Cboth information generation method and device, storage medium and program product

Abstract

The embodiment of the invention provides a copywriting information generation method and device, a storage medium and a program product. In the embodiment of the invention, document types are distinguished, and in response to a selection operation on at least one text document option and a selection operation on at least one audiovisual document option, a text document generation model and an audiovisual document generation model are respectively utilized to generate an audiovisual document; at least one first textual document and at least one first audiovisual document are generated. And further, in response to a publishing operation, combining the first audio-visual copywriting and the first text copywriting into target copywriting information according to copywriting layout information supported by a target social platform, and publishing the target copywriting information to the target social platform. The writing speed of the copywriting information can be improved, and the use experience of the service demand user and the transaction rate between the service demand user and the second user are improved.

Description

Technical Field

[0001] The present application relates to the field of computer processing technology, and in particular to a method, device, storage medium and program product for generating text information. Background Art

[0002] With the development of Internet technology, posting on social platforms to guide C-end users to retain information has become a mainstream trend. Taking the housekeeping platform as an example, the platform agent can post a post containing the resume of the housekeeper through the social platform. The resume content can be based on the basic information and work experience of the aunt, write relevant introduction copy, and select appropriate pictures or videos for posting, so as to achieve the purpose of retaining information from C-end users.

[0003] However, the above method, through manual writing of publishing copy content, requires repeated searching for the characteristics and advantages of domestic workers in resumes when there are a large number of domestic workers, which is cumbersome, labor-intensive, and inefficient. Summary of the invention

[0004] Multiple aspects of the present application provide a copywriting information generation method, device, storage medium and program product to improve the speed of copywriting information, and the service demand user can quickly obtain key information related to the second user through the copywriting information, which can improve the transaction rate between the service demand user and the second user.

[0005] The embodiment of the present application provides a method for generating copy information, which is applied to a target service platform, wherein the target application runs on a terminal device of a first user, and an information publishing page in the target application is associated with a social platform, the method comprising: receiving a notification message of a second user uploading resume information, wherein the notification message includes identification information of the second user, and is used to notify the first user to publish profile information for the first user on the social platform; in response to the first user's access operation to the information publishing page, displaying the information publishing page, wherein the information publishing page includes at least one copy option of a text type and at least one copy option of an audio-visual type; wherein the at least one copy option of an audio-visual type is used to indicate generation of at least one audio-visual copy based on an audio-visual copy generation model, and the at least one copy option of a text type is used to indicate generation of at least one audio-visual copy based on an audio-visual copy generation model. Instructing to generate at least one text copy based on a text copy generation model; responding to a selection operation of the at least one text-type copy option, determining a selected first target copy option, and calling the text copy generation model to generate a first text copy according to the first target copy option and the resume information; responding to a selection operation of the at least one audio-visual copy option, determining a selected second target copy option, and calling the audio-visual copy generation model to generate a first audio-visual copy adapted to the second target material option according to the second target material option and the resume information; responding to a publishing operation, combining the first audio-visual copy and the first text copy into target copy information according to the copy layout information supported by the target social platform, and publishing the target material information on the target social platform.

[0006] An embodiment of the present application also provides an electronic device, including: a memory and a processor; the memory is used to store a computer program; the processor is coupled to the memory and is used to execute the computer program to implement the steps in the above method.

[0007] An embodiment of the present application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor implements the steps in the above method.

[0008] An embodiment of the present application also provides a computer program product, which includes a computer program / instructions. When the computer program / instructions are executed by a processor, the processor is enabled to implement the steps in the above method.

[0009] In the embodiment of the present application, the copy types are distinguished into text copy and audio-visual copy, and in response to the selection operation of at least one text copy option and the selection operation of at least one audio-visual copy option, at least one first text copy and at least one first audio-visual copy are generated using the text copy generation model and the audio-visual copy generation model, respectively, for the first user to select the copy type from, so as to generate the target copy information, thereby improving the writing speed of the copy information, and selecting the copy type according to the actual needs of the first user can also improve the user experience. Further, in response to the publishing operation, according to the copy layout information supported by the target social platform, the first audio-visual copy and the first text copy are combined into the target copy information, and the target copy information is published on the target social platform. The combination of multiple types of copy makes it easy for users to quickly understand key information in combination with the multiple types of copy information contained in the target copy information, thereby improving the transaction rate between the service demand user and the second user. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0011] Figure 1 A flowchart of a method for generating copywriting information provided by an exemplary embodiment of the present application;

[0012] Figure 2a A schematic diagram of a resume filling interface provided for an exemplary embodiment of the present application;

[0013] Figure 2b A schematic diagram of another resume filling interface provided for another exemplary embodiment of the present application;

[0014] Figure 2c A schematic diagram of another resume filling interface provided for another exemplary embodiment of the present application;

[0015] Figure 2d A schematic diagram of another resume filling interface provided for another exemplary embodiment of the present application;

[0016] Figure 3 A schematic structural diagram of an electronic device provided as an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0018] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0019] In view of the technical problem that when publishing the copy content manually, there is a large number of domestic workers and it is cumbersome, labor-intensive and inefficient to repeatedly search for the characteristics and advantages of domestic workers in their resumes, in the case of a large number of domestic workers, in an embodiment of the present application, the copy types are differentiated into text copy and audio-visual copy, and in response to the selection operation of at least one text copy option and the selection operation of at least one audio-visual copy option, at least one first text copy and at least one first audio-visual copy are generated using a text copy generation model and an audio-visual copy generation model, respectively, for the first user to select a copy type from, so as to generate the target copy information, thereby improving the speed of writing the copy information, and selecting the copy type according to the actual needs of the first user can also improve the user experience. Furthermore, in response to the publishing operation, the first audio-visual copy and the first text copy are combined into target copy information according to the copy layout information supported by the target social platform, and the target copy information is published on the target social platform. The combination of multiple types of copy makes it easier for users to quickly understand key information based on the multiple types of copy information contained in the target copy information, thereby improving the transaction rate between the service demand user and the second user.

[0020] A solution provided by an embodiment of the present application is described in detail below in conjunction with the accompanying drawings.

[0021] Figure 1 The following is a flow chart of a method for generating text information provided by an exemplary embodiment of the present application. Figure 1 As shown, the method is applied to a target application, the target application is run on a terminal device of a first user, and an information publishing page in the target application is associated with a social platform, and the method includes:

[0022] 101. Receive a notification message of a second user uploading resume information, where the notification message includes identification information of the second user, and is used to notify a first user to publish profile information for the first user on a social platform;

[0023] 102. In response to the first user's access operation to the information release page, display the information release page, wherein the information release page includes at least one text copy option and at least one audio-visual copy option; wherein the at least one audio-visual copy option is used to instruct to generate at least one audio-visual copy based on the audio-visual copy generation model, and the at least one text copy option is used to instruct to generate at least one text copy based on the text copy generation model;

[0024] 103. In response to a selection operation of at least one text-type copywriting option, determine a selected first target copywriting option, and call a text copywriting generation model to generate a first text copywriting according to the first target copywriting option and resume information;

[0025] 104. In response to a selection operation of at least one audio-visual text option, determine a selected second target text option, and call an audio-visual text generation model to generate a first audio-visual text adapted to the second target text option according to the second target text option and the resume information;

[0026] 105. In response to the publishing operation, the first audiovisual copy and the first text copy are combined into target copy information according to copy layout information supported by the target social platform, and the target copy information is published on the target social platform.

[0027] In this embodiment, the implementation form of the first user's terminal device is not limited. The terminal device can be a smart handheld device, such as a smart phone, a tablet computer, a laptop or a desktop computer, etc.; or the terminal device can also be a smart wearable device, such as a smart watch, a smart bracelet, etc.; or the terminal device can also be various smart home appliances with display screens, such as a smart TV, a smart large screen or a smart robot, etc.

[0028] In this embodiment, the target application is an application with a copywriting information generation function. It should be noted that the target application can be used only to generate copywriting information, or the target application can be used to generate copywriting information and provide services to service demand users. In the case where the target application can be used to generate copywriting information and provide services to service demand users, the target application can be a housekeeping service application, a rental service application, or a food delivery service application, etc.

[0029] In this embodiment, the first user may be a staff member of the target application, and the staff member may be a manager, an operation and maintenance staff, a developer, etc. The second user may be a service staff member or a merchant who has signed a contract with the service staff member, and this embodiment does not limit this. The service staff member may be a domestic service staff member or a service staff member of other industries. Taking domestic service staff as an example, domestic service staff members may be live-in nannies, day shift nannies, hourly workers, confinement nannies, live-in childcare nannies, day shift childcare nannies, etc.

[0030] In this embodiment, the type of social platform is not limited, as long as it can publish copy information and push it to users of the social platform. For example, the social platform can be a platform that can provide social capabilities, such as Douyin, Xiaohongshu, blogs, etc.

[0031] In this embodiment, the second user can fill in the resume information through the resume filling page, which includes at least one page display control. In response to the selection operation of at least one sub-page display control, the corresponding sub-page can be jumped to display, and each sub-page includes at least one required item and / or at least one optional item. Figure 2a For an optional resume fill-in page, such as Figure 2a As shown, the sub-page display control includes "basic information control", "work information control" and "photo information control", and each sub-page display control is associated with a corresponding sub-page. Figure 2a As shown in the figure, the “basic information control” corresponds to the basic information subpage; Figure 2b As shown in the figure, the "work information control" corresponds to the work information subpage; Figure 2c As shown, the "photo information control" corresponds to the photo information subpage. Among them, the basic information subpage includes the housekeeping staff's name, mobile phone number, gender, date of birth, zodiac sign, constellation and other mandatory items. The work information subpage includes mandatory items such as work status, main work type, work experience, expected salary, service address, order acceptance time, and optional items such as secondary work type and entry time. For the jump display method of each subpage, for example, when the subpage displayed when entering the resume filling page is the basic information subpage, in response to the selection operation of the "work information control", the basic information subpage jumps to the work information subpage; further, in response to the selection operation of the "photo information control", the work information subpage jumps to the photo information subpage.

[0032] In an optional embodiment, the resume filling page may be a page in the target application. The first user may fill in the resume information on the resume filling page after logging into the target application. The first user may also enter the resume filling page to fill in the resume information through a page link of the resume filling page sent to the first user by the target application.

[0033] Further, after the resume information is filled in, the target application will receive a notification message of the second user uploading the resume information, and the notification message includes the identification information of the second user, which is used to notify the first user to publish the profile information for the first user on the social platform. The identification information of the second user can be the name, contact information or other identification that can represent the second user, which is not limited in this embodiment.

[0034] In this embodiment, the target application also includes an information release page, and in response to the first user's access operation to the information release page, the information release page is displayed, and the information release page includes at least one text copy option and at least one audio-visual copy option. Among them, the at least one audio-visual copy option is used to indicate that at least one audio-visual copy is generated based on the audio-visual copy generation model, and the at least one text copy option is used to indicate that at least one text copy is generated based on the text copy generation model, and the audio-visual copy includes images, audio, and video.

[0035] In an optional embodiment, in response to a selection operation of a copy option of the at least one text category, a selected first target copy option is determined, and based on the first target copy option and the resume information, the text copy generation model is called to generate a first text copy.

[0036] Furthermore, at least one text-type copywriting option also includes a short copywriting option and a long copywriting option, the short copywriting has a first character threshold, the long copywriting has a second character threshold, and the second character threshold is greater than the first character threshold. Then, according to the first target copywriting option and the resume information, the text copywriting generation model is called to generate the first text copywriting, including: determining the job position and gender attribute of the second user based on the resume information; extracting keywords from the resume information; using the text copywriting generation model to analyze the contextual semantics and context of the keywords based on the keywords and the job position; when the first text copywriting is a short copywriting, based on the contextual semantics and context, generating a first detailed description copywriting corresponding to the keywords, the number of characters of the first detailed description copywriting is less than or equal to the first character threshold; when the first text copywriting is a long copywriting, based on the contextual semantics and context, generating a second detailed description copywriting corresponding to the keywords, the number of characters of the second detailed description copywriting is less than or equal to the second character threshold.

[0037] Optionally, based on the resume information, determining the job application and gender attribute of the second user includes: traversing various contents in the resume information table; and reading the job application and gender attributes from the job application item and gender item.

[0038] Optionally, extracting keywords from the resume information includes: preprocessing the resume information to obtain a preprocessed resume information text; performing word segmentation on the preprocessed resume information text to obtain multiple word segments; performing part-of-speech tagging on each word segment, where the parts of speech include nouns, verbs, adjectives, etc.; matching the vocabulary in the resume according to a predefined keyword list; counting the word frequency to extract the vocabulary with higher frequency of occurrence; using a machine learning model to extract candidate keywords from the vocabulary with higher frequency of occurrence; filtering and sorting the candidate keywords, and post-processing them to obtain the final keywords.

[0039] Among them, preprocessing includes data cleaning and noise removal. Data cleaning is used to remove irrelevant information in the resume, such as headers, footers, page numbers, etc.; noise removal is used to delete non-key symbols, special characters and extra blanks in the text. Word segmentation can be performed in Chinese and English. When performing Chinese word segmentation, Chinese word segmentation tools (such as jieba, HanLP, etc.) can be used to segment the text into separate words, and when performing English word segmentation, word segmentation tools (such as NLTK, spaCy, etc.) can be used to segment the text into words. Part-of-speech tagging is used to use natural language processing tools to tag the words after word segmentation and identify nouns, verbs, adjectives, etc. Using machine learning models to extract keywords from words with high frequency can use feature extraction models, such as TF-IDF, Word2Vec, BERT, etc. models to extract features; or, a classification model can be used, such as training a classifier (such as SVM, random forest, neural network, etc.) to identify keywords; or, clustering analysis, such as K-means, hierarchical clustering, etc., can be used to group words with high frequency and extract common keywords for each group. The candidate keywords are filtered and sorted, and then post-processed to obtain the final keywords, including: filtering out irrelevant keywords based on context and domain knowledge; sorting the extracted keywords, giving priority to the most important keywords; synonym merging, merging synonyms to reduce keyword redundancy; context analysis, analyzing the context of keywords to ensure the accuracy of keywords, so as to obtain the final keywords.

[0040] Optionally, a text copy generation model is used to analyze the contextual semantics and context of the keywords based on the keywords and the job positions applied for, including: determining a resume script framework corresponding to the resume information based on the keywords and the job positions applied for, the resume script framework is used to characterize the relationship description information between the components of the resume, the relationship description information at least includes position relationship description information and association relationship description information; and obtaining the contextual semantics and context based on the analysis of the relationship description information.

[0041] In another optional embodiment, according to the second target copy option and the resume information, calling the audio-visual copy generation model to generate a first audio-visual copy adapted to the second target copy option includes: determining the first audio-visual copy type corresponding to the first target copy option according to the identification information of the second target copy option; when the first audio-visual copy type is an image copy, using the audio-visual copy generation model to select a first target background image, a target image copy template, and a first digital human image corresponding to the second user based on the resume information, and generating a target image copy based on the target background image, the target image copy template, and the first digital human image Image copy; when the first audio-visual copy type is an audio copy, the audio-visual copy generation model is used to determine the gender attribute of the second user based on the resume information, and the resume information is converted into a target audio copy based on the gender attribute; when the first audio-visual copy type is a video copy, the audio-visual copy generation model is used to determine the gender attribute of the second user, at least one target background image and a second digital human image based on the resume information, and the resume information is converted into a spoken audio of the second digital human image based on the gender attribute and the resume information, and a target video copy is generated based on at least one target background image, the second digital human image and the spoken audio.

[0042] Based on the semantics, context and gender attributes of the resume information analyzed in the above embodiments, a first target background image, a target image text template and a first digital human image corresponding to the second user are selected based on the resume information, including: selecting a first target background image that is adapted to the context from a background image library according to the context of the resume information; selecting a target image text module that is adapted to the semantics from an image text template library according to the semantics of the resume information; and selecting a first digital human image according to gender attributes, semantics and context.

[0043] In an optional embodiment, the audiovisual copy generation model is used to select a first target background image, a target image copy template, and a first digital human image corresponding to the second user based on the resume information, and a target image copy is generated based on the target background image, the target image copy template, and the first digital human image, including: determining the job position and gender attribute of the second user based on the resume information; selecting a target background image from a background image template library, selecting a first target image copy template from an image copy template library, and selecting a first target digital human image adapted to the second user from a digital human image template library based on the job position and gender attribute. ; Among them, the first target image copy template has image layout information, the first target image copy template includes a background image area, at least one text picture area and a digital human area, different text pictures correspond to different content themes and picture styles, the target background image, the first target image copy template and the first target digital human image have different display levels; extract keywords adapted to each content theme from the resume information, and generate each text picture based on each keyword and the corresponding picture style; based on the target background image, each text picture, the first target digital human image and the hierarchical relationship, generate the image copy according to the layout information of the image copy template.

[0044] In an optional embodiment, an audio-visual copy generation model is used to determine the gender attribute of the second user based on resume information, and the resume information is converted into a target audio copy based on the gender attribute, including: determining the job application position and gender attribute of the second user based on the resume information; extracting keywords from the resume information; using the audio-visual copy generation model to analyze the contextual semantics and context of the keywords based on the keywords and the job application position; generating a detailed description copy of the keywords based on the contextual semantics and context; converting the detailed description copy of the keywords into an audio copy adapted to the gender attribute to obtain the target audio copy.

[0045] In an optional embodiment, at least one target background image has a start time and an end time for display; an audio-visual text generation model is used to determine the gender attribute of the second user, at least one target background image and a second digital human image based on the resume information, and the resume information is converted into a spoken audio of the second digital human image based on the gender attribute and the resume information; and a target video text is generated based on at least one target background image, the second digital human image and the spoken audio, including: determining the job position and gender attribute of the second user based on the resume information; extracting keywords from the resume information; analyzing the contextual semantics and context of the keywords based on the keywords and the job position using the audio-visual text generation model; generating a detailed description text of the keywords based on the contextual semantics and context; converting the detailed description text of the keywords into a spoken text adapted to the gender attribute; and generating a target video text based on at least one target background image having a start time and an end time for display, a second digital human image and a spoken text.

[0046] Further optionally, the resume information includes mandatory resume content and optional resume content; after obtaining the resume information, you can also traverse the resume information; determine whether the resume information includes all mandatory resume content; if the judgment result is no, determine at least one mandatory resume content that is missing in the resume information; generate prompt information based on the at least one mandatory resume content that is missing, and send the prompt information to the second user, so that the second user can submit at least one mandatory resume content to the target application.

[0047] Furthermore, the information release page in the target application also includes multiple social platform selection items, and the multiple social platform selection items are associated with corresponding social platforms. After the first user selects the copy type and generates the corresponding copy information, at least one social platform can be selected from the multiple social platform selection items to share the copy information on the corresponding social platform. It should be noted that for one sharing, the user can select one or more copy types. Figure 2d A page for publishing information about a domestic worker.

[0048] It should be noted that the reasoning process of the text copy generation model and the video copy generation model in the above embodiment can be performed on the server side or on the terminal device. When the reasoning process is performed on the terminal device, the terminal device can be connected to the server side for communication, and the terminal device can send a model conversion request message to the server side, the model conversion request message includes the system type of the mobile terminal, available resource information and the model function required by the mobile terminal, so as to request the server side to convert the initial text copy generation model and the initial copy generation model into the text copy generation model and the audio-visual copy generation model based on the system type, available resource information and model function; receive the model conversion response message returned by the server side, the model conversion response message is used to notify the mobile terminal to obtain the model files of the text copy generation model and the audio-visual copy generation model from the remote persistent storage space; obtain the model files of the text copy generation model and the audio-visual copy generation model from the remote persistent storage space and store them in the local persistent storage space, and when using the text copy generation model and the audio-visual copy generation model, load the model files from the local persistent storage space to run the text copy generation model and the audio-visual copy generation model.

[0049] Among them, the text copy generation model and the audio-visual copy generation model are obtained by converting the model format of the initial text copy generation model and the initial copy generation model. The initial text copy generation model and the initial copy generation model are developed on the server side through a target model development framework suitable for the server side.

[0050] The communication connection between the server and the terminal device can be achieved by wireless communication connection or wired connection. For the wireless communication connection, optionally, the communication connection can be achieved through a mobile network. Accordingly, the network standard of the mobile network can be 2G (GSM), 2.5G (GPRS), 3G (WCDMA, TD-SCDMA, CDMA2000, UTMS), 4G (LTE), 4G+ (LTE+), 5G, WiMax or any of the new network standards that will appear in the future. In addition, when the server and the terminal device are located in the same local area network, wireless communication connection can also be achieved through Bluetooth, WiFi, infrared, zigbee or NFC. For the wired communication connection, optionally, the communication connection can be achieved through Ethernet, serial communication, universal serial bus (USB), high-definition multimedia interface (HDMI) and the like. Among them, Ethernet is usually used for local area network (LAN) connection, which supports multiple transmission rates such as 10Mbps, 100Mbps, 1Gbps, 10Gbps, etc. Serial communication includes standards such as RS-232 and RS-485; it is used to connect computers and external devices such as keyboards, mice, printers, etc. USB includes USB 1.1, USB2.0, USB 3.0, USB 3.1, USB 4 and other versions, each with different transmission rates.

[0051] The technical solutions provided in the above embodiments of the present application distinguish the types of copywriting into text copywriting and audio-visual copywriting, and in response to the selection operation of at least one text copywriting option and the selection operation of at least one audio-visual copywriting option, respectively use the text copywriting generation model and the audio-visual copywriting generation model to generate at least one first text copywriting and at least one first audio-visual copywriting for the first user to select the copywriting type from, so as to generate the target copywriting information, thereby improving the writing speed of the copywriting information, and selecting the copywriting type according to the actual needs of the first user can also improve the user's experience. Further, in response to the publishing operation, according to the copywriting layout information supported by the target social platform, the first audio-visual copywriting and the first text copywriting are combined into the target copywriting information, and the target copywriting information is published on the target social platform. The combination of multiple types of copywriting facilitates the user to quickly understand the key information in combination with the multiple types of copywriting information contained in the target copywriting information, thereby improving the transaction rate between the service demand user and the second user.

[0052] Figure 3 The following is a schematic diagram of the structure of an electronic device provided by an exemplary embodiment of the present application. Figure 3As shown, it includes: a memory 30a and a processor 30b; the memory 30a is used to store a computer program; the processor 30b is coupled to the memory 30a and is used to execute the computer program to implement the following steps:

[0053] The method further comprises: receiving a notification message of a second user uploading resume information, wherein the notification message includes identification information of the second user, and is used to notify the first user to publish profile information for the second user on the social platform; in response to the first user's access operation to the information publishing page, displaying the information publishing page, wherein the information publishing page includes at least one text copy option and at least one audio-visual copy option; wherein the at least one audio-visual copy option is used to indicate that at least one audio-visual copy is generated based on an audio-visual copy generation model, and the at least one text copy option is used to indicate that at least one text copy is generated based on a text copy generation model; in response to the at least one text copy option, In response to a selection operation of a copy option, a selected first target copy option is determined, and according to the first target copy option and the resume information, a text copy generation model is called to generate a first text copy; in response to a selection operation of at least one audio-visual copy option, a selected second target copy option is determined, and according to the second target copy option and the resume information, an audio-visual copy generation model is called to generate a first audio-visual copy adapted to the second target copy option; in response to a publishing operation, the first audio-visual copy and the first text copy are combined into target copy information according to the copy layout information supported by the target social platform, and the target copy information is published on the target social platform.

[0054] Further optionally, at least one text-type copywriting option includes a short copywriting option and a long copywriting option, the short copywriting has a first character threshold, the long copywriting has a second character threshold, and the second character threshold is greater than the first character threshold; then, according to the first target copywriting option and the resume information, a text copywriting generation model is called to generate a first text copywriting, including: determining the job and gender attribute of the second user based on the resume information; extracting keywords in the resume information; using the text copywriting generation model to analyze the contextual semantics and context of the keywords based on the keywords and the job application; when the first text copywriting is a short copywriting, based on the contextual semantics and contextwriting, a first detailed description copywriting corresponding to the keywords is generated, and the number of characters in the first detailed description copywriting is less than or equal to the first character threshold; when the first text copywriting is a long copywriting, based on the contextual semantics and contextwriting, a second detailed description copywriting corresponding to the keywords is generated, and the number of characters in the second detailed description copywriting is less than or equal to the second character threshold.

[0055] Optionally, according to the second target copy option and resume information, calling an audio-visual copy generation model to generate a first audio-visual copy adapted to the second target copy option includes: determining the first audio-visual copy type corresponding to the first target copy option according to the identification information of the second target copy option; when the first audio-visual copy type is an image copy, using the audio-visual copy generation model to select a first target background image, a target image copy template and a first digital human image corresponding to the second user based on the resume information, and generating a target image copy based on the target background image, the target image copy template and the first digital human image; when the first audio-visual copy type is an audio copy, using the audio-visual copy generation model to determine the gender attribute of the second user based on the resume information, and converting the resume information into a target audio copy based on the gender attribute; when the first audio-visual copy type is a video copy, using the audio-visual copy generation model to determine the gender attribute of the second user, at least one target background image and a second digital human image based on the resume information, converting the resume information into a spoken audio of the second digital human image based on the gender attribute and the resume information, and generating a target video copy based on at least one target background image, the second digital human image and the spoken audio.

[0056] Optionally, the audio-visual copy generation model is used to select a first target background image, a target image copy template, and a first digital human image corresponding to the second user based on the resume information, and a target image copy is generated based on the target background image, the target image copy template, and the first digital human image, including: determining the job position and gender attribute of the second user based on the resume information; selecting a target background image from a background image template library, selecting a first target image copy template from an image copy template library, and selecting a first target digital human image adapted to the second user from a digital human image template library based on the job position and gender attribute; wherein the first target image The image copy template has image layout information. The first target image copy template includes a background image area, at least one text picture area and a digital human area. Different text pictures correspond to different content themes and picture styles. The target background image, the first target image copy template and the first target digital human image have different display levels. Keywords that are adapted to each content theme are extracted from the resume information, and each text picture is generated based on each keyword and the corresponding picture style. Based on the target background image, each text picture, the first target digital human image and the hierarchical relationship, the image copy is generated according to the layout information of the image copy template.

[0057] Optionally, an audio-visual copy generation model is used to determine the gender attribute of the second user based on resume information, and the resume information is converted into a target audio copy based on the gender attribute, including: determining the job application position and gender attribute of the second user based on the resume information; extracting keywords from the resume information; using the audio-visual copy generation model to analyze the contextual semantics and context of the keywords based on the keywords and the job application position; generating a detailed description copy of the keywords based on the contextual semantics and context; converting the detailed description copy of the keywords into an audio copy adapted to the gender attribute to obtain the target audio copy.

[0058] Furthermore, at least one target background image has a start time and an end time of display; then the audio-visual copy generation model is used to determine the gender attribute of the second user, at least one target background image and a second digital human image based on the resume information, and the resume information is converted into a spoken audio of the second digital human image based on the gender attribute and the resume information, and a target video copy is generated based on at least one target background image, the second digital human image and the spoken audio, including: determining the job position and gender attribute of the second user based on the resume information; extracting keywords from the resume information; using the audio-visual copy generation model to analyze the contextual semantics and context of the keywords based on the keywords and the job position; generating a detailed description copy of the keywords based on the contextual semantics and context; converting the detailed description copy of the keywords into a spoken copy adapted to the gender attribute; generating a target video copy based on at least one target background image having a start time and an end time of display, a second digital human image and a spoken copy.

[0059] Furthermore, the resume information includes mandatory resume content and optional resume content; after obtaining the resume information, the resume information can also be traversed; determine whether the resume information includes all mandatory resume content; if the judgment result is no, determine at least one mandatory resume content that is missing in the resume information; generate prompt information based on the missing at least one mandatory resume content, and send the prompt information to the second user, so that the second user can submit at least one mandatory resume content to the target application.

[0060] Further optionally, the text copy generation model and the audio-visual copy generation model are obtained by converting the model format of the initial text copy generation model and the initial copy generation model, and the initial text copy generation model and the initial copy generation model are developed on the server side through a target model development framework suitable for the server side.

[0061] Further optionally, a model conversion request message is sent to the server, the model conversion request message includes the system type of the mobile terminal, available resource information and model functions required by the mobile terminal, so as to request the server to convert the initial text copy generation model and the initial copy generation model into the text copy generation model and the audio-visual copy generation model based on the system type, available resource information and model functions; a model conversion response message returned by the server is received, the model conversion response message is used to notify the mobile terminal to obtain the model files of the text copy generation model and the audio-visual copy generation model from the remote persistent storage space; the model files of the text copy generation model and the audio-visual copy generation model are obtained from the remote persistent storage space and stored in the local persistent storage space, and when the text copy generation model and the audio-visual copy generation model are used, the model files are loaded from the local persistent storage space to run the text copy generation model and the audio-visual copy generation model.

[0062] Furthermore, if Figure 3 As shown, the electronic device also includes: a communication component 30c, a display 30d, a power component 30e, an audio component 30f and other components. Figure 3 Only some components are shown schematically, which does not mean that the electronic device only includes Figure 3 Components shown.

[0063] The detailed implementation and beneficial effects of the electronic device provided in the embodiments of the present application have been described in detail in the aforementioned embodiments and will not be elaborated here.

[0064] An exemplary embodiment of the present application further provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor is caused to implement the steps in the above-mentioned method embodiments.

[0065] An exemplary embodiment of the present application further provides a computer program product, which includes a computer program / instructions. When the computer program / instructions are executed by a processor, the processor is enabled to implement the steps in the above-mentioned method embodiments.

[0066] The above-mentioned memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0067] The above-mentioned communication component is configured to facilitate wired or wireless communication between the device where the communication component is located and other devices. The device where the communication component is located can access a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G / LTE, 5G and other mobile communication networks, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (Ultra Wide Band, UWB) technology, Bluetooth (BlueTooth, BT) technology and other technologies.

[0068] The above-mentioned display includes a screen, and the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0069] The power supply assembly provides power to various components of the device where the power supply assembly is located. The power supply assembly may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device where the power supply assembly is located.

[0070] The above-mentioned audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (Microphone, MIC), and when the device where the audio component is located is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in a memory or sent via a communication component. In some embodiments, the audio component also includes a speaker for outputting an audio signal.

[0071] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, compact disk read-only memory (Compact Disk Read-Only Memory, CD-ROM), optical storage, etc.) that contain computer-usable program code.

[0072] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0073] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0075] In a typical configuration, a computing device includes one or more processors (Central Processing Unit, CPU), input / output interface, network interface and memory.

[0076] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash memory (flashRAM). The memory is an example of a computer-readable medium.

[0077] Computer-readable media include permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change random access memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0078] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0079] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for generating copywriting information, characterized in that: Applied to a target application, the target application is run on a terminal device of a first user, and an information publishing page in the target application is associated with a social platform, the method comprising: Receiving a notification message of a second user uploading resume information, wherein the notification message includes identification information of the second user and is used to notify the first user to publish profile information for the second user on the social platform; In response to the first user's access operation to the information release page, the information release page is displayed, wherein the information release page includes at least one text copy option and at least one audio-visual copy option; wherein the at least one audio-visual copy option is used to indicate that at least one audio-visual copy is generated based on an audio-visual copy generation model, and the at least one text copy option is used to indicate that at least one text copy is generated based on a text copy generation model; In response to a selection operation of the copywriting option of the at least one text category, determining a selected first target copywriting option, and calling the text copywriting generation model to generate a first text copy according to the first target copywriting option and the resume information; In response to a selection operation of the at least one audio-visual text option, determining a selected second target text option, and calling the audio-visual text generation model to generate a first audio-visual text adapted to the second target text option according to the second target text option and the resume information; In response to a publishing operation, the first audiovisual copy and the first text copy are combined into target copy information according to copy layout information supported by the target social platform, and the target copy information is published on the target social platform.

2. The method according to claim 1, characterized in that The copy options of the at least one text category include a short copy option and a long copy option, the short copy has a first character threshold, the long copy has a second character threshold, and the second character threshold is greater than the first character threshold; According to the first target copy option and the resume information, calling the text copy generation model to generate a first text copy includes: Based on the resume information, determining the job position and gender attribute of the second user; Extracting keywords from the resume information; Analyze the contextual semantics and language context of the keyword based on the keyword and the job position using the text copy generation model; In the case where the first text copy is the short copy, generating a first detailed description copy corresponding to the keyword based on the contextual semantics and context, wherein the number of characters in the first detailed description copy is less than or equal to the first character threshold; In the case where the first text copy is the long copy, a second detailed description copy corresponding to the keyword is generated based on the contextual semantics and context, and the number of characters in the second detailed description copy is less than or equal to the second character threshold.

3. The method according to claim 1, characterized in that According to the second target text option and the resume information, calling the audio-visual text generation model to generate a first audio-visual text adapted to the second target text option includes: Determining a first audiovisual text type corresponding to the first target text option according to the identification information of the second target text option; In the case where the first audio-visual copy type is an image copy, using the audio-visual copy generation model to select a first target background image, a target image copy template, and a first digital human image corresponding to the second user based on the resume information, and generating a target image copy based on the target background image, the target image copy template, and the first digital human image; In the case where the first audiovisual copy type is an audio copy, using the audiovisual copy generation model to determine the gender attribute of the second user based on the resume information, and converting the resume information into a target audio copy based on the gender attribute; In the case where the first audio-visual copy type is a video copy, the audio-visual copy generation model is used to determine the gender attribute, at least one target background image and a second digital human image of the second user based on the resume information, the resume information is converted into spoken audio of the second digital human image based on the gender attribute and the resume information, and a target video copy is generated based on the at least one target background image, the second digital human image and the spoken audio.

4. The method according to claim 3, characterized in that The method comprises: selecting a first target background image, a target image text template, and a first digital human image corresponding to the second user based on the resume information by using the first artificial intelligence big model, and generating a target image text based on the target background image, the target image text template, and the first digital human image, including: Based on the resume information, determining the job position and gender attribute of the second user; Based on the job position and the gender attribute, a target background image is selected from a background image template library, a first target image copy template is selected from an image copy template library, and a first target digital human image adapted to the second user is selected from a digital human image template library; wherein the first target image copy template has image layout information, the first target image copy template includes a background image area, at least one text image area and a digital human area, different text images correspond to different content themes and image styles, and the target background image, the first target image copy template and the first target digital human image have different display levels; Extracting keywords that match each content theme from the resume information, and generating text images based on each keyword and a corresponding image style; Based on the target background image, the text images, the first target digital human image and the hierarchical relationship, the image copy is generated according to the layout information of the image copy template.

5. The method according to claim 3, characterized in that: Determining the gender attribute of the second user based on the resume information using the audiovisual copy generation model, and converting the resume information into a target audio copy based on the gender attribute, including: Based on the resume information, determining the job position and gender attribute of the second user; Extracting keywords from the resume information; Analyzing the contextual semantics and language context of the keywords based on the keywords and the job positions using the audio-visual copy generation model; Based on the contextual semantics and context, generate a detailed description copy of the keyword; The detailed description text of the keyword is converted into an audio text adapted to the gender attribute to obtain a target audio text.

6. The method according to claim 3, characterized in that The at least one target background image has a start time and an end time for display; The method comprises: using the audio-visual text generation model to determine the gender attribute of the second user, at least one target background image, and a second digital human image based on the resume information; converting the resume information into a spoken audio of the second digital human image based on the gender attribute and the resume information; and generating a target video text based on the at least one target background image, the second digital human image, and the spoken audio, including: Based on the resume information, determining the job position and gender attribute of the second user; Extracting keywords from the resume information; Analyzing the context and language of the key words based on the key words and the job positions using the audio-visual copywriting generation model; Based on the contextual semantics and context, generate a detailed description copy of the keyword; Converting the detailed description of the keyword into a spoken copy adapted to the gender attribute; A target video copy is generated based on the start time and end time of display of the at least one target background image, the second digital human image and the spoken copy.

7. The method according to any one of claims 1 to 6, characterized in that The resume information includes required resume content and optional resume content; After obtaining the resume information, the method further includes: Traversing the resume information; Determine whether the resume information includes all required resume contents; If the result of the judgment is negative, determining at least one required resume content item missing from the resume information; Prompt information is generated based on the at least one required resume content item that is missing, and the prompt information is sent to the second user, so that the second user can submit the at least one required resume content item to the target application.

8. The method according to any one of claims 1 to 6, characterized in that The text copy generation model and the audio-visual copy generation model are obtained by converting the model format of the initial text copy generation model and the initial copy generation model, and the initial text copy generation model and the initial copy generation model are developed on the server side through a target model development framework suitable for the server side.

9. The method according to claim 8, characterized in that Also includes: Sending a model conversion request message to the server, wherein the model conversion request message includes the system type of the mobile terminal, available resource information, and model functions required by the mobile terminal, so as to request the server to convert the initial text copy generation model and the initial copy generation model into the text copy generation model and the audio-visual copy generation model based on the system type, available resource information, and model functions; Receiving a model conversion response message returned by the server, wherein the model conversion response message is used to notify the mobile terminal to obtain the model files of the text copy generation model and the audio-visual copy generation model from a remote persistent storage space; The model files of the text copy generation model and the audio-visual copy generation model are obtained from the remote persistent storage space and stored in the local persistent storage space. When the text copy generation model and the audio-visual copy generation model are used, the model files are loaded from the local persistent storage space to run the text copy generation model and the audio-visual copy generation model.

10. An electronic device, characterized in that: include: Memory and processor; The memory is used to store a computer program; the processor is coupled to the memory and is used to execute the computer program to implement the steps in the method according to any one of claims 1 to 9.

11. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is caused to implement the steps in the method according to any one of claims 1 to 9.

12. A computer program product, characterized in that The computer program product comprises a computer program / instruction, which, when executed by a processor, enables the processor to implement the steps of any one of the methods of claims 1 to 7.

Images