to public information is included, searching the public information on the network; generating an abstract of the public information as an extended abstract according to the content semantics of the short message and the public information; embedding the extended abstract in the corresponding position of the short message.

2. The AI-based short message platform intelligent operation method according to claim 1, wherein the method further comprises the steps of: before the short message is sent to the user's mobile phone, determining whether the content semantics of the short message includes semantics for guiding the opening of a specified APP; when the semantics for guiding the opening of a specified APP is included, generating an instruction code for calling the specified APP and attaching relevant calling parameters to the instruction code, and embedding the instruction code in the corresponding position of the short message.

3. The AI-based short message platform intelligent operation method according to claim 1, wherein the method of generating an abstract of the public information as an extended abstract according to the content semantics of the short message and the public information comprises: extracting the value related to the content semantics of the short message and the value pursuit tendency; calculating the matching degree of the searched public information and the value related to the content semantics, and selecting the public information with a matching degree lower than a preset reference value according to the matching degree; grouping the remaining public information according to the value pursuit tendency; extracting the abstract of the public information in each group, and merging the abstracts of the two groups as an extended abstract.

4. The AI-based short message platform intelligent operation method according to any one of claims 1 to 3, wherein the method of identifying the content semantics of the short message and identifying the category of the short message according to the content semantics comprises: reading a preset keyword classification table, which records a plurality of keywords corresponding to the category of each short message; when the short message or the content semantics of the short message includes a matching keyword, setting the category of the short message as the category corresponding to the matching keyword; reading a preset category description, and calculating the matching degree of the content semantics of the remaining short messages and the category description; obtaining the category of the short message according to the matching degree.

5. The AI-based short message platform intelligent operation method according to any one of claims 1 to 3, wherein the method of showing or sending the selected short message to the user in response to the user's operation comprises: calculating the contribution degree of each short message to the abstract; when the user clicks on the link, showing all short messages in the group to the user, and the short messages are arranged in descending order of the contribution degree. ​ ​ ​ ​ A trigger link is added after each SMS, and when the trigger link is clicked, the corresponding SMS is sent to the user's mobile phone.

6. An AI-based short message platform intelligent operation system, characterized in that, The method comprises: intercepting module, intercepting the SMS sent to the user's mobile phone based on the user's registration; recognition module, recognizing the content semantics of the SMS, and identifying the category of the SMS according to the content semantics; sending module, sending the SMS of the instant sending category to the user's mobile phone according to the preset instant sending category; notification module, grouping the SMS of the notification category according to the content semantics, extracting the summary of all the SMS of the notification category within a period according to the preset period, generating a link for viewing all the SMS in the group, and sending the summary and the link to the user's mobile phone; display module, in response to the user's operation, displaying or sending the selected SMS to the user, and judging whether the content semantics of the SMS of the notification category includes semantics related to public information; when the semantics related to public information is included, searching the public information on the network; generating a summary of the public information as an extended summary according to the content semantics of the SMS and the public information; embedding the extended summary in the corresponding position of the SMS.

7. An electronic device, comprising: The method comprises a processor and a memory. The processor is connected to the memory. The memory is used to store executable program codes. The processor reads the executable program codes stored in the memory to run the program corresponding to the executable program codes, so as to execute the method according to any one of claims 1-5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the method according to any one of claims 1-5.

9. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the method according to any one of claims 1-5.

Images