Message template generation method, device, electronic device and storage medium

Abstract

The present application proposes a method, device, electronic device and storage medium for generating a message template, wherein the method comprises: obtaining a user's uplink message and identifying a user topic semantic tag of the user's uplink message. Obtaining a target message material that matches the user topic semantic tag from a message template material knowledge base; generating a message template based on the message format definition of the message template and the target message material. Generate a message template based on the message behavior on the user side combined with the message material, thereby obtaining a message template with a better user experience. Update the recommendation index based on the message response behavior on the user side to achieve the recommendation accuracy of the message template.

Description

Technical Field

[0001] The present application relates to the field of message communication technology, and in particular to a method, device, electronic device and storage medium for generating a message template. Background Art

[0002] In the prior art, rich media message services such as 5G messages will provide rich media message template library services for access applications. General message template implementation methods include the following modes: 1. The application platform provides graphical or low-code message editing functions, and merchants create message templates for use in related message sending scenarios; 2. After the application platform completes the design of the message template, it forms the corresponding message template in advance according to the established message format definition and puts it on the platform side for merchants to choose to use; 3. Merchants can edit or import message templates in the function interface provided by the application platform according to their own needs. 4. The application platform implements import tools based on the open interfaces of other application platforms to import relevant message template information from other application platforms.

[0003] The existing technology of artificial driving is affected by artificial cognition and has certain limitations. There is a lack of a user dimension (C-end) association mechanism between message template-related content materials and the current platform. Summary of the invention

[0004] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0005] To this end, the first purpose of this application is to propose a method for generating message templates to improve the quality of message templates and solve the problem of lack of correlation between the generation of message templates and user-side dimensions in related technologies, thereby improving user experience.

[0006] The second objective of the present application is to provide a device for generating a message template.

[0007] The third objective of the present application is to provide an electronic device.

[0008] A fourth objective of the present application is to provide a computer-readable storage medium.

[0009] A fifth object of the present application is to provide a computer program product.

[0010] To achieve the above-mentioned purpose, the first embodiment of the present application proposes a method for generating a message template, comprising:

[0011] Acquire a first user uplink message, and identify a user topic semantic tag of the first user uplink message;

[0012] Acquire target message material matching the user topic semantic tag from a message template material knowledge base; wherein the message template material knowledge base stores message materials used to generate message templates;

[0013] Based on the message format definition of the message template and the target message material, a first message template is generated.

[0014] In some implementations, the method further includes:

[0015] In response to the user's editing operation on the first message template, a target message template for sending a message is generated.

[0016] In some implementations, the step of identifying a user topic semantic tag of the first user's uplink message includes:

[0017] Using a preprocessing technology corresponding to the message type of the first user uplink message, obtaining text form information of the first user uplink message;

[0018] The semantic information of the text form information is identified to obtain a user topic semantic tag of the first user's uplink message.

[0019] In some implementations, acquiring the target message material matching the user topic semantic tag from a message template material knowledge base includes:

[0020] Based on the multiple attributes of the message material, the target message material matching the user topic semantic tag is obtained from the message template material knowledge base; wherein the multiple attributes of the message material include material tags and material attributes, the material tags are used to indicate the application scenarios of the message materials, and the material attributes are used to indicate the parameter positions when the message materials are assembled into messages.

[0021] In some implementations, after generating the first message template, the step further includes:

[0022] The first message template is stored in a message template library, and template attribute information of the first message template is presented in the message template library; wherein the template attribute information includes attribute information of the reaction user feedback information obtained based on the first user uplink message.

[0023] In some implementations, storing the first message template in a message template library includes:

[0024] When a message template identical to the first message template is already stored in the message template library, and a user uplink message associated with the identical message template and the first user uplink message are from different users, the user attention attribute value of the identical message template is updated.

[0025] In some implementations, the method further includes:

[0026] Obtaining a second user uplink message of a message feedback sent by the user based on the first message template;

[0027] Using a preprocessing technology corresponding to the message type of the second user uplink message, obtaining text form information of the second user uplink message;

[0028] Identify semantic information of the text form information to obtain a user topic semantic tag of the second user's uplink message;

[0029] Based on the user topic semantic tag of the second user's uplink message, the attributes of the first message template are updated; wherein the attributes include the number of times the message template triggers the user's uplink positive behavior and the number of times the message template triggers the user's uplink negative behavior.

[0030] In some implementations, the method further includes:

[0031] Based on the attributes of the first message template, a recommended indicator value of the first message template is updated.

[0032] In some implementations, the generating a first message template based on the message format definition of the message template and the target message material includes:

[0033] Generate prompt words based on the message format definition of the message template and the target message material; and generate a first message template based on the prompt words and the trained large language model; or,

[0034] The vectorized target message material is input into the fine-tuned large speech model to generate a first message template that conforms to the message format definition of the message template.

[0035] To achieve the above-mentioned purpose, the second aspect of the present application proposes a message template generation device, including:

[0036] A message analysis module, configured to obtain an uplink message of a first user and identify a user topic semantic tag of the uplink message of the first user;

[0037] A material acquisition module, used to acquire target message materials matching the user topic semantic tag from a message template material knowledge base; wherein the message template material knowledge base stores message materials used to generate message templates;

[0038] The template generation module is used to generate a first message template based on the message format definition of the message template and the target message material.

[0039] In some implementations, the template generation module is further used to:

[0040] In response to the user's editing operation on the first message template, a target message template for sending a message is generated.

[0041] In some implementations, the message analysis module is specifically used to:

[0042] Using a preprocessing technology corresponding to the message type of the first user uplink message, obtaining text form information of the first user uplink message;

[0043] The semantic information of the text form information is identified to obtain a user topic semantic tag of the first user's uplink message.

[0044] In some implementations, the material acquisition module is specifically used to:

[0045] Based on the multiple attributes of the message material, the target message material matching the user topic semantic tag is obtained from the message template material knowledge base; wherein the multiple attributes of the message material include material tags and material attributes, the material tags are used to indicate the application scenarios of the message materials, and the material attributes are used to indicate the parameter positions when the message materials are assembled into messages.

[0046] In some implementations, when storing the first message template in a message template library, the template generation module is further configured to:

[0047] When a message template identical to the first message template is already stored in the message template library, and a user uplink message associated with the identical message template and the first user uplink message are from different users, the user attention attribute value of the identical message template is updated.

[0048] In some implementations, the template generation module is further used to:

[0049] Obtaining a second user uplink message of a message feedback sent by the user based on the first message template;

[0050] Using a preprocessing technology corresponding to the message type of the second user uplink message, obtaining text form information of the second user uplink message;

[0051] Identify semantic information of the text form information to obtain a user topic semantic tag of the second user's uplink message;

[0052] Based on the user topic semantic tag of the second user's uplink message, the attributes of the first message template are updated; wherein the attributes include the number of times the message template triggers the user's uplink positive behavior and the number of times the message template triggers the user's uplink negative behavior.

[0053] In some implementations, the template generation module is further used to:

[0054] Based on the attributes of the first message template, a recommended indicator value of the first message template is updated.

[0055] In some implementations, the template generation module, when generating the first message template based on the message format definition of the message template and the target message material, is specifically configured to:

[0056] Generate prompt words based on the message format definition of the message template and the target message material; and generate a first message template based on the prompt words and the trained large language model; or,

[0057] The vectorized target message material is input into the fine-tuned large speech model to generate a first message template that conforms to the message format definition of the message template.

[0058] To achieve the above-mentioned purpose, the third aspect embodiment of the present application proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method described in the first aspect.

[0059] To achieve the above-mentioned purpose, the fourth aspect of the present application proposes a computer-readable storage medium, in which computer-readable storage medium is stored computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in the first aspect.

[0060] To achieve the above-mentioned purpose, the fifth aspect of the present application proposes a computer program product, including a computer program, which implements the method described in the first aspect when executed by a processor.

[0061] The message template generation method, device, electronic device and storage medium provided in the present application obtain user topic semantic tags by identifying the semantics of the uplink message on the user side, match the target message material in an increased message template material knowledge base based on the user topic semantic tags, and assemble them into new message templates, thereby obtaining message templates with better user-side experience.

[0062] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0064] Figure 1 A flowchart of a method for generating a message template provided in Embodiment 1 of the present application;

[0065] Figure 2 A flowchart of a method for generating a message template provided in Embodiment 2 of the present application;

[0066] Figure 3 A block diagram of a message template generation device provided in Embodiment 3 of the present application; DETAILED DESCRIPTION

[0067] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0068] Terminology explanation:

[0069] Platform: refers to the system architecture.

[0070] Existing 5G messages and even OTT (Over The Top, which refers to providing various application services to users through the Internet, and this service is provided by a third party other than the operator) such as the A2P rich media message service of WeChat Internet products will provide rich media message template library services for access applications. Through the message module library, the threshold for designing and producing A2P message content on the application side can be lowered, and the efficiency of message sending can be improved.

[0071] The general message template implementation methods include the following modes: 1. The application platform provides a graphical or low-code message editing function, and merchants create message templates for use in related message sending scenarios. 2. After completing the design of the message template, the application platform itself forms the corresponding message template in advance according to the established message format definition and puts it on the platform side for merchants to choose to use. 3. Merchants can edit or import message templates in the function interface provided by the application platform according to their own needs. The application platform forms the message template results according to the established message format definition and puts them on the platform side for merchants to choose to use. 4. The application platform implements the import tool based on the open interface of other application platforms to import relevant message template information from other application platforms. According to the established message format definition, convert and form the platform's own message template for commercial use.

[0072] The current implementation mechanism of message templates can meet the basic needs of merchants. In addition to the above template generation methods, the application platform also provides business type tags and user group tag settings based on manual and big data technology, and provides merchants with relevant usage scenario recommendations and association functions. Combined with data analysis capabilities, the frequency of use of different merchant types is counted. Based on statistical information, a recommendation mechanism is added to relevant message templates to facilitate merchant selection.

[0073] Under the existing technology, the realization of message templates is essentially still edited directly or indirectly by merchants or application message platform operators. The generation of existing message templates is based on the materials and related logic at the application platform level and is realized through manual driving. There are the following limitations: 1. The message templates generated by the back-end operators of the application platform are all based on the one-way understanding of the relevant message application scenarios from the perspective of the application platform service side. 2. Although message templates can be imported through third-party application platforms, the message ecological model corresponding to each application platform may be different, and it is essentially just an enhancement of the ability to generate message templates from the perspective of the application platform service side. 3. The application platform optimizes the recommendation of message templates based on manual tags or big data intelligent tags, which improves the efficiency of merchants using message templates, but the content of message templates has not been optimized. In summary, under the analysis of the existing message template generation technology, there is a lack of C-end user dimension association mechanism for docking the content materials related to the message template with the current platform.

[0074] In response to the above problems, the embodiments of the present application provide a method and device for generating a message template. Based on the existing technologies for implementing message templates, a series of mechanisms associated with the C-end user dimension are further implemented to improve the message usage experience of C-end users, as well as the accuracy and value of the overall application message service.

[0075] The following describes the message template generation method, device and equipment of the embodiments of the present application with reference to the accompanying drawings.

[0076] Figure 1 A flowchart of a method for generating a message template provided in an embodiment of the present application.

[0077] It should be noted that the execution subject of the message template generation method of the embodiment of the present application is the message template generation device of the embodiment of the present application, and the message template generation device can be configured in an electronic device so that the electronic device can execute the message template generation function.

[0078] like Figure 1 As shown, the method for generating the message template includes the following steps:

[0079] Step 101: obtain an uplink message of a first user, and identify a user topic semantic tag of the uplink message of the first user.

[0080] The execution entity of the embodiment of the present application may be a message template automatic generation platform.

[0081] First of all, it should be noted that user uplink messages refer to message information sent by users to applications, including messages actively sent to applications and feedback messages sent to applications. These two types of messages represent the willingness to request application-side services and cognitive feedback on received application messages, respectively. In order to implement a message template generation mechanism associated with the C-end user dimension, this embodiment uses user uplink messages as an important reference factor for message template generation to improve the quality of message template generation.

[0082] As an implementation method, a method for identifying a user topic semantic label of an uplink message of a first user; comprising: adopting a preprocessing technology corresponding to the message type of the uplink message of the first user to obtain text form information of the uplink message of the first user; identifying the semantic information of the text form information to obtain a user topic semantic label of the uplink message of the first user.

[0083] Exemplarily, the message template automatic generation platform obtains the user's uplink message from the application message platform by connecting to the main message flow of the application message platform. According to the message type of the user's uplink message, the user's uplink message preprocessing logic is executed to finally form the text form information of the user's uplink message. The preprocessing logic includes but is not limited to AI (Artificial Intelligence) technology to complete speech-to-text, image recognition, video recognition and other processing. For example, if the message type is video, video recognition is performed to obtain the voice information in the video, and then speech-to-text is converted to obtain text form information. Based on AI semantic analysis technology, user topic semantic tags are derived based on text form information. That is, based on big data, AI and other technologies, user topic semantic tags that users care about can be derived.

[0084] Step 102, obtaining target message material matching the user topic semantic tag from a message template material knowledge base; wherein the message template material knowledge base stores message materials used to generate message templates.

[0085] As an implementation method, based on multiple attributes of the message material, the target message material that matches the user topic semantic tag is obtained from the message template material knowledge base; wherein the multiple attributes of the message material include material tags and material attributes, the material tag is used to indicate the application scenario of the message material, and the material attribute is used to indicate the parameter position when the message material is assembled into a message.

[0086] It can be understood that based on the user topic semantic tags of the user's uplink message, the message template material knowledge base is queried to match the optimal message material information, thereby determining the matching target message material.

[0087] It should be noted that before executing this step, it is necessary to establish a message template material knowledge base for the application message platform to assemble rich media message templates suitable for the current application message platform requirements. Based on big data technology, a message template material knowledge base can be established as a material basis for automatically generating message templates. The big data technology used here includes but is not limited to data warehouse services based on frameworks such as ClickHouse and StarRocks. In addition to storing the original content of the message material, the message template material knowledge base also includes the relevant attribute values ​​of each message material.

[0088] Exemplarily, the message materials in the message template material knowledge base provide materials for the application message platform to assemble into rich media message templates suitable for the current application message platform requirements. The relevant attribute items of each message material include but are not limited to the contents of Table 1 (which can be updated and expanded according to actual needs).

[0089] Table 1:

[0090]

[0091]

[0092] In addition to manual settings, the source of message materials in the message template material knowledge base can also provide multiple methods such as API interface and file import, and provide automatic import function for merchant developers or big data system calls associated with the application message platform itself. This embodiment combines AI, big data and other technologies to automatically generate relevant message materials.

[0093] As an implementation method, the message template knowledge material library may include multiple types of databases to store different types of message materials. For example, it may include relational databases, non-relational databases, and vector databases used by AI large models. When constructing a vector database, the message materials obtained by various methods may be converted into material vectors and stored in the vector database.

[0094] For the vector database, when obtaining the target message material that matches the user topic semantic tag, the user topic semantic tag can be vectorized through the vector model to obtain the user topic semantic tag vector. Based on the user topic semantic tag vector, the vector database is queried to obtain the corresponding target message material vector.

[0095] Step 103: Generate a first message template based on the message format definition of the message template and the target message material.

[0096] As an implementation method, for the method of generating message templates, a plurality of generation methods can be introduced in a componentized manner, and during the generation process, component selection is performed according to conditions, and one component is selected to generate the message template.

[0097] As a possible implementation method, according to the message format definition of the application message platform, based on the message material matched from the message template material knowledge base, the corresponding message template is automatically converted in a programmatic manner.

[0098] As another possible implementation, based on the message format definition of the message template and the target message material, a prompt word is generated; based on the prompt word and a trained large language model, a message template is generated.

[0099] As another possible implementation, the target message material is input into a fine-tuned large speech model to generate a message template that conforms to a message format definition of the message template.

[0100] For example, when generating a 5G message template, the vectorized message template knowledge base can be combined with the prompt word engineering processing, and the relevant prompt words can be generated based on the message format definition corresponding to the 5G message standard, and then the LLM language model can be called to obtain the relevant target 5G message template. Alternatively, fine-tuning can be performed directly based on the LLM large speech model, and the purpose of automatically generating the message template required under the message format definition corresponding to the 5G message standard based on the LLM can also be achieved.

[0101] In this embodiment, after the message template is generated, the generated new message template is written into the message template library.

[0102] In some embodiments, after generating the first message template, the method further includes: storing the first message template in a message template library, and presenting template attribute information of the first message template in the message template library. The template attribute information may include but is not limited to attribute information of the response user feedback information obtained based on the first user uplink message.

[0103] Furthermore, when a message template identical to the first message template is stored in the message template library, and the user uplink message associated with the same message template and the first user uplink message are from different users, the user attention attribute value of the same message template is updated.

[0104] For example, if the generated message template already exists and is generated based on uplink messages of different users, the user attention attribute value in the corresponding attribute of the message template in the message template library is increased by 1. At the same time, the latest user topic association time attribute value of the message template is set or updated.

[0105] In this embodiment, the template attribute information of the message template is displayed to the merchants in the message template library for the merchants to select and use for sending messages.

[0106] It should be noted that, compared with the prior art, the solution of the present application expands the attribute items of the message template in the message template library.

[0107] Exemplarily, the attribute items of the extended message template are shown in Table 2.

[0108] Table 2:

[0109]

[0110]

[0111] Therefore, by expanding the attribute items of the message template in the message template library, an association method for attributes related to the user's uplink message behavior (i.e., attributes reflecting user feedback information) is added for presentation to merchants as a reference for selecting and editing message templates.

[0112] After the message template is generated and written into the message template library, the merchant can select the message template to implement the message below based on the message template.

[0113] In some embodiments, in response to a user's editing operation on a first message template, a target message template for sending a message is generated.

[0114] In other words, based on the general message template editing function, merchants can perform secondary editing and optimization based on the automatically generated message template to form a target message template for the final message delivery.

[0115] The message template generation method of this embodiment identifies the semantics of the uplink message on the user side to obtain the user topic semantic tag, matches the target message material in the added message template material knowledge base based on the user topic semantic tag, and assembles it into a new message template, thereby obtaining a message template with better user-side experience and facilitating the accurate push of messages.

[0116] On the basis of the above-mentioned embodiment, the message response behavior of C-end users can more effectively and indirectly reflect the validity of the associated message template, help merchants to reuse it, and realize the accurate push of subsequent message push. Figure 2 A flow chart of another method for generating a message template provided in an embodiment of the present application. Figure 2 As shown, the method for generating the message template may include the following steps:

[0117] Step 201: obtaining a second user uplink message of a user sending a message feedback based on a first message template.

[0118] Step 202: Using a preprocessing technology corresponding to the message type of the second user's uplink message, obtain text form information of the second user's uplink message.

[0119] Step 203: Identify the semantic information of the text form information to obtain a user topic semantic tag of the second user's uplink message.

[0120] It should be noted that the implementation of steps 201-203 of this embodiment may specifically refer to step 101 in the above embodiment, and the principles are the same, which will not be repeated here.

[0121] Step 204: Update the attributes of the first message template based on the user topic semantic tag of the second user's uplink message.

[0122] The attributes that need to be updated may include, but are not limited to, the number of times the message template triggers a user's positive uplink behavior and the number of times the message template triggers a user's negative uplink behavior.

[0123] Therefore, the user feedback is judged as positive or negative based on the user topic semantic tag of the user's uplink message, and the attribute value of the corresponding message template in the message template library is updated based on the relevant judgment result. That is, if it is judged that the message template triggers the user's uplink positive behavior, the number of times the message template triggers the user's uplink positive behavior +1, and if it is judged that the message template triggers the user's uplink negative behavior, the number of times the message template triggers the user's uplink negative behavior +1.

[0124] Step 205: Update the recommended index value of the first message template based on the attribute of the first message template.

[0125] Based on the attribute values ​​of the message template, the recommendation index values ​​of the message template are updated, and the recommendation index values ​​can be presented to merchants to improve the accuracy of the recommendation, thereby improving the merchant's usage experience.

[0126] For example, if the message template triggers the user's uplink positive behavior times +1, then the recommended index value is +1; if the message template triggers the user's uplink negative behavior times +1, then the recommended index value is -1.

[0127] The relevant user feedback information in the template information of the message template is displayed to merchants in the message template library for merchants to refer to and optimize the message template. Therefore, the message response behavior of C-end users can more effectively and indirectly reflect the effectiveness of the associated message template, increase the recommendation index of user-side feedback, and achieve the accuracy of recommendation of subsequent message templates.

[0128] The message template generation method of this embodiment updates the attributes of the message template that reflect the user feedback information based on the message response behavior on the user side, thereby updating the recommendation index to achieve the recommendation accuracy of the message template and improve the merchant usage experience.

[0129] In order to clearly illustrate the above embodiment, specific examples are now provided for illustration.

[0130] In order to implement the above embodiment, the present application also proposes a device for generating a message template. Figure 3 A schematic diagram of a message template generation device provided in an embodiment of the present application. Figure 3 As shown, the message template generation device may include: a message analysis module 301, a material acquisition module 302 and a template generation module 303.

[0131] The message analysis module 301 is used to obtain an uplink message of the first user and identify a user topic semantic tag of the uplink message of the first user;

[0132] The material acquisition module 302 is used to acquire target message materials that match the user topic semantic tag from the message template material knowledge base; wherein the message template material knowledge base stores message materials used to generate message templates;

[0133] The template generation module 303 is used to generate a first message template based on the message format definition of the message template and the target message material.

[0134] Furthermore, in a possible implementation of the embodiment of the present application, the template generation module 303 is further configured to:

[0135] In response to the user's editing operation on the first message template, a target message template for sending a message is generated.

[0136] Further, in a possible implementation of the embodiment of the present application, the message analysis module 301 is specifically used to:

[0137] Using a preprocessing technology corresponding to the message type of the first user uplink message, obtaining text form information of the first user uplink message;

[0138] The semantic information of the text form information is identified to obtain a user topic semantic label of the first user's uplink message.

[0139] Furthermore, in a possible implementation of the embodiment of the present application, the material acquisition module 302 is specifically configured to:

[0140] Based on multiple attributes of the message material, the target message material matching the user topic semantic tag is obtained from the message template material knowledge base; wherein the multiple attributes of the message material include material tags and material attributes, the material tags are used to indicate the application scenarios of the message materials, and the material attributes are used to indicate the parameter positions when the message materials are assembled into messages.

[0141] Furthermore, in a possible implementation of the embodiment of the present application, when the template generation module 303 stores the first message template in the message template library, it is further configured to:

[0142] When a message template identical to the first message template is stored in the message template library and a user uplink message associated with the same message template is different from the first user uplink message, the user attention value attribute of the same message template is updated.

[0143] Furthermore, in a possible implementation of the embodiment of the present application, the template generation module 303 is further configured to:

[0144] Obtaining a second user uplink message of a message feedback sent by the user based on the first message template;

[0145] Using a preprocessing technology corresponding to the message type of the second user uplink message, obtaining text form information of the second user uplink message;

[0146] Identify semantic information of the text form information to obtain a user topic semantic label of the second user's uplink message;

[0147] Based on the user topic semantic tag of the second user's uplink message, the message response attributes of the first message template are updated; wherein the message response attributes include the number of times the message template triggers the user's uplink positive behavior and the number of times the message template triggers the user's uplink negative behavior.

[0148] Furthermore, in a possible implementation of the embodiment of the present application, the template generation module 303 is further configured to:

[0149] Based on the attributes of the message template, the recommended indicator value of the message template is updated.

[0150] Further, in a possible implementation manner of the embodiment of the present application, when the template generation module generates the first message template based on the message format definition of the message template and the target message material; it is specifically used to:

[0151] Generate prompt words based on the message format definition of the message template and the target message material; and generate a first message template based on the prompt words and the trained large language model; or,

[0152] The vectorized target message material is input into the fine-tuned large speech model to generate a first message template that conforms to the message format definition of the message template.

[0153] It should be noted that the above explanation of the embodiment of the method for generating a message template is also applicable to the device for generating a message template of this embodiment, and will not be repeated here.

[0154] The message template generation device of the embodiment of the present application identifies the semantics of the uplink message on the user side to obtain the user topic semantic tag, matches the target message material in the added message template material knowledge base based on the user topic semantic tag, and assembles it into a new message template, thereby obtaining a message template with better user experience. Based on the message response behavior on the user side, the attributes of the message template that reflect the user feedback information are updated, thereby updating the recommendation index to achieve the recommendation accuracy of the message template and improve the merchant usage experience.

[0155] In order to implement the above embodiments, the present application also proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method provided by the above embodiments.

[0156] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0157] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0158] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0159] It should be noted that personal information from users should be collected for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. In addition, such collection / sharing should be carried out after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign the agreement / authorization including authorization of relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others who have access to personal information data comply with its privacy policy and procedures.

[0160] The present application is expected to provide an implementation scheme for users to selectively block the use or access of personal information data. That is, the present disclosure is expected to provide hardware and / or software to prevent or block access to such personal information data. Once the personal information data is no longer needed, the risk can be minimized by limiting data collection and deleting the data. In addition, when applicable, such personal information is de-identified to protect the privacy of the user.

[0161] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0162] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0163] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0164] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0165] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0166] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0167] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0168] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for generating a message template, characterized in that: The following steps are involved: Acquire a first user uplink message, and identify a user topic semantic tag of the first user uplink message, wherein the user uplink message refers to message information sent by a user to an application; Acquire target message material matching the user topic semantic tag from a message template material knowledge base; wherein the message template material knowledge base stores message materials used to generate message templates; Generate a first message template based on the message format definition of the message template and the target message material; The method further comprises: Obtaining a second user uplink message of a message feedback sent by the user based on the first message template; Using a preprocessing technology corresponding to the message type of the second user uplink message, obtaining text form information of the second user uplink message; Identify semantic information of the text form information to obtain a user topic semantic tag of the second user's uplink message; Based on the user topic semantic tag of the second user's uplink message, the attributes of the first message template are updated; wherein the attributes include the number of times the message template triggers the user's uplink positive behavior and the number of times the message template triggers the user's uplink negative behavior.

2. The method according to claim 1, characterized in that The method further comprises: In response to the user's editing operation on the first message template, a target message template for sending a message is generated.

3. The method according to claim 1, characterized in that The step of identifying the user topic semantic tag of the first user's uplink message comprises: Using a preprocessing technology corresponding to the message type of the first user uplink message, obtaining text form information of the first user uplink message; The semantic information of the text form information is identified to obtain a user topic semantic tag of the first user's uplink message.

4. The method according to claim 1, characterized in that: The step of acquiring target message material matching the user topic semantic tag from a message template material knowledge base comprises: Based on the multiple attributes of the message material, the target message material matching the user topic semantic tag is obtained from the message template material knowledge base; wherein the multiple attributes of the message material include material tags and material attributes, the material tags are used to indicate the application scenarios of the message materials, and the material attributes are used to indicate the parameter positions when the message materials are assembled into messages.

5. The method according to claim 1, characterized in that After generating the first message template, the method further includes: The first message template is stored in a message template library, and template attribute information of the first message template is presented in the message template library; wherein the template attribute information includes attribute information of the reaction user feedback information obtained based on the first user uplink message.

6. The method according to claim 5, characterized in that The storing the first message template into a message template library comprises: When a message template identical to the first message template is already stored in the message template library, and a user uplink message associated with the identical message template and the first user uplink message are from different users, the user attention attribute value of the identical message template is updated.

7. The method according to claim 1, characterized in that The method further comprises: Based on the attributes of the first message template, a recommended indicator value of the first message template is updated.

8. The method according to claim 1, characterized in that The generating a first message template based on the message format definition of the message template and the target message material comprises: Generate prompt words based on the message format definition of the message template and the target message material; and generate a first message template based on the prompt words and the trained large language model; or, The vectorized target message material is input into the fine-tuned large speech model to generate a first message template that conforms to the message format definition of the message template.

9. A message template generating device, characterized in that: include: A message analysis module, configured to obtain a first user uplink message and identify a user topic semantic tag of the first user uplink message, wherein the user uplink message refers to message information sent by a user to an application; A material acquisition module, used to acquire target message materials matching the user topic semantic tag from a message template material knowledge base; wherein the message template material knowledge base stores message materials used to generate message templates; A template generation module, configured to generate a first message template based on a message format definition of the message template and the target message material; The template generation module is also used for: Obtaining a second user uplink message of a message feedback sent by the user based on the first message template; Using a preprocessing technology corresponding to the message type of the second user uplink message, obtaining text form information of the second user uplink message; Identify semantic information of the text form information to obtain a user topic semantic tag of the second user's uplink message; Based on the user topic semantic tag of the second user's uplink message, the attributes of the first message template are updated; wherein the attributes include the number of times the message template triggers the user's uplink positive behavior and the number of times the message template triggers the user's uplink negative behavior.

10. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 8 when executed by a processor.

Images