Information sending method and device and intelligent terminal
By automatically analyzing chat messages to identify contact levels and attributes, generating personalized messages and sending them, the problem of users having to edit messages multiple times is solved, improving the efficiency and personalization of message sending.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-10
- Publication Date
- 2026-03-27
AI Technical Summary
Users need to perform multiple editing operations when sending messages to multiple contacts, resulting in a waste of time and effort, and making it impossible to send personalized messages.
By analyzing chat messages, the system automatically identifies the importance level, associated attributes, and preferred titles of contacts, generates matching information, and automatically sends it within a preset level. Users only need to confirm the sending.
It reduces the tedious manual editing process for users, ensures that key contacts are not overlooked, and improves the efficiency and personalization of message delivery.
Smart Images
Figure CN121750604A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of communication technology, specifically providing an information transmission method, apparatus, and smart terminal. Background Technology
[0002] With the continuous development and progress of the information society, the ways people communicate are becoming increasingly rich and diverse, and more convenient and efficient. For example, through modern communication tools such as telephones, text messages, or various social media apps, people can contact other users anytime, anywhere, and achieve instant communication, no matter where they are or how far apart they are.
[0003] However, with the ever-accelerating pace of life and increasing work pressure, the number of contacts in people's contact lists is also constantly growing, requiring users to spend a significant amount of time and energy maintaining interpersonal relationships. A common practice is for users to manually select all or some of their contacts and then send a mass message with the same content to maintain contact. However, this method of sending messages has significant drawbacks. It's possible that sending a large number of identical messages within a specific timeframe, or sending too many messages, could result in important contacts being missed, making it impossible to tailor messages based on different times, people, and relationship types.
[0004] If users want to send personalized and targeted messages to each recipient, they need to perform multiple tedious message editing operations. This not only consumes a lot of time and energy, but is also extremely inconvenient to operate, greatly affecting communication efficiency and user experience.
[0005] Accordingly, a new technical solution is needed in this field to solve the above problems. Summary of the Invention
[0006] The present invention aims to solve the above-mentioned technical problems, namely, that users need to perform multiple message editing operations to send targeted messages to each contact, which takes a lot of time and is extremely inconvenient.
[0007] This invention provides an information sending method, comprising: Obtain chat information between the target user and each of several contacts; Based on the chat information, the importance level, association attributes, and preferred titles of each contact are determined respectively; Based on the importance level, determine whether matching information needs to be generated; If the importance level of the contact is within the preset importance level, then matching information with the preferred name is generated based on the association attribute and the preferred name. Receive confirmation from the target user and send feedback; Send the matching information to the corresponding contact; The importance level includes at least two levels.
[0008] By employing the aforementioned technical solutions, the system automatically analyzes historical chat information to intelligently identify the importance level, association attributes, and preferred titles of contacts, avoiding the tedious manual filtering and editing of information by users. For example, the system can automatically distinguish between different relationships such as colleagues, family, and friends, and generate customized messages with specific preferred titles (such as "General Manager Zhang" or "Aunt Li"), significantly reducing repetitive work for users. Through a preset importance level mechanism, information generation for high-priority contacts is prioritized, ensuring that key interpersonal relationships are not overlooked and solving the problem of important contacts being overlooked in mass messaging scenarios. Users only need to confirm the sending feedback to complete personalized message distribution, eliminating the need for manual editing, which is particularly suitable for scenarios requiring large-scale reach but also differentiation, such as holiday greetings and customer maintenance.
[0009] In a specific implementation of the above-described information sending method, the chat information is at least one chat record between the target user and each of the contacts on the chat interface of an instant messaging application.
[0010] By adopting the above technical solution, existing interactive data can be used directly without additional input, enhancing the practicality of the solution and its alignment with user habits.
[0011] In a specific implementation of the above-described information sending method, the step of determining the importance level, association attribute, and preferred address of each contact based on the chat information includes: The features of the chat information of the aforementioned contacts are obtained to obtain the semantic features of each chat message; Based on the semantic features, the classification probabilities of each importance level, each associated attribute, and each preferred form of address for each contact corresponding to each chat message are determined; Based on the classification probabilities, the importance level, association attributes, and preferred titles of each contact are determined.
[0012] In a specific implementation of the above information sending method, the step of determining the importance level, association attribute, and preferred address of each contact based on the classification probability includes: Based on the classification probability of each chat message in each importance level, each association attribute, and each preferred name, the mean probability of each contact in each importance level, each association attribute, and each preferred name is determined respectively. Based on the mean probability, the importance level, association attribute, and preferred title of each contact are determined.
[0013] By employing the aforementioned technical solutions, the accuracy of relationship identification can be improved by extracting semantic features and performing probabilistic classification. For example, combining features such as dialogue frequency and content intimacy to quantify relationship levels reduces subjective misjudgments.
[0014] In a specific implementation of the above information sending method, the step of generating matching information with the preferred name based on the association attribute and the preferred name includes: Obtain the keywords input by the target user; Based on the keywords currently input by the target user and the associated attributes and preferred names of each contact, matching information corresponding to each contact is generated.
[0015] By adopting the above technical solution, keywords are introduced to make the generated content more relevant to the user's current intent.
[0016] In a specific implementation of the above information sending method, the importance level is five levels. The step of generating matching information with the preferred title based on the association attribute and the preferred title, if the contact's importance level is within a preset importance level, includes: If the importance level of the contact is between level one and level four, then matching information with the preferred title is generated based on the association attribute and the preferred title.
[0017] In a specific implementation of the above information sending method, the step of generating matching information with the preferred title based on the association attribute and the preferred title, if the importance level of the contact is between level one and four, includes: If the importance level is level one, then multiple matching information corresponding to the contact is generated, and the matching information selected by the target user is obtained; If the importance level is level two, then generate a single matching information for the contact. If the importance level is three, then generate a summary of the single matching information for the contact person; If the importance level is four, a list of the contacts is generated, and individual matching information for each contact is generated based on the contact selected by the target user.
[0018] By adopting the above technical solutions, we can refine the hierarchical processing strategy (such as generating multiple options for users to choose from at the first level, and only generating a list at the fourth level) to achieve reasonable resource allocation—providing more refined services for high-level contacts and simplifying the processing of low-priority contacts, thus balancing personalization and efficiency.
[0019] In a specific implementation of the above information sending method, if the importance level is level one, then five matching information corresponding to the contact is generated.
[0020] The present invention also discloses an information transmission device, comprising: The information acquisition module is used to acquire chat information between the target user and each of several contacts. The relationship determination module is used to determine the importance level, association attributes, and preferred titles for each contact based on the chat information. The text generation module is used to generate matching information for each contact based on the keywords currently input by the target user and the importance level, association attributes, and preferred titles of each contact. The information sending module is used to transmit matching information to the window of the corresponding contact in the instant messaging application, and to control the instant messaging application to send the matching information.
[0021] The present invention also discloses a smart terminal, comprising: a processor and a storage medium communicatively connected to the processor, the storage medium being adapted to store multiple instructions; the processor being adapted to call the instructions in the storage medium to execute the steps in the above-described information sending method. Attached Figure Description
[0022] The preferred embodiments of the present invention are described below with reference to the accompanying drawings, in which: Figure 1 This is a flowchart of the main steps of an embodiment of the information sending method of the present invention; Figure 2 This is a flowchart of the expanded steps of step S102 in the information sending method of the present invention; Figure 3 This is a flowchart of the expanded steps of step S202 in the information sending method of the present invention; Figure 4 This is a flowchart of the expanded steps of step S104 in the information sending method of the present invention. Detailed Implementation
[0023] Preferred embodiments of this application are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of this application and are not intended to limit the scope of protection of this application. Those skilled in the art can make adjustments as needed to adapt to specific application scenarios.
[0024] It should be noted that "multiple" in this application means at least two.
[0025] like Figure 1As shown, to address the problem that sending targeted messages to each contact requires multiple message editing operations, which is time-consuming and extremely inconvenient, this invention provides a message sending method, including: S101, Obtain chat information between the target user and each of several contacts. Specifically, the chat information refers to at least one chat record between the target user and each contact on the chat interface of an instant messaging application. Instant messaging applications include WeChat, QQ, SMS, etc. The instant messaging application can be a single specified instant messaging application or multiple specified instant messaging applications. The several contacts can be all contacts of the target user on the instant messaging application, or several contacts specified by the target user on the instant messaging application. When obtaining chat information, all historical chat information between the target user and each of the several contacts can be obtained, or historical chat information between the target user and each of the several contacts within a preset duration or preset time interval can be obtained. For example, when it is necessary to generate target text information for contact A and contact B, the chat information between the target user and contact A, and the chat information between the target user and contact B can be obtained. When obtaining chat information, note information for the contacts is also obtained simultaneously. The note information is part of the chat information.
[0026] S102, based on chat information, determine the importance level, association attributes, and preferred address for each contact. Specifically, the importance level is the degree of importance of each contact relative to the target user, and there are five levels of importance. For example, the importance level of contacts such as leaders, elders, and investors is level one; the importance level of contacts such as family members, close colleagues, friends, and classmates is level two; the importance level of contacts such as colleagues, friends, and classmates with whom you have a casual relationship is level three; the importance level of contacts such as students, employees, and neighbors is level four; and the importance level of other contacts, such as those for repairs or advertising, is level five. The chat information between the target user and the contacts can reflect the importance level between the target user and the contacts. For example, when the contact is the target user's superior or investor, the chat information generally uses more honorifics. When the target user and the contact are colleagues, the chat information generally involves work-related content; when the target user and the contact are friends, the chat information generally involves leisure and entertainment-related content. Therefore, based on the chat information between the target user and each of the several contacts, and combined with the chat frequency, the importance level between the target user and each contact can be determined separately. For example, based on the chat information between the target user and contact X, the importance level of the target user and contact X can be determined. Association attributes represent the relationship between the target user and each contact, reflecting the type of relationship. Association attributes include, but are not limited to, relatives, lovers, business partners, friends, teacher-student, classmates, colleagues, superiors and subordinates, etc. Preference titles are the target user's habitual way of addressing each contact, such as "Old Zhang" or "Teacher Zhang." Association attributes and preference titles can also be obtained from chat information.
[0027] S103, determine whether to generate matching information based on importance level. Specifically, if the importance level is 1 to 4, generate matching information with preferred titles. If the importance level is 5, do not generate matching information with preferred titles. Alternatively, if the importance level is 5, generate matching information with preferred titles only after the target user clicks.
[0028] S104. If the contact's importance level is within the preset importance level, then based on the association attribute and preferred address, generate matching information with the preferred address. Specifically, the preset importance level is from level one to level four. For example, if the association attribute is "teacher" and the preferred address is "Teacher Li," the generated matching information could be "Teacher Li wishes you a happy holiday."
[0029] S105, Obtain confirmation from the target user and send feedback. Specifically, after the matching information is generated, the target user needs to confirm the matching information before subsequent operations can proceed.
[0030] S106, Send matching information to the corresponding contact. Specifically, after the target user confirms the matching information to be sent, it can be sent directly to the corresponding contact, or it can be sent to the corresponding contact through an instant messaging application.
[0031] It should be noted that setting the number of importance levels to five is not mandatory. Those skilled in the art can choose the number of importance levels based on the specific application scenario. The number of importance levels can be two, three, four, or six, etc.
[0032] In this way, by automatically analyzing historical chat information, the system intelligently identifies the importance level, related attributes, and preferred titles of contacts, avoiding the tedious manual filtering and editing of information by users. For example, the system can automatically distinguish between different relationships such as colleagues, family, and friends, and generate customized messages with specific preferred titles (such as "General Manager Zhang" or "Aunt Li"), significantly reducing repetitive work for users. By pre-setting an importance level mechanism, the system prioritizes the generation of messages for high-priority contacts, ensuring that key interpersonal relationships are not overlooked and solving the problem of important contacts being buried in mass messaging scenarios. Users only need to confirm the sending feedback to complete the personalized message distribution, without having to manually edit each message, which is especially suitable for scenarios that require large-scale reach but also differentiation, such as holiday greetings and customer maintenance.
[0033] It should be noted that all user-related data collected in this application was collected with the user's consent and authorization, and the collection, use, and processing of such user data must comply with the relevant laws, regulations, and standards of the relevant countries and regions.
[0034] like Figure 2 As shown, in one or more embodiments, step S102, which determines the importance level, association attribute, and preferred address for each contact based on chat information, includes: S201, Obtain the semantic features of chat information from several contacts.
[0035] S202, based on semantic features, determines the classification probability of each chat message in each importance level, associated attribute, and preferred address.
[0036] S203, based on classification probability, determine the importance level, association attributes and preferred titles for each contact.
[0037] Specifically, a large language model is used to analyze chat messages from several contacts and output semantic features. Based on the semantic features, the classification probability of each chat message in each importance level, each association attribute, and each preferred form of address is output. Finally, based on the classification probability of each chat message in each importance level, each association attribute, and each preferred form of address, the importance level, each association attribute, and each preferred form of address between the target user and each contact are determined.
[0038] like Figure 3 As shown, in one or more embodiments, step S202, which determines the importance level, association attribute, and preferred address for each contact based on classification probability, includes: S301, based on the classification probability of each chat message in each importance level, each association attribute and each preferred name, determine the mean probability of each contact in each importance level, each association attribute and each preferred name respectively. S302, based on the mean probability, determine the importance level, association attributes, and preferred form of address for each contact. In this way, by extracting sentence semantic features and entity semantic features and performing probability classification, the accuracy of relationship identification is improved. For example, combining features such as dialogue frequency and content intimacy to quantify relationship levels reduces subjective misjudgments.
[0039] Specifically, taking the determination of importance levels as an example, the classification probability is the probability of each chat message in each importance level among several chat messages corresponding to each contact. For example, the chat messages corresponding to contact X include chat messages X1, X2, and X3, and the chat messages corresponding to contact Y include chat messages Y1, Y2, and Y3. The large language model can output the classification probabilities of chat messages X1, X2, and X3 in each importance level, as well as the classification probabilities of chat messages Y1, Y2, and Y3 in each importance level. In this embodiment, after outputting the classification probabilities of each chat message in each importance level through the large language model, the classification probabilities of each chat message in each importance level among several chat messages corresponding to each contact are weighted and averaged to obtain the mean probability of the target user and each contact in each importance level. For example, the classification probabilities of chat message X1 in importance levels A, B, and C are respectively P 1A P 1B and P 1C The probability of classifying chat message X2 into importance levels A (Level 1), B (Level 2), and C (Level 3) are respectively P1, P2, P3, P4, P5, P6, P7, P8, P9, P10, P<sub 2A P 2B and P 2C Then the mean probabilities of the target user and contact X in relation to attribute A, attribute B, and attribute C are respectively (P... 1A +P 2A ) / 2、(P 1B +P 2B ) / 2 and (P 1C +P 2C ) / 2.
[0040] After obtaining the mean probabilities of the target user and each contact at each importance level, the mean probabilities of the target user and each contact at each importance level are compared. Based on the comparison results, the importance level corresponding to the highest mean probability is determined from each importance level, and this importance level is determined as the importance level between the target user and that contact. For example, if the mean probabilities of the target user and contact X being level A (Level 1), B (Level 2), and C (Level 3) are 50%, 30%, and 20%, respectively, then the importance level between the target user and contact X is determined to be level A.
[0041] It should be noted that language models include, but are not limited to, ChatGPT, GPT-4, Claude, Tongyi Qianwen, Doubao, and Yuanbao, and this application does not limit them.
[0042] like Figure 4 As shown, in one or more embodiments, step S104, which generates matching information with preferred titles based on association attributes and preferred titles, includes: S401, Obtain the keywords entered by the target user; S402, based on the keywords currently input by the target user and the associated attributes and preferred titles for each contact, generate matching information for each contact. For example, if the keywords are "Chinese New Year greetings" and "highlighting a festive atmosphere," the large language model generates matching information for each contact based on the keywords currently input by the target user and the associated attributes and preferred titles for each contact. In this way, by introducing keywords, the generated content is made more closely aligned with the user's current intent.
[0043] In one or more implementations, if the contact's importance level is between level one and four, the step of generating matching information with preferred titles based on association attributes and preferred titles includes: If the importance level is level one, then generate multiple matching information for the contact and obtain the matching information selected by the target user; If the importance level is level two, then generate a single matching information for the contact. If the importance level is three, then generate a brief summary of the individual matching information for the contact. If the importance level is four, a list of contacts is generated, and individual matching information for each contact is generated based on the contact selected by the target user. This refined level-based processing strategy (e.g., generating multiple options for the user to choose from at level one, and only generating a list at level four) achieves reasonable resource allocation—providing more refined services to high-importance contacts and simplifying processing for low-importance contacts, thus balancing personalization and efficiency.
[0044] Specifically, for example, if contact X's importance level is Level 1, multiple matching entries for contact X are generated and displayed to the target user, who then selects the desired matching entry. If contact Y's importance level is Level 2, a single matching entry for contact Y is generated and displayed to the target user. Multiple Level 2 matching entries can be displayed on the same page, allowing the target user to modify the matching information. The user can either confirm a single contact's matching entry or confirm matching entries for all contacts on the displayed page. If none of the matching entries meet the target user's needs, the user can delete either the single contact's matching entry or all matching entries on the displayed page. If a contact's importance level is Level 3, a simplified version of the single matching entry for that contact is generated, and multiple simplified entries are displayed on the page. The target user can then review these simplified entries. If modifications are needed, the user can click on the simplified entry to view the detailed matching entry and make the changes. After review, if the simplified entry is satisfactory, the user can confirm either the single contact's simplified entry or confirm all simplified entries on the displayed page. After confirming the brief information, the corresponding matching information is sent to the contact. If none of the matching information meets the target user's needs, the target user can delete the brief information for a single contact or delete the brief information for all contacts on the display page. It should be noted that the brief information is used to increase the number of contacts and their corresponding matching information displayed on the page; the information sent to the contact is the matching information corresponding to the brief information. Deleting the brief information also deletes the corresponding matching information.
[0045] Those skilled in the art will understand that all or part of the processes in the method of the above embodiment of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium can include any entity or device capable of carrying computer program code, media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.
[0046] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the server or client according to embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a PC program and PC program products) for performing some or all of the methods described herein. Such programs implementing the present invention can be stored on a PC-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.
[0047] Based on the same inventive concept, this invention also discloses an information sending device, comprising: an information acquisition module for acquiring chat information between a target user and each of several contacts; a relationship determination module for determining the importance level, association attributes, and preferred titles of each contact based on the chat information; a text generation module for generating matching information corresponding to each contact based on the keywords currently input by the target user and the importance level, association attributes, and preferred titles of each contact; and an information sending module for transmitting the matching information to the window of the corresponding contact in an instant messaging application and controlling the instant messaging application to send the matching information.
[0048] Based on the same inventive concept, this invention also discloses a smart terminal, comprising: a processor and a storage medium communicatively connected to the processor, the storage medium being adapted to store multiple instructions; the processor being adapted to invoke the instructions in the storage medium to execute the steps in the aforementioned information transmission method. The processor of this smart terminal provides computing and control capabilities. The memory of this smart terminal includes a non-volatile storage medium and 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 computer program in the non-volatile storage medium. The smart terminal also includes a network interface for communicating with external terminals via a network connection. The computer program, executed by the processor, can implement an information transmission method. The smart terminal also includes a display screen, which can be a liquid crystal display screen or an electronic ink display screen.
[0049] Those skilled in the art will understand that although some embodiments herein include certain features included in other embodiments but not others, combinations of features from different embodiments are intended to be within the scope of this application and form different embodiments. For example, any of the claimed embodiments in the claims of this application can be used in any combination.
[0050] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will all fall within the scope of protection of the present invention.
Claims
1. A method for sending information, characterized in that, include: Obtain chat information between the target user and each of several contacts; Based on the chat information, the importance level, association attributes, and preferred titles of each contact are determined respectively; Based on the importance level, determine whether matching information needs to be generated; If the importance level of the contact is within the preset importance level, then matching information with the preferred name is generated based on the association attribute and the preferred name. Receive confirmation from the target user and send feedback; Send the matching information to the corresponding contact; The importance level includes at least two levels.
2. The information transmission method according to claim 1, characterized in that, The chat information refers to at least one chat record between the target user and each of the aforementioned contacts on the chat interface of the instant messaging application.
3. The information transmission method according to claim 1, characterized in that, The step of determining the importance level, association attribute, and preferred address for each contact based on the chat information includes: The features of the chat information of the aforementioned contacts are obtained to obtain the semantic features of each chat message; Based on the semantic features, the classification probabilities of each importance level, each associated attribute, and each preferred form of address for each contact corresponding to each chat message are determined; Based on the classification probabilities, the importance level, association attributes, and preferred titles of each contact are determined.
4. The information transmission method according to claim 3, characterized in that, The step of determining the importance level, association attribute, and preferred address for each contact based on the classification probability includes: Based on the classification probability of each chat message in each importance level, each association attribute, and each preferred name, the mean probability of each contact in each importance level, each association attribute, and each preferred name is determined respectively. Based on the mean probability, the importance level, association attribute, and preferred title of each contact are determined.
5. The information transmission method according to claim 1, characterized in that, The step of generating matching information with the preferred name based on the associated attribute and the preferred name includes: Obtain the keywords input by the target user; Based on the keywords currently input by the target user and the associated attributes and preferred names of each contact, matching information corresponding to each contact is generated.
6. The information transmission method according to claim 5, characterized in that, The importance level is five levels. The step of generating matching information with the preferred title based on the association attribute and the preferred title, if the contact's importance level is within a preset importance level, includes: If the importance level of the contact is between level one and level four, then matching information with the preferred title is generated based on the association attribute and the preferred title.
7. The information transmission method according to claim 6, characterized in that, If the importance level of the contact is between level one and four, the step of generating matching information with the preferred title based on the association attribute and the preferred title includes: If the importance level is level one, then multiple matching information corresponding to the contact is generated, and the matching information selected by the target user is obtained; If the importance level is level two, then generate a single matching information for the contact. If the importance level is three, then generate a summary of the single matching information for the contact person; If the importance level is four, a list of the contacts is generated, and individual matching information for each contact is generated based on the contact selected by the target user.
8. The information transmission method according to claim 7, characterized in that, If the importance level is Level 1, then five matching information entries are generated for the contact.
9. An information transmitting device, characterized in that, include: The information acquisition module is used to acquire chat information between the target user and each of several contacts. The relationship determination module is used to determine the importance level, association attributes, and preferred titles for each contact based on the chat information. The text generation module is used to generate matching information for each contact based on the keywords currently input by the target user and the importance level, association attributes, and preferred titles of each contact. The information sending module is used to transmit matching information to the window of the corresponding contact in the instant messaging application, and to control the instant messaging application to send the matching information.
10. A smart terminal, characterized in that, include: A processor and a storage medium communicatively connected to the processor, the storage medium being adapted to store multiple instructions; the processor being adapted to invoke the instructions in the storage medium to execute the steps of the information transmission method according to any one of claims 1-8.