Text content generation method and device, medium, electronic equipment and program product

Abstract

The invention discloses a text content generation method and device, a medium, electronic equipment and a program product, and the method comprises the steps: displaying an information configuration interface which is used for configuring an attribute value of a preset attribute field of a to-be-recommended object; in response to a triggered generation operation, target text content is generated based on an attribute value configured by the information configuration interface, the target text content is used for live broadcast, the target text content comprises a tag field and text content corresponding to the tag field, the tag field is used for representing a content structure of the target text content, and the text content is used for representing the content structure of the target text content. The target text content comprises the label field and the text content corresponding to the label field, and the label field is used for representing the content structure of the target text content, so that when a user browses the target text content, the content structure of the target text content can be clearly known, the user can conveniently understand the target text content, and the user experience is improved. And a data basis is provided for improving the live broadcast effect based on the target text content.

Description

Technical Field

[0001] The present disclosure relates to the field of live broadcast technology, and in particular, to a text content generation method, device, medium, electronic device and program product. Background Art

[0002] With the rapid growth of streaming media technology, live broadcasting business is becoming increasingly popular, and live broadcasting platforms have become one of the most popular media nowadays. Generally speaking, in order to improve the live broadcasting effect, before users start live broadcasting, they can conduct live broadcasting simulation exercises based on pre-provided text content for live broadcasting.

[0003] In related technologies, models can be used to automatically generate text content for live broadcasting for users. The quality of text content is one of the important factors affecting the live broadcasting effect. Therefore, how to improve the quality of text content is crucial. Summary of the invention

[0004] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] In a first aspect, the present disclosure provides a text content generation method, comprising: Displaying an information configuration interface, wherein the information configuration interface is used to configure attribute values ​​of preset attribute fields of the object to be recommended; In response to the triggered generation operation, target text content is generated based on the attribute value configured in the information configuration interface, and the target text content is used for live broadcast. The target text content includes a label field and text content corresponding to the label field, and the label field is used to characterize the content structure of the target text content.

[0006] In a second aspect, the present disclosure provides a text content generating device, comprising: A first display module is configured to display an information configuration interface, wherein the information configuration interface is used to configure attribute values ​​of preset attribute fields of the objects to be recommended; The first generation module is configured to generate target text content in response to a triggered generation operation based on the attribute value configured in the information configuration interface, wherein the target text content is used for live broadcast, and the target text content includes a label field and text content corresponding to the label field, and the label field is used to characterize the content structure of the target text content.

[0007] In a third aspect, the present disclosure provides a computer-readable medium having a computer program stored thereon, which implements the steps of the method described in the first aspect when the computer program is executed by a processing device.

[0008] In a fourth aspect, the present disclosure provides an electronic device, including: a storage device having a computer program stored thereon; A processing device is used to execute the computer program in the storage device to implement the steps of any one of the methods in the first aspect.

[0009] In a fifth aspect, the present disclosure provides a computer program product, comprising a computer program, which implements the steps of the method described in the first aspect when executed by a processor.

[0010] Through the above technical solution, since the target text content includes a label field and text content corresponding to the label field, the label field is used to characterize the content structure of the target text content, so that when the user browses the target text content, the content structure of the target text content can be clearly understood, which facilitates the user's understanding of the target text content and provides a data basis for improving the effect of live broadcast based on the target text content.

[0011] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings: Figure 1 The figure is a flowchart of a method for generating text content according to an exemplary embodiment of the present disclosure.

[0013] Figure 2a It is a schematic diagram of a first information configuration interface according to an exemplary embodiment of the present disclosure.

[0014] Figure 2b is another schematic diagram of a first information configuration interface according to an exemplary embodiment of the present disclosure.

[0015] Figure 3a is a schematic diagram of a second information configuration interface according to an exemplary embodiment of the present disclosure.

[0016] Figure 3b It is an interface diagram after configuring the attribute value of the corresponding preset attribute field based on the input operation.

[0017] Figure 4 It is an interface schematic diagram of a display interface and an information configuration interface according to an exemplary embodiment of the present disclosure.

[0018] Figure 5 is a schematic diagram of a practice interface according to an exemplary embodiment of the present disclosure Figure 6 It is a schematic diagram of an interface of a displayed analysis report according to an exemplary embodiment of the present disclosure.

[0019] Figure 7 The present invention is a block diagram of a text content generating device according to an exemplary embodiment of the present invention.

[0020] Figure 8 It is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0022] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0023] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0024] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0025] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0026] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0027] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0028] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0029] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0030] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0031] At the same time, it is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0032] In the related art, a model can be used to automatically generate text content for users to use in live broadcasting, and users can practice live broadcasting or simulate live broadcasting based on the text content. However, in the related art, the generated text content lacks a description of the content structure, which makes it difficult for users to understand, affecting the effect of users' simulated practice of live broadcasting based on the text content or affecting the effect of live broadcasting.

[0033] In addition, after the simulation practice, the user needs to repeatedly watch the recorded video or audio file of the practice in order to analyze the deficiencies in the practice process, which is inefficient.

[0034] In view of this, embodiments of the present disclosure provide a text content generation method, device, medium, electronic device, and program product.

[0035] The present disclosure is further explained and illustrated below in conjunction with the accompanying drawings.

[0036] Figure 1 The flowchart of a text content generation method according to an exemplary embodiment of the present disclosure is shown. The text content generation method can be applied to an electronic device, and the text content generation method can be executed by a text content generation device, wherein the text content generation device can be implemented by software and / or hardware, and the software and / or hardware can be configured in the electronic device. Figure 1 , the text content generation method may include the following steps: Step 110, displaying an information configuration interface, the information configuration interface is used to configure the attribute values ​​of the preset attribute fields of the objects to be recommended; Step 120, in response to the triggered generation operation, target text content is generated based on the attribute value configured in the information configuration interface, the target text content is used for live broadcast, the target text content includes a tag field and text content corresponding to the tag field, and the tag field is used to characterize the content structure of the target text content.

[0037] Through the above method, since the target text content includes a label field and text content corresponding to the label field, the label field is used to characterize the content structure of the target text content, so that when the user browses the target text content, the content structure of the target text content can be clearly understood, which is convenient for the user to understand the target text content, thereby providing a data basis for improving the live broadcast effect.

[0038] In the present disclosure, users can perform live broadcast based on target text content, or practice live broadcast based on target text content. As an example, the target text content may include text content related to the object to be recommended, or may include text content related to the object to be recommended and interactive content that simulates interaction with users watching the live broadcast.

[0039] In the present disclosure, the object to be recommended may refer to a commodity, such as books, food, and clothes, etc. The present disclosure is exemplarily described below with the object to be recommended being a commodity.

[0040] In the present disclosure, the attribute values ​​corresponding to the preset attribute fields are used to describe the objects to be recommended, and the preset attribute fields include selling point attribute fields, name attribute fields, category attribute fields, and discount attribute fields, etc. Among them, some preset attribute fields can support automatic filling of attribute values, and the attribute values ​​of some preset attribute fields need to be selected by the user. For specific configuration, please refer to the following embodiments.

[0041] In a possible manner, the information configuration interface can also be used to configure the user's name attribute field, and the user's user name attribute field can set a default attribute value. In addition, the user's name attribute field can also support the user's autonomous modification, and when the user autonomously configures the attribute value of the user's name attribute field, if it is detected that the attribute value of the user's name attribute field is the same as the attribute value of the configured user's name attribute field, the electronic device can display a first prompt message, and the first prompt message is used to prompt the user not to repeatedly configure the same user name. As an example, the first prompt message can be "User names cannot be repeated."

[0042] In the present disclosure, step 110 may be implemented in the following manner: in response to a triggered information configuration operation, an information configuration interface is displayed, wherein the information configuration operation may be a single-click operation or a double-click operation on an information configuration control, and the like.

[0043] In a possible manner, the electronic device may display the generated target text content in response to a display operation on the target text content, so as to facilitate browsing.

[0044] In a possible manner, the object to be recommended may be an object that obtains attribute values ​​through a preset interface, and correspondingly, the display information configuration interface includes a first information configuration interface, and the first information configuration interface is also used to configure the object to be recommended. Among them, the object that can obtain attribute values ​​through the preset interface belongs to an online object, which is an object stored in the commodity library. Such objects maintain attribute values ​​of preset attribute fields, so they can be obtained through the preset interface. Therefore, the above method may also include: in response to an object selection operation triggered on the first information configuration interface, obtaining the attribute value of the preset attribute field of the object to be recommended corresponding to the object selection operation through the preset interface; according to the attribute value, automatically filling in the attribute value of the corresponding preset attribute field in the first information configuration interface.

[0045] It should be noted that the object to be recommended can be configured through an object selection operation.

[0046] In the present disclosure, the attribute value of the preset attribute field of the selected object to be recommended can be obtained through the interface. The preset attribute field here may refer to a field that supports automatic filling of attribute values. For example, the preset interface can be obtained by obtaining the information of the selected object to be recommended for analysis, and the information here may refer to information containing attribute values, such as the product details page of the object to be recommended. The product details page describes the selling point information (corresponding to the attribute value of the selling point attribute field) and promotion information (corresponding to the attribute value of the promotion attribute field) of the product. The selling point information and promotion information can be image information and text information. Therefore, the corresponding attribute values ​​can be extracted based on the semantic understanding and image analysis of the product details page, and returned through the preset interface to realize the automatic acquisition of the attribute values ​​of the preset attribute fields of the object to be recommended.

[0047] Figure 2a is a schematic diagram of a first information configuration interface according to an exemplary embodiment of the present disclosure. Figure 2a In the example, an add control "*Add Product" is provided for adding products. The object selection operation triggered by the add control can trigger a process of obtaining the attribute value of the preset attribute field of the selected object to be recommended through the preset interface, and automatically fill the obtained attribute value into the corresponding preset attribute field. Figure 2b is another schematic diagram of a first information configuration interface according to an exemplary embodiment of the present disclosure, Figure 2b This is an interface diagram after the attribute value of the preset attribute field is automatically filled. Figure 2b , automatically fill in the preset attribute fields of attribute values, such as product selling point attribute fields and discount attribute fields.

[0048] It is worth mentioning that Figure 2a and Figure 2b The first information configuration interface shown also includes a name editing control “*user name” for editing the user's name attribute field. By triggering the name editing control, the attribute value of the user's name attribute field can be autonomously modified.

[0049] It is worth noting that the control "*Add Product" can support the product search function. After the user enters a keyword, a list of products matching the keyword can be provided for the user to perform an object selection operation.

[0050] It is worth noting that after the attribute value is automatically filled, the user can also support self-modification, and before the automatic filling, the first information configuration interface can display the second prompt information corresponding to the preset attribute field, which is used to prompt the user that the automatic filling and self-modification of the user can be supported after the product is selected. The second prompt information can refer to Figure 2aFor a preset attribute field that can be set with multiple attribute values, the second prompt information corresponding to the preset attribute field can also prompt the user to input the format of the attribute value independently, for example, two attribute values ​​need to be directly configured with preset symbols.

[0051] Through the above method, the function of automatically obtaining attribute values ​​is utilized to realize automatic acquisition of attribute values ​​without the need for users to fill in manually, thereby improving the configuration efficiency of the attribute values ​​of the recommended objects; at the same time, it supports users to modify attribute values ​​independently, thereby improving the practicality of the overall solution.

[0052] In a possible manner, the object to be recommended may also be an object that obtains attribute values ​​based on a user's input operation, and correspondingly, the display information configuration interface includes a second information configuration interface. Compared with an object that can obtain attribute values ​​from a preset interface, an object that obtains attribute values ​​based on a user's input operation is an offline object, and the product library does not maintain such an object, and further does not maintain attribute values, so the attribute values ​​cannot be obtained through the preset interface. Therefore, the above method may also include: in response to an input operation triggered by a preset attribute field in the second information configuration interface, displaying input data corresponding to the input operation in the second information configuration interface, the input data being used to characterize the attribute value of the preset attribute field.

[0053] In this embodiment, the preset attribute fields may include a name attribute field describing the object to be recommended, a category attribute field, a selling point attribute field, and a preferential attribute field, etc. For each preset attribute field, an input operation may be performed.

[0054] Figure 3a is a schematic diagram of a second information configuration interface according to an exemplary embodiment of the present disclosure. Figure 3a In the example, controls corresponding to preset attribute fields are provided, and corresponding input data is displayed according to the input operation of the corresponding controls. Figure 3b is another schematic diagram of a second information configuration interface according to an exemplary embodiment of the present disclosure, Figure 3b It is an interface diagram after configuring the attribute value of the corresponding preset attribute field based on the input operation. Figure 3b The preset attribute fields include, for example, the name attribute field, category attribute field, selling point attribute field, and discount attribute field that describe the object to be recommended. For these preset attribute fields, users can edit the attribute values ​​independently.

[0055] It is worth mentioning that Figure 3a and Figure 3b The second information configuration interface shown also includes a name editing control “*user name” for editing the user's name attribute field. By triggering the name editing control, the attribute value of the user's name attribute field can be independently edited.

[0056] In this embodiment, when the attribute value of the preset attribute field has not been configured, the third prompt information of the corresponding preset attribute field can be displayed. For example, for the name attribute field and the category attribute field, the third prompt information can be used to prompt the maximum number of words of the input data allowed to be entered by the user and the number of words of the input data entered by the user. For another example, for a preset attribute field that can set multiple attribute values, such as a selling point attribute field, the third prompt information can prompt the user to enter the format of the attribute value independently, for example, two attribute values ​​directly need to be configured with a preset symbol.

[0057] In the above manner, the attribute value of the corresponding object to be recommended is configured through user input.

[0058] In the present disclosure, the mutual switching between the first information configuration interface and the second information configuration interface can be realized through the object switching control. Figure 2a , the object switching control can be Figure 2a The "listed products" and "custom products" shown in the figure can be switched by selecting an object to display the corresponding first information configuration interface or second information configuration interface.

[0059] It is worth noting that, after the information configuration operation is triggered, it can be configured that the first information configuration interface or the second information configuration interface is displayed by default.

[0060] In the present disclosure, when generating target text content, the preset attribute fields may include fields that must be configured with attribute values, and may also include fields that do not have to be configured with attribute values. For fields that must be configured with attribute values, corresponding fourth prompt information may be displayed to prompt that the field must be configured with attribute values. For example, when the preset attribute field is a selling point attribute field, the fourth prompt information is "the attribute value corresponding to the selling point attribute field is key information in the text content used for live broadcast and is a required item."

[0061] In the present disclosure, the generating operation can be triggered by the generating operation, for example, by clicking or double-clicking. Further, when the preset attribute field that must be configured with an attribute value is not configured with an attribute value, the generating operation can be in a disabled state, that is, the generating operation cannot be triggered.

[0062] In a possible manner, the preset attribute field includes an attribute field that provides candidate attribute values. In this case, after configuring the object to be recommended, the above method may also include: in the information configuration interface, displaying at least one target control, each of the at least one target control corresponds to a candidate attribute value corresponding to the preset attribute field, and the candidate attribute value is predicted based on the information of the object to be recommended; in response to a trigger operation on the target control, using the candidate attribute value corresponding to the target control as the attribute value of the preset attribute field.

[0063] It is worth noting that the candidate attribute values ​​are attribute values ​​provided to users for quick configuration. For objects that obtain attribute values ​​through a preset interface, the information of the object to be recommended may be the product details page of the object to be recommended, and the candidate attribute values ​​may be predicted based on, for example, the product details page of the object to be recommended. For objects that obtain attribute values ​​based on user input operations, the information of the object to be recommended may be the attribute values ​​of the name attribute field and the category attribute field input by the user to describe the object to be recommended, and the candidate attribute values ​​may be predicted based on the attribute values ​​of the name attribute field and the category attribute field input by the user. In a possible manner, a large language model (LLM) may be used for prediction.

[0064] Following the above example, in this embodiment, the attribute field providing the candidate attribute value may be a selling point attribute field and a preferential attribute field. Figure 2b and Figure 3b For the selling point attribute field, the target control "Dressing skills" is displayed; for the discount attribute field, the target control "Get coupons when the transaction is completed" is displayed.

[0065] In the present disclosure, the triggering operation of the target control can be implemented based on a single-click operation on the target control.

[0066] At the same time, the corresponding configured attribute value can also support the cancellation operation. Figure 3b , you can delete the configured property values ​​based on the delete controls corresponding to each property value, for example, Figure 3b Delete the control "Quick-drying X" corresponding to the property value "Quick-drying".

[0067] Through the above method, attribute values ​​are recommended to users, which reduces the difficulty of configuring attribute values ​​and thus improves the configuration efficiency of attribute values.

[0068] In a possible manner, step 120 may be implemented in the following manner: in response to a triggered generation operation, different content generation models are used based on the attribute values ​​configured in the information configuration interface to generate target text content corresponding to each content generation model.

[0069] The target text contents generated by different content generation models are different. As an example, the target text contents may have different styles, such as formal style and informal style. In contrast to the formal style, the informal style is a humorous style. As another example, the focus of the target text contents may be different. For example, the focus of the target text contents may focus on introducing the product content, or may focus on the interactive content when introducing the product.

[0070] Different content generation models can be obtained by using different training data, so as to achieve the generation of different target text contents. As an example, the content generation model can be a large language model.

[0071] From the above content, it can be seen that the target text content needs to include a label field that describes the content structure. When training the content generation model, the following structural rules can be used as the rules for generating the target text content to guide the generation of the target text content, so that the trained content generation model is capable of generating target text content that expresses the content structure. The structural rules can refer to the following table:

[0072] Among them, the second-level tag is the next-level tag of the first-level tag, and the first-level tag and the second-level tag in the table are used to characterize the content structure of the target text content. In other embodiments, a third-level tag can also be set under the second-level tag.

[0073] According to the above table, the generated target text content can be: "[Label A] <Tag A1>XXXX.

[0074] <Tag A2>XXXX.

[0075]

Label B

[0076] <Tag B2>XXXXXXXXX.

[0077]

Label C

[0078] <Tag C2>XXXX. ” Through the above method, multiple versions of target text content are provided for users to browse, thereby improving the richness of data and supporting users to select preferred target text content from multiple versions of target text content.

[0079] In the present disclosure, a generation interface is displayed in parallel with the information configuration interface, and a generation operation can be displayed in the generation interface to trigger the generation operation.

[0080] In the present disclosure, after the target text content is generated, the target text content can be displayed on a display interface. The display interface and the information configuration interface can be displayed in parallel.

[0081] Figure 4 is an interface diagram of a display interface and an information configuration interface according to an exemplary embodiment of the present disclosure. Figure 4The display interface and the information configuration interface can be displayed in parallel. In the display interface, the target text content generated by different content generation models can be switched through the switch control "target text content 1" or "target text content 2" for switching the display of the target text content.

[0082] Continue to refer to Figure 4 , the user can trigger the "regenerate" control for regenerating the target text content to achieve the regeneration of the target text content of the corresponding content generation model. In other embodiments, the operation for regenerating the text content corresponding to each label field can be triggered to correspondingly regenerate the text content of some label fields.

[0083] Continue to refer to Figure 4 , the user can realize autonomous editing of the target text content by triggering the "Edit" control for editing the target text content, and after editing, the user can also perform a save operation through the electronic device. After the user edits, before performing a save operation through the electronic device, when performing operations such as refreshing the page or closing the page, a fifth prompt message can be displayed to prompt the user to perform a save operation through the electronic device. In other embodiments, when there are many idle resources, each editing operation of the user can trigger automatic saving.

[0084] In a possible manner, after the target text content is generated, the method may further include: in response to a modification operation on the attribute value, displaying prompt information, the prompt information being used to prompt whether to regenerate the target text content.

[0085] After the prompt message is displayed, the user can decide whether to trigger the generation operation based on the actual situation. After the generation operation is triggered, different content generation models can be used to regenerate the target text content corresponding to each content generation model based on the attribute values ​​configured in the information configuration interface.

[0086] In a possible manner, the above method may further include: obtaining user feedback data, the user feedback data being used to represent the user's evaluation of the target text content generated by each content generation model; and determining whether to update each content generation model based on the user feedback data.

[0087] Among them, the user feedback data can represent the user's evaluation of whether the generated target text content is satisfied. Figure 4 , the user can trigger the control "like" or "dislike" trigger operation to achieve the evaluation of the generated target text content. It can be understood that "like" is a satisfactory evaluation and "dislike" is an unsatisfactory evaluation.

[0088] In the present disclosure, user feedback data within a preset time period can be counted to determine whether to update each content generation model. For example, if more than a preset number or a preset proportion of user feedback data within a preset time period for a content generation model are unsatisfactory, it is determined that the content generation model is updated; otherwise, it is determined that the content generation model is not updated.

[0089] Through the above method, the user's feedback data on the target text content is used to determine whether to update the content generation model, so as to ensure that the content generation model can meet the user's demand for content.

[0090] In the present disclosure, the user can select from a plurality of target text contents and perform live practice based on the selected target text contents. As an example, after the user selects the target text content for live practice and triggers the operation of entering the practice interface, the practice interface is further displayed. Figure 5 This is a schematic diagram of a practice interface according to an exemplary embodiment of the present disclosure, in which a practice control "start practice" can be triggered to start recording of live practice. If the practice control is triggered without the user selecting target text content for live practice, a sixth prompt information can be displayed, which is used to prompt the user to select the target text content.

[0091] In the present disclosure, before entering into recording, it is necessary to obtain permission to use the microphone and camera and detect whether the microphone and camera are present. If permission to use the microphone and camera is not obtained or the microphone and camera are not detected, the seventh prompt message is displayed. The seventh prompt message is used to prompt the user that the microphone and camera are abnormal and ask the user to try again.

[0092] In the present disclosure, the recording can simultaneously record the audio and picture during the live practice to obtain a corresponding multimedia file.

[0093] In the present disclosure, after the user triggers recording, the practice interface can display a countdown to start recording, and the countdown can display minute information and second information. For different categories of objects to be recommended, the configured countdown duration can be different.

[0094] In the present disclosure, the recording may be performed according to pre-configured recording parameters, for example, the size of the recorded picture may be the same as the size of the live broadcast picture.

[0095] In the present disclosure, saving can be performed in real time during the recording process, or the saving of the recorded multimedia file can be performed after receiving a saving operation triggered by the user.

[0096] In the present disclosure, the target text content may only include content related to the product, and there is no interactive content. Therefore, an eighth prompt information may also be displayed in the practice interface. Among them, the eighth prompt information is used to prompt the user to increase interaction in the contact to get closer to the live broadcast scene.

[0097] In the present disclosure, during the recording process, the user can trigger the operation of ending the recording through the electronic device, and the electronic device responds to the operation and displays the ninth prompt information. The ninth prompt information is used to prompt the user whether to confirm the end of the recording, and the recording result can be scored after the end of the recording. While displaying the ninth prompt information, a confirmation control and a cancel control are displayed to support the user to submit an instruction to confirm the end of the recording or cancel the end of the recording.

[0098] Continue to refer to Figure 5 In the present disclosure, in the practice interface, the target text content and the recording screen can be provided synchronously, and the selling point attribute values ​​involved in the target text content (for example Figure 5 Selling point 1, selling point 2, etc.) and preferential attribute values ​​(e.g. Figure 5 Activity 1, Activity 2, etc. shown).

[0099] In a possible manner, the above method may also include: obtaining a multimedia file to be evaluated, the multimedia file being a recording of a user's live practice based on the target text content; determining report content based on the multimedia file and a preset strategy; and generating an analysis report of the multimedia file based on the report content, the analysis report being used to reflect the user's language expression ability.

[0100] In the present disclosure, the user can trigger the operation of scoring the above recording results through the electronic device, and after the operation is triggered, the tenth prompt information is displayed. The tenth prompt information is used to prompt the user that the recording results have been submitted and the corresponding analysis report has been generated.

[0101] In the present disclosure, the multimedia file may be a video file or an audio file, which is not limited in the present disclosure.

[0102] In the present disclosure, the electronic device may display the analysis report in response to a display operation for the analysis report triggered by the user, so as to facilitate the user's browsing.

[0103] The following example takes the report content including score information, task information, target suggestion information, prohibited content information, selling point information and annotation information as an example, and combines Figure 6 To illustrate the present disclosure, Figure 6 It is a schematic diagram of an interface of a displayed analysis report according to an exemplary embodiment of the present disclosure.

[0104] In the present disclosure, the rating information may include a rating score and an evaluation text corresponding to the rating score. The rating score may be set to a corresponding rating level, such as level A, level B, level C, and level D. Figure 6 When displayed, the rating score can be displayed with the corresponding rating level. Further, an explanation control for the rating level can be triggered to display the relationship between the rating level and the rating score.

[0105] In the present disclosure, the report content may include rating information, and the preset attribute field includes a selling point attribute field. The above-mentioned step of determining the report content based on the multimedia file and the preset strategy may include: determining the rating score based on the difference between the duration of the multimedia file and the preset standard duration, the difference between the text content describing the selling point in the multimedia file and the attribute value of the configured selling point attribute field, and the number of times preset banned words appear in the text content corresponding to the multimedia file; and determining the evaluation text corresponding to the rating score based on the rating score.

[0106] For example, the score weights of multiple scoring items can be set. As an example, the scoring items can include a scoring item for explanation duration, and the scoring item for explanation duration corresponds to the difference between the duration of the multimedia file and the preset standard duration. The highest score for the scoring item for explanation duration can be set to 10 points, and the score is determined according to the difference between the duration of the multimedia file and the preset standard duration. The greater the difference, the lower the score, and the smaller the difference, the higher the score.

[0107] As an example, the scoring item may include a selling point explanation scoring item, which corresponds to the difference between the text content describing the selling point in the multimedia file and the attribute value of the configured selling point attribute field. The selling point explanation scoring item may be set to a maximum score of 40 points, and the score is determined according to the difference between the text content describing the selling point in the multimedia file and the attribute value of the configured selling point attribute field. For example, the score may be characterized in the following manner: S=C1 / C2*40; Wherein, S represents the score, C1 represents the number of types of selling points involved in the multimedia file, which can be obtained by analyzing the text content describing the selling points in the multimedia file, and C2 represents the number of attribute values ​​of the configured selling point attribute field.

[0108] As an example, the scoring item may include a content standard scoring item, which corresponds to the number of times a preset banned word appears in the text content corresponding to the multimedia file. The content standard scoring item may be set to a maximum score of 50 points, and the score is determined according to the number of times the preset banned word appears in the text content corresponding to the multimedia file, and the more times the banned word appears, the lower the score.

[0109] In the present disclosure, preset banned words may be configured in advance, and whether the preset banned words appear in the text content is determined based on the semantic configuration.

[0110] In the present disclosure, the evaluation text corresponding to the scoring score can be pre-configured. When determining the analysis report, the evaluation text corresponding to the scoring score is directly obtained.

[0111] Continue to refer to Figure 6 ,The report content can also include task information, which can be user name information, task creation time information and continuous duration information, which can be obtained from the configuration information of the information configuration interface and the process of the user recording multimedia files.

[0112] In the present disclosure, the report content may also include first suggestion information. The above-mentioned step of determining the report content based on the multimedia file and a preset strategy may also include: determining whether the text content corresponding to the multimedia file meets the conditions of the corresponding suggestion text; and determining the suggestion text corresponding to the conditions as the first suggestion information.

[0113] As an example, the condition of the suggested text may include a condition related to the selling point attribute field. Specifically, the condition of the suggested text may be that the attribute value describing the selling point attribute field in the text content of the multimedia file pair does not completely cover the attribute value related to the selling point attribute field in the target text content.

[0114] As an example, the condition for suggesting text may include a condition related to a preset banned word. Specifically, the condition for suggesting text may be that text content matching the preset banned word exists in the text content of the multimedia file pair.

[0115] As an example, the condition for suggesting text may include that the duration of the multimedia file is less than a preset duration threshold, wherein the preset duration threshold may be 8 minutes.

[0116] Among them, by splicing all the suggestion texts corresponding to the conditions, the first suggestion information can be obtained.

[0117] It should be understood that the suggested text corresponding to the condition may be pre-configured. When the suggested text is displayed, the dimension corresponding to the suggested text is displayed synchronously, for example Figure 6 The dimensions of selling point explanation, banned words and explanation duration are mentioned.

[0118] In the present disclosure, the report content may also include second suggestion information, such as Figure 6 The second suggestion information is a common and required suggestion information in any analysis report. The second suggestion information is used to prevent users from guiding consumers to conduct transactions offline or on other platforms (non-live broadcast platforms) to maintain security.

[0119] In the present disclosure, the report content may also include prohibited content information. The above-mentioned step of determining the report content based on the multimedia file and the preset strategy may also include: determining whether there is text matching the preset banned words in the text content corresponding to the multimedia file; determining the text matching the preset banned words in the text content as prohibited content; and determining the prohibited content information based on all prohibited content.

[0120] Among them, the text content can be matched with preset banned words based on semantics.

[0121] Continue to refer to Figure 6 The prohibited content information includes the number of times the preset prohibited words appear in the text content corresponding to the multimedia file, the prohibited word labels corresponding to the preset prohibited words (e.g. Figure 6 false propaganda in the text content), the text content corresponding to the preset banned words (such as Figure 6 The time when the text content in: XXXXX) appears in the multimedia file (e.g. Figure 6 The start time mentioned above) and corresponding optimization suggestions.

[0122] When there are a lot of text contents corresponding to the preset banned words, they can be displayed in a folded display mode, and a control for displaying all the contents can be provided, such as Figure 6 The "all records" shown are used to trigger the display of text content corresponding to all preset banned words.

[0123] In the present disclosure, it can be seen from the above content that the preset attribute field includes a selling point attribute field. In this case, the report content also includes selling point information, and the selling point information is used to characterize whether the attribute value corresponding to the configured selling point attribute field is covered by the text content corresponding to the multimedia file. The above step of determining the report content based on the multimedia file and based on the preset strategy may also include: comparing the first text content and the second text content to obtain a comparison result, the first text content is the text content corresponding to the multimedia file, and the second text content is the attribute value corresponding to the configured selling point attribute field; determining the selling point comparison information based on the comparison result.

[0124] The selling point comparison information includes the attribute value corresponding to the configured selling point attribute field, and the display style of the display content corresponding to the attribute value covered by the text content corresponding to the multimedia file is different from that of the attribute value not covered by the text content corresponding to the multimedia file. Figure 6In the example shown, first, the attribute values ​​corresponding to the configured selling point attribute fields can be displayed in sequence, and the display styles of the display content corresponding to the attribute values ​​covered by the text content corresponding to the multimedia file and the display content corresponding to the attribute values ​​not covered by the text content corresponding to the multimedia file can be distinguished. Based on the different display styles, the user can clearly distinguish the selling points explained during the practice from the selling points not explained. The display content in this embodiment may include the attribute values ​​corresponding to the selling point attribute fields (e.g. Figure 6 Selling point 1 and selling point 2 in the multimedia file), the text content corresponding to the attribute value covered by the text content corresponding to the multimedia file (for example Figure 6 the explanation content in the multimedia file), and the time when the text content appears in the multimedia file.

[0125] When there is a lot of display content, it can be displayed in a folded display manner, and a control for displaying all the display content is provided, such as Figure 6 The "all records" shown are used to trigger the display of all display contents.

[0126] In the present disclosure, the report content may also include annotation information, and the annotation information is used to characterize the text content corresponding to the multimedia file and the content structure of the text content. The above-mentioned step of determining the report content based on the multimedia file and a preset strategy may also include: segmenting the text content corresponding to the multimedia file to obtain at least one sub-text; for each sub-text in the at least one sub-text, determining a label field that matches the semantics of the sub-text, and annotating the sub-text according to the label field that matches the semantics to obtain an annotation result of the sub-text, wherein the annotation result characterizes the content structure; generating annotation information according to each sub-text and the annotation results corresponding to each sub-text.

[0127] The multimedia file may be divided into time periods, and text extraction may be performed on each time period to obtain at least one subtext.

[0128] Among them, the label field in this embodiment is the label field involved in the target text content. For details, please refer to the label field provided in the above table. As an example, at least one subtext in the annotation information is displayed in the order of the time when it appears in the multimedia file. When the subtext is displayed, the corresponding label field is displayed at the same time. Figure 6 In the example shown, when the subtext "Can you hear it?" is displayed, the label field "Product introduction" is displayed.

[0129] Continue to refer to Figure 6 In the present disclosure, the report content may also include the video corresponding to the multimedia file. Figure 6The playback control shown realizes the playback and pause of the video, and supports the user to control the playback parameters during the playback process. The playback parameters include the playback progress and the playback volume, etc. In addition, a ninth prompt information may be further displayed, and the ninth prompt information is used to prompt that the video can only be played within the validity period.

[0130] After obtaining the contents of each report, the contents of each report are spliced ​​together to obtain an analysis report, for example Figure 6 The analysis report shown.

[0131] Through the above method, the multimedia files recorded by the user when practicing live broadcast based on the target text content are evaluated in multiple dimensions such as explanation duration and explanation content, and the text content corresponding to the multimedia file is structuredly annotated, so that the user can quickly and clearly understand the missing content when tracing back the recording structure, which is conducive to the user to conduct targeted live broadcast practice on the missing content, thereby improving the live broadcast effect.

[0132] In a possible manner, the analysis report of the multimedia file may be returned to the task configuration platform, and the task configuration platform may determine whether to assign a task of re-performing live broadcast practice to the user client where the user is located according to the analysis report.

[0133] In this way, users can be motivated to continuously improve the effectiveness of live broadcast practice, thereby improving the live broadcast effect.

[0134] Figure 7 is a block diagram of a text content generating device according to an exemplary embodiment of the present disclosure. Figure 7 , the text content generating device 700 comprises: The first display module 701 is configured to display an information configuration interface, wherein the information configuration interface is used to configure attribute values ​​of preset attribute fields of the objects to be recommended; The first generation module 702 is configured to generate target text content in response to a triggered generation operation based on the attribute value configured in the information configuration interface, wherein the target text content is used for live broadcast, and the target text content includes a tag field and text content corresponding to the tag field, and the tag field is used to characterize the content structure of the target text content.

[0135] Optionally, the object to be recommended includes an object whose attribute value is obtained through a preset interface, the display information configuration interface includes a first information configuration interface, and the first information configuration interface is also used to configure the object to be recommended, and the device 700 further includes: A first response module is configured to, in response to an object selection operation triggered on the first information configuration interface, obtain, through the preset interface, an attribute value of a preset attribute field of a to-be-recommended object corresponding to the object selection operation; The filling module is configured to automatically fill in the attribute value of the corresponding preset attribute field in the first information configuration interface according to the attribute value.

[0136] Optionally, the object to be recommended includes an object whose attribute value is obtained based on an input operation of a user, the display information configuration interface includes a second information configuration interface, and the device 700 further includes: The second response module is configured to respond to an input operation triggered by a preset attribute field in the second information configuration interface, and display input data corresponding to the input operation in the second information configuration interface, wherein the input data is used to represent the attribute value of the preset attribute field.

[0137] Optionally, the preset attribute field includes an attribute field for providing a candidate attribute value, and the apparatus 700 further includes: A second display module is configured to display at least one target control in the information configuration interface after configuring the object to be recommended, each of the at least one target control corresponding to a candidate attribute value corresponding to the preset attribute field, and the candidate attribute value is predicted based on the information of the object to be recommended; The third response module is configured to respond to the trigger operation on the target control and use the candidate attribute value corresponding to the target control as the attribute value of the preset attribute field.

[0138] Optionally, the first generating module 702 is further configured to: in response to a triggered generating operation, adopt different content generating models based on the attribute values ​​configured in the information configuration interface to generate target text content corresponding to each of the content generating models.

[0139] Optionally, the device 700 further includes: The fourth response module is configured to display prompt information in response to a modification operation on the attribute value after generating the target text content, wherein the prompt information is used to prompt whether to regenerate the target text content.

[0140] Optionally, the device 700 further includes: A first acquisition module is configured to acquire user feedback data, wherein the user feedback data is used to represent the user's evaluation of the target text content generated by each content generation model; The first determination module is configured to determine whether to update each of the content generation models according to the user feedback data.

[0141] Optionally, the device 700 further includes: A second acquisition module is configured to acquire a multimedia file to be evaluated, wherein the multimedia file is a recording of a user performing a live practice based on the target text content; A second determination module is configured to determine report content based on the multimedia file and a preset strategy; The second generating module is configured to generate an analysis report of the multimedia file according to the report content, wherein the analysis report is used to reflect the language expression ability of the user.

[0142] Optionally, the report content includes rating information, the rating information includes a rating score and an evaluation text corresponding to the rating score, the preset attribute field includes a selling point attribute field, and the second determination module includes: A first determination submodule is configured to determine a rating score according to a difference between a duration of the multimedia file and a preset standard duration, a difference between a text content describing a selling point in the multimedia file and an attribute value of the configured selling point attribute field, and a number of times a preset banned word appears in the text content corresponding to the multimedia file; The second determination submodule is configured to determine the evaluation text corresponding to the rating score according to the rating score.

[0143] Optionally, the report content includes first suggestion information, and the second determining module includes: A third determination submodule is configured to determine whether the text content corresponding to the multimedia file meets the condition of the corresponding suggested text; The fourth determining submodule is configured to determine the suggestion text corresponding to the condition that satisfies the condition as the first suggestion information.

[0144] Optionally, the report content includes prohibited content information, and the second determination module includes: A fifth determination submodule is configured to determine whether there is text matching a preset banned word in the text content corresponding to the multimedia file; A sixth determination submodule is configured to determine the text in the text content that matches the preset banned words as banned content; The seventh determination submodule is configured to determine prohibited content information according to all the prohibited content.

[0145] Optionally, the preset attribute field includes a selling point attribute field, the report content includes selling point information, and the selling point information is used to indicate whether the attribute value corresponding to the configured selling point attribute field is covered by the text content corresponding to the multimedia file, and the second determining module includes: A comparison submodule is configured to compare the first text content with the second text content to obtain a comparison result, wherein the first text content is the text content corresponding to the multimedia file, and the second text content is the attribute value corresponding to the configured selling point attribute field; The eighth determining submodule is configured to determine selling point comparison information according to the comparison result.

[0146] Optionally, the display styles of the attribute values ​​covered by the text content corresponding to the multimedia file and the display styles of the display contents corresponding to the attribute values ​​not covered by the text content corresponding to the multimedia file in the selling point comparison information are different.

[0147] Optionally, the report content includes annotation information, where the annotation information is used to characterize text content corresponding to the multimedia file and a content structure of the text content, and the second determining module includes: a segmentation submodule, configured to segment the text content corresponding to the multimedia file to obtain at least one subtext; a marking submodule configured to determine, for each subtext in the at least one subtext, the tag field that matches the semantics of the subtext, and mark the subtext according to the tag field that matches the semantics to obtain a marking result of the subtext, wherein the marking result represents the content structure; The generating submodule is configured to generate the annotation information according to each of the subtexts and the annotation results corresponding to each of the subtexts.

[0148] An embodiment of the present disclosure provides a computer-readable medium having a computer program stored thereon. When the computer program is executed by a processing device, the steps of the above-mentioned text content generation method are implemented.

[0149] An embodiment of the present disclosure provides a computer program product, including a computer program, which implements the steps of the above-mentioned text content generation method when executed by a processor.

[0150] An embodiment of the present disclosure provides an electronic device, including: a storage device having a computer program stored thereon; A processing device is used to execute the computer program in the storage device to implement the steps of the above-mentioned text content generation method.

[0151] Reference below Figure 8, which shows a schematic diagram of the structure of an electronic device 800 suitable for implementing the embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 8 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0152] like Figure 8 As shown, the electronic device 800 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage device 808 to a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 are also stored. The processing device 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0153] Typically, the following devices may be connected to the I / O interface 805: an input device 806 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 807 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 808 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 809. The communication device 809 may allow the electronic device 800 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 8 The electronic device 800 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0154] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 809, or installed from a storage device 808, or installed from a ROM 802. When the computer program is executed by the processing device 801, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0155] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0156] In some embodiments, the electronic devices may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0157] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0158] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: displays an information configuration interface, wherein the information configuration interface is used to configure the attribute values ​​of the preset attribute fields of the objects to be recommended; in response to a triggered generation operation, generates target text content based on the attribute values ​​configured in the information configuration interface, wherein the target text content is used for live broadcast, and the target text content includes a tag field and text content corresponding to the tag field, wherein the tag field is used to characterize the content structure of the target text content.

[0159] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0160] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0161] The modules involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a module does not, in some cases, limit the module itself.

[0162] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0163] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0164] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0165] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0166] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims. Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Claims

1. A method for generating text content, characterized in that: include: Displaying an information configuration interface, wherein the information configuration interface is used to configure attribute values ​​of preset attribute fields of the object to be recommended; In response to the triggered generation operation, target text content is generated based on the attribute value configured in the information configuration interface, and the target text content is used for live broadcast. The target text content includes a label field and text content corresponding to the label field, and the label field is used to characterize the content structure of the target text content.

2. The method according to claim 1, characterized in that The object to be recommended includes an object that obtains an attribute value through a preset interface, the display information configuration interface includes a first information configuration interface, and the first information configuration interface is also used to configure the object to be recommended, and the method further includes: In response to an object selection operation triggered on the first information configuration interface, acquiring, through the preset interface, an attribute value of a preset attribute field of the to-be-recommended object corresponding to the object selection operation; According to the attribute value, the attribute value of the corresponding preset attribute field is automatically filled in the first information configuration interface.

3. The method according to claim 1, characterized in that The object to be recommended includes an object whose attribute value is obtained based on an input operation of a user, the information display configuration interface includes a second information configuration interface, and the method further includes: In response to an input operation triggered by a preset attribute field in the second information configuration interface, input data corresponding to the input operation is displayed in the second information configuration interface, where the input data is used to represent an attribute value of the preset attribute field.

4. The method according to claim 1, characterized in that: The preset attribute field includes an attribute field that provides candidate attribute values. After configuring the object to be recommended, the method further includes: In the information configuration interface, at least one target control is displayed, each of the at least one target control corresponds to a candidate attribute value corresponding to the preset attribute field, and the candidate attribute value is predicted based on the information of the object to be recommended; In response to a trigger operation on the target control, the candidate attribute value corresponding to the target control is used as the attribute value of the preset attribute field.

5. The method according to claim 1, characterized in that The generating operation in response to the triggering generates target text content based on the attribute value configured in the information configuration interface, including: In response to the triggered generation operation, different content generation models are used based on the attribute values ​​configured in the information configuration interface to generate target text content corresponding to each of the content generation models.

6. The method according to claim 1, characterized in that After generating the target text content, the method further includes: In response to the modification operation on the attribute value, prompt information is displayed, where the prompt information is used to prompt whether to regenerate the target text content.

7. The method according to claim 5, characterized in that The method further comprises: Acquire user feedback data, where the user feedback data is used to represent the user's evaluation of the target text content generated by each of the content generation models; Determine whether to update each of the content generation models according to the user feedback data.

8. The method according to any one of claims 1 to 7, characterized in that: The method further comprises: Acquire a multimedia file to be evaluated, wherein the multimedia file is a recording of a user performing a live practice based on the target text content; According to the multimedia file, determining the report content based on a preset strategy; An analysis report of the multimedia file is generated according to the report content, wherein the analysis report is used to reflect the language expression ability of the user.

9. The method according to claim 8, characterized in that The report content includes rating information, the rating information includes a rating score and an evaluation text corresponding to the rating score, the preset attribute field includes a selling point attribute field, and the determining of the report content based on the preset strategy according to the multimedia file includes: Determine a rating score according to the difference between the duration of the multimedia file and a preset standard duration, the difference between the text content describing the selling point in the multimedia file and the attribute value of the configured selling point attribute field, and the number of times a preset banned word appears in the text content corresponding to the multimedia file; According to the rating score, an evaluation text corresponding to the rating score is determined.

10. The method according to claim 8, characterized in that The report content includes first suggestion information, and the determining of the report content based on the multimedia file and a preset strategy further includes: Determining whether the text content corresponding to the multimedia file meets the conditions of the corresponding suggested text; The suggestion text corresponding to the condition is determined as the first suggestion information.

11. The method according to claim 8, characterized in that The report content includes prohibited content information, and the determining of the report content based on the multimedia file and a preset policy further includes: Determining whether there is text matching a preset banned word in the text content corresponding to the multimedia file; Determining text in the text content that matches a preset banned word as banned content; Determine prohibited content information based on all the prohibited contents.

12. The method according to claim 8, characterized in that The preset attribute field includes a selling point attribute field, the report content includes selling point information, the selling point information is used to indicate whether the attribute value corresponding to the configured selling point attribute field is covered by the text content corresponding to the multimedia file, and the report content is determined based on the preset strategy according to the multimedia file, further comprising: Comparing the first text content with the second text content to obtain a comparison result, wherein the first text content is the text content corresponding to the multimedia file, and the second text content is the attribute value corresponding to the configured selling point attribute field; According to the comparison result, selling point comparison information is determined.

13. The method according to claim 12, characterized in that The display styles of the attribute values ​​covered by the text content corresponding to the multimedia file in the selling point comparison information are different from the display styles of the display content corresponding to the attribute values ​​not covered by the text content corresponding to the multimedia file.

14. The method according to claim 8, characterized in that The report content includes annotation information, the annotation information is used to characterize the text content corresponding to the multimedia file and the content structure of the text content, and the determining the report content based on the multimedia file and a preset strategy further includes: Segmenting the text content corresponding to the multimedia file to obtain at least one sub-text; For each subtext in the at least one subtext, determining the tag field that matches the semantics of the subtext, and annotating the subtext according to the tag field that matches the semantics to obtain an annotation result of the subtext, wherein the annotation result represents the content structure; The annotation information is generated according to each of the sub-texts and the annotation results corresponding to each of the sub-texts.

15. A text content generating device, characterized in that: include: A first display module is configured to display an information configuration interface, wherein the information configuration interface is used to configure attribute values ​​of preset attribute fields of the objects to be recommended; The first generation module is configured to generate target text content in response to a triggered generation operation based on the attribute value configured in the information configuration interface, wherein the target text content is used for live broadcast, and the target text content includes a label field and text content corresponding to the label field, and the label field is used to characterize the content structure of the target text content.

16. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processing device, the steps of the method according to any one of claims 1 to 14 are implemented.

17. An electronic device, characterized in that: include: a storage device having a computer program stored thereon; A processing device, configured to execute the computer program in the storage device to implement the steps of the method according to any one of claims 1 to 14.

18. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 14 are implemented.

Images