Message rendering method and device, electronic equipment and storage medium

Abstract

The invention provides a message rendering method and device, electronic equipment and a storage medium, and relates to the technical field of computers, in particular to the technical fields of information technologies, artificial intelligence, human-computer interaction, interactive systems and the like. According to the specific implementation scheme, under the conditions that a message temporary storage queue is not empty and a rendering processing module is in a non-working state, a target machine message is extracted from the message temporary storage queue; wherein the message temporary storage queue is used for storing at least one machine message sent by the chat robot; the target machine message is a machine message stored in the head of the message temporary storage queue; and rendering the target machine message by using a rendering processing module.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, in particular to technical fields such as information technology, artificial intelligence, human-computer interaction, and interactive systems, and specifically to a message rendering method, device, electronic device, and storage medium. Background Art

[0002] With the continuous iteration and optimization of large language model technology, chatbots based on large language models have also been widely used in many fields. However, the applicability of chatbots in consulting scenarios at the current stage is still insufficient. Summary of the invention

[0003] The present disclosure provides a message rendering method, device, electronic device and storage medium.

[0004] According to a first aspect of the present disclosure, a message rendering method is provided, comprising:

[0005] When the message temporary storage queue is not empty and the rendering processing module is in a non-working state, extracting a target machine message from the message temporary storage queue; wherein the message temporary storage queue is used to store at least one machine message sent by the chat robot; the target machine message is the machine message stored at the head of the message temporary storage queue;

[0006] The target machine message is rendered using the rendering processing module.

[0007] According to a second aspect of the present disclosure, a message rendering device is provided, comprising:

[0008] A message extraction unit, used to extract a target machine message from the temporary message storage queue when the temporary message storage queue is not empty and the rendering processing module is in a non-working state; wherein the temporary message storage queue is used to store at least one machine message sent by the chat robot; the target machine message is the machine message stored at the head of the temporary message storage queue;

[0009] The first message rendering unit is used to render the target machine message by using the rendering processing module.

[0010] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0011] at least one processor;

[0012] a memory communicatively coupled to the at least one processor;

[0013] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method provided by the embodiment of the present disclosure.

[0014] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method provided according to an embodiment of the present disclosure.

[0015] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program, which implements the method provided according to the embodiment of the present disclosure when executed by a processor.

[0016] The use of the present disclosure can improve the applicability of chat robots in consultation scenarios.

[0017] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0019] Figure 1 A flowchart of a message rendering method provided by an embodiment of the present disclosure;

[0020] Figure 2 A schematic diagram of a storage method of machine messages provided in an embodiment of the present disclosure;

[0021] Figure 3 A schematic diagram of a rendering process of a target machine message provided by an embodiment of the present disclosure;

[0022] Figure 4 A schematic diagram of a machine message transfer method provided in an embodiment of the present disclosure;

[0023] Figure 5 A schematic diagram of a transfer method of a consultation message provided in an embodiment of the present disclosure;

[0024] Figure 6 A complete flow chart of a message rendering method provided by an embodiment of the present disclosure;

[0025] Figures 7A to 7F An example diagram of a message rendering method provided by an embodiment of the present disclosure;

[0026] Figure 8 A schematic diagram of a scenario of a message rendering method provided by an embodiment of the present disclosure;

[0027] Fig. 9 A schematic structural block diagram of a message rendering device provided in an embodiment of the present disclosure;

[0028] Fig.10 A schematic structural block diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0030] As mentioned in the background technology, with the continuous iteration and optimization of the big language model technology, chatbots based on the big language model have also been widely used in many fields. However, the applicability of chatbots in the current stage in consulting scenarios is still insufficient.

[0031] Specifically, the inventors have found that the chatbots currently on the market mainly adopt a question-and-answer conversation mode, that is, after the user sends a consultation message, the chatbot will generate a machine message for replying to the consultation message and send it to the terminal device for rendering. Moreover, before the machine message generated by the chatbot is rendered by the terminal device, the user cannot send a new consultation message to the chatbot, and the chatbot will not actively push new machine messages to the user. However, in the consultation scenario, the conversation mode between the user and the chatbot needs to be more flexible. For example, the chatbot needs to actively send one or more machine messages to the user when the user is not speaking, and the terminal device also needs to adaptively display these machine messages. Since the message sending mechanism of the chatbot is convenient and controllable, in order to improve the applicability of the chatbot in the consultation scenario, first of all, it is necessary to provide a method that enables the terminal device to adaptively display one or more machine messages sent by the chatbot.

[0032] In view of the above problems, the embodiments of the present disclosure provide a message rendering method, which can be applied to electronic devices. The electronic device can be a terminal device. Here, the terminal device can be a conventional computer (desktop computer, laptop computer, etc.), a car computer, a tablet computer, a smart phone, a personal digital assistant or other similar computing device. Figure 1 The flowchart diagram shown in the figure illustrates a message rendering method provided by an embodiment of the present disclosure. It should be noted that although the logical order is shown in the flowchart diagram, in some cases, the steps shown or described in the flowchart can also be performed in other orders.

[0033] Step S101 : when the temporary message storage queue is not empty and the rendering processing module is in a non-working state, extract the target machine message from the temporary message storage queue.

[0034] Among them, the message temporary storage queue is used to store at least one (that is, one or more) machine messages sent by the chat robot. Here, the chat robot can be implemented by relying on a large language model integrated in a service device (for example, a server, a workbench, a mainframe computer or other similar computing device), and the large language model can be a pre-trained neural network model, which has general language knowledge, world knowledge, professional knowledge in various fields, etc., and is stored in the model in the form of parameters. Specifically, the large language model can be a pre-trained autoregressive generative model of the Transformer architecture. In addition, it should be noted that in the embodiment of the present disclosure, when there are multiple machine messages stored in the message temporary storage queue, the multiple machine messages can be sent by the chat robot at one time, or they can be sent by the chat robot in multiple times, and the embodiment of the present disclosure does not limit this.

[0035] Based on the above description, it can be understood that in the embodiment of the present disclosure, the chat robot can also actively send at least one machine message to the user when the user does not speak. After receiving the at least one machine message sent by the chat robot, the terminal device can store the at least one machine message in the message temporary queue. Specifically, the at least one machine message can be stored in the message temporary queue from the end of the message temporary queue according to the order in which the at least one machine message is sent. Figure 2 For example, the at least one machine message includes machine message 1, machine message 2, and machine message 3. Machine message 1, machine message 2, and machine message 3 may be stored in the message temporary storage queue from the tail of the message temporary storage queue in the order in which they are sent (i.e., first sending machine message 1, then sending machine message 2, and finally sending machine message 3).

[0036] It is understandable that in the embodiment of the present disclosure, the message temporary storage queue usually has more message storage locations, and is not limited to Figure 2 5 shown.

[0037] In addition, in the embodiment of the present disclosure, the target machine message is the machine message stored at the head of the message temporary storage queue. For example, in the above example, the target machine message is machine message 1. Then, when the message temporary storage queue is not empty and the rendering processing module is in a non-working state, machine message 1 can be extracted from the head of the message temporary storage queue as the target machine message. The rendering processing module is used to process the rendering work of conversation messages (for example, machine messages sent by chatbots, consultation messages input by users, etc.).

[0038] Step S102: Render the target machine message using a rendering processing module.

[0039] After the target machine message is extracted from the message temporary storage queue, the target machine message may be rendered in the conversation interface using the rendering processing module.

[0040] Based on the above description of step S101 and step S102, it can be known that the chat robot can also actively send multiple machine messages to the user when the user does not speak. More importantly, after receiving the multiple machine messages sent by the chat robot, the terminal device can store the multiple machine messages in the message temporary storage queue, and adopt the message rendering method provided by the embodiment of the present disclosure, when the message temporary storage queue is not empty and the rendering processing module is in a non-working state, extract the target machine message (that is, the machine message stored at the head of the message temporary storage queue) from the message temporary storage queue, and then use the rendering processing module to render the target machine message. In this way, the message temporary storage function of the message temporary storage queue can be used to assist the rendering processing module in rendering the multiple machine messages sent by the chat robot one by one, so that the terminal device can adaptively display the multiple machine messages sent by the chat robot, thereby improving the applicability of the chat robot in the consultation scenario.

[0041] In addition, it should be noted that in the embodiment of the present disclosure, the working state of the rendering processing module can be determined by the global rendering state variable. For example, when the rendering processing module is in the working state, the global rendering state variable can be set to "1", and when the rendering processing module is in the non-working state, the global rendering state variable can be set to "0". Based on this, it can be understood that in the embodiment of the present disclosure, when the rendering processing module is used to render the target machine message, the global rendering state variable can be set to "1", and after the rendering work for the target machine message is completed, the global rendering state variable can be set to "0".

[0042] Please combine Figure 3 Further, in an optional implementation, the “rendering the target machine message” in step S102 may include:

[0043] Step S302-1, disassemble the target machine message to obtain at least one to-be-rendered part with a specific rendering order.

[0044] Each of the at least one to-be-rendered parts has a corresponding message category. Here, the message category can be a text category or a non-text category, and the non-text category can be one of a resource locator (Uniform Resource Locator, URL) category, a tag category, and a picture category. In this way, not only the richness of the target machine message can be improved, making the conversation interface more vivid and intuitive, but also the readability of the target machine message can be improved to enhance the user experience.

[0045] In addition, in the above implementation, each of the at least one portion to be rendered has the same data structure. Exemplarily, the data structure may be:

[0046] Message category: ******,

[0047] Display content: ******,

[0048] True value: ******,

[0049] Display mode:******

[0050] Assume that the target machine message is disassembled to obtain 4 parts to be rendered with a specific rendering order, and part 1 is included in the 4 parts to be rendered. Its message category is text category, and the displayed content is "Hello, do you want to consult about the popular car models in 2024?", the truth value is empty, and the display mode is word-by-word printing. Then, part 1 to be rendered can be expressed as:

[0051] type: 'text',

[0052] text: 'Hello, do you want to consult about the popular models in 2024? ',

[0053] value:",

[0054] needtype:true

[0055] Among them, "type: 'text'" is used to represent that the message category of part 1 to be rendered is a text category; "text: 'Hello, do you want to consult about the popular car models in 2024?'" is used to represent that the display content of part 1 to be rendered is "Hello, do you want to consult about the popular car models in 2024?"; "value: "" is used to represent that the true value of part 1 to be rendered is empty; "needtype: true" is used to represent that the display mode of part 1 to be rendered is word-for-word printing.

[0056] Assume that the target machine message is disassembled to obtain 4 parts to be rendered with a specific rendering order, and part 2 to be rendered is one of the 4 parts to be rendered. The message category is a non-text category, specifically a URL category, and the displayed content is "Click here to enter the 2024 popular car model introduction page", the true value is https: / / www.pcmi.com, and the display mode is overall printing. Then, part 2 to be rendered can be expressed as:

[0057] type: 'url',

[0058] text: 'Click here to enter the 2024 popular car model introduction page',

[0059] value: 'https: / / www.pcmi.com',

[0060] needtype:false

[0061] Among them, "type: 'url'" is used to characterize that the message category of part 2 to be rendered is the URL category; "text: 'Click here to enter the 2024 popular car model introduction page'" is used to characterize that the display content of part 2 to be rendered is "Click here to enter the 2024 popular car model introduction page"; "value: 'https: / / www.pcmi.com'" is used to characterize that the true value of part 2 to be rendered is "https: / / www.pcmi.com", that is, when the user clicks on the display content "Click here to enter the 2024 popular car model introduction page", it will enter the 2024 popular car model introduction page based on https: / / www.pcmi.com; "needtype: false" is used to characterize that the display mode of part 2 to be rendered is overall printing.

[0062] Assume that the target machine message is disassembled to obtain 4 parts to be rendered with a specific rendering order, and part 3 is included in the 4 parts to be rendered, and its message category is a non-text category, specifically a label category, and the display content is "Here is the car model I am interested in", the truth value is empty, and the display mode is overall printing, then part 3 to be rendered can be expressed as:

[0063] type: 'tag',

[0064] text: 'Here are the models I'm interested in',

[0065] value:",

[0066] needtype:false

[0067] Among them, "type: 'tag'" is used to represent that the message category of the part 3 to be rendered is a tag category; "text: 'Here are the models I am interested in'" is used to represent that the display content of the part 3 to be rendered is "Here are the models I am interested in", and it belongs to a tag; "value: "" is used to represent that the true value of the part 3 to be rendered is empty; "needtype: false" is used to represent that the display mode of the part 3 to be rendered is overall printing.

[0068] Assume that the target machine message is disassembled to obtain 4 parts to be rendered with a specific rendering order, and part 4 is included in the 4 parts to be rendered. The message category is a non-text category, specifically a picture category, and the displayed content is a picture named "WWW Automobile Club Promotional Picture". The true value is / data / images / promotions / WWW Automobile Club Promotional Picture.jpg, and the display mode is overall printing. Then, part 4 to be rendered can be expressed as:

[0069] type: 'image',

[0070] text: 'A picture named "WWW Automobile Club Promotional Picture"',

[0071] value: ' / data / images / promotions / WWW Automobile Club Promotional Picture.jpg',

[0072] needtype:false

[0073] Among them, "type: 'image'" is used to represent that the message category of the part to be rendered 4 is the picture category; "text: 'A picture named "WWW Automobile Club Promotional Picture"'" is used to represent that the display content of the part to be rendered 4 is a picture named "WWW Automobile Club Promotional Picture"; "value: ' / data / images / promotions / WWW Automobile Club Promotional Picture.jpg'" is used to represent that the true value of the part to be rendered 4 is " / data / images / promotions / WWW Automobile Club Promotional Picture.jpg", which is specifically used to represent that the display content of the part to be rendered 4 can be obtained through the storage path " / data / images / promotions / WWW Automobile Club Promotional Picture.jpg"; "needtype: false" is used to represent that the display mode of the part to be rendered 4 is overall printing.

[0074] In addition, it should be noted that, in the above implementation, the specific rendering order of the four parts to be rendered may be the arrangement order of the four parts to be rendered in the target machine message. For example, in the above example, the arrangement order of the four parts to be rendered from front to back is: part 1 to be rendered, part 2 to be rendered, part 3 to be rendered, and part 4 to be rendered. Then, the specific rendering order of the four parts to be rendered from front to back is also: part 1 to be rendered, part 2 to be rendered, part 3 to be rendered, and part 4 to be rendered.

[0075] Step S302-2: determining a target rendering portion from at least one portion to be rendered according to a specific rendering order.

[0076] Continuing with the above example, the specific rendering order of the four parts to be rendered is from front to back: part 1 to be rendered, part 2 to be rendered, part 3 to be rendered, and part 4 to be rendered. Assuming that the rendering work of part 1 to be rendered has been completed, but the rendering work of part 2 to be rendered, part 3 to be rendered, and part 4 to be rendered has not been completed, then according to the specific rendering order, part 2 with rendering can be determined from the four parts to be rendered as the target rendering part; assuming that the rendering work of part 1 to be rendered and part 2 to be rendered has been completed, but the rendering work of part 3 to be rendered and part 4 to be rendered has not been completed, then according to the specific rendering order, part 3 with rendering can be determined from the four parts to be rendered as the target rendering part.

[0077] Step S302-3: Render the target rendering part based on the rendering mode corresponding to the message category corresponding to the target rendering part.

[0078] In one example, when the message category corresponding to the target rendering part is a text category, the target rendering part can be rendered in a word-by-word printing manner (the speed of word-by-word printing can be set according to actual application requirements, and the embodiment of the present disclosure does not limit this); or, when the message category corresponding to the target rendering part is a non-text category, the target rendering part can be rendered in a whole-printing manner. In this way, when the message category corresponding to the target rendering part is a text category, rendering the target rendering part in a word-by-word printing manner will present a typewriter effect, which can not only attract the user's attention to enhance the user experience, but also alleviate the anxiety that the user may have when waiting for the target machine message, so as to further enhance the user experience; when the message category corresponding to the target rendering part is a non-text category, rendering the target rendering part in a whole-printing manner can improve the overall rendering speed of the target machine message.

[0079] In addition, in the above implementation, when the message category corresponding to the target rendering part is a non-text category, and the non-text category is a URL category, the target rendering part may include a URL body part and a page key content corresponding to the URL body part.

[0080] Continuing with the above example, the four parts to be rendered include part 1 to be rendered, part 2 to be rendered, part 3 to be rendered, and part 4 to be rendered. Assuming that the target rendering part is part 2 to be rendered, its URL body part may include:

[0081] type: 'url',

[0082] text: 'Click here to enter the 2024 popular car model introduction page',

[0083] value: 'https: / / www.pcmi.com',

[0084] needtype:false

[0085] That is, the final displayed content of the rendered URL body part is "Click here to enter the 2024 popular car model introduction page"; and the key content of the page corresponding to the URL body part can be the key content extracted from the 2024 popular car model introduction page, which can be text content, picture content, video content, etc., and the present disclosed embodiment does not limit this.

[0086] Furthermore, in the above implementation manner, "rendering the target rendering part in an overall printing manner" may include: rendering the URL body part in a first target area in the conversation interface in an overall printing manner, and determining a second target area related to the first target area in the conversation interface, and then rendering the key content of the page in the second target area in an overall printing manner. Among them, the first target area may be a blank area in the conversation page; the second target area may be an area below the target area, and the embodiments of the present disclosure are not limited to this. In this way, when the message category corresponding to the target rendering part is a non-text category, and the non-text category is a URL category, not only the URL body part will be rendered in the first target area in the conversation interface, but also the key content of the page corresponding to the URL body part will be rendered in the second target area in the conversation interface, so that the user can quickly determine whether it is necessary to enter and browse the overall page content corresponding to the URL body part based on the URL body part based on the key content of the page, so as to enhance the user experience.

[0087] Through the above method, in the embodiment of the present disclosure, the target machine message can be disassembled to obtain at least one part to be rendered with a specific rendering order, and the target rendering part can be determined from the at least one part to be rendered according to the specific rendering order, and then the target rendering part can be rendered based on the rendering method corresponding to the message category corresponding to the target rendering part. In this way, on the one hand, computing resources and memory resources can be dynamically allocated according to the complexity of the target rendering part to avoid resource waste; on the other hand, since each part to be rendered in at least one part to be rendered has a corresponding message category, and the message category can be used to determine the rendering method of the part to be rendered, the parts to be rendered of different message categories in at least one part to be rendered will be rendered based on different rendering methods, which can not only enhance the degree of adaptation of each part to be rendered in at least one part to be rendered and its rendering method, but also improve the display effect of the rendering process. Interesting, to enhance the user experience.

[0088] In some optional implementations, the message rendering method may further include:

[0089] When it is detected that the human-computer interaction touch point is located in the first target area or the second target area, the residence time of the human-computer interaction touch point is recorded;

[0090] Determine the waiting time threshold;

[0091] When the dwell time is greater than or equal to the waiting time threshold, the overall page content corresponding to the URL body is rendered.

[0092] The human-computer interaction touch point may be the stop position of a mouse pointer on the conversation interface, or the stop position of a user's finger on the conversation interface (in this case, the terminal device is a touch-sensitive device).

[0093] In addition, in the embodiments of the present disclosure, the waiting time threshold can be set according to actual application requirements, and the embodiments of the present disclosure do not limit this.

[0094] In one example, the waiting time threshold may be determined in the following manner:

[0095] Get the duration of the current session;

[0096] Calculate the percentage of the number of consultation messages in the current session to the total number of messages in the current session;

[0097] Based on the duration and the percentage value, a waiting time threshold is obtained.

[0098] The consultation message may be a message sent by a user; the total number of messages may be the sum of the number of consultation messages and the number of machine messages. Here, the machine message may be a message sent by a chat robot.

[0099] After obtaining the duration and percentage value, the reference value can be obtained through the following calculation logic:

[0100] TP=T×A+P×B

[0101] Among them, TP is used to represent the reference value; T is used to represent the duration; A is used to represent the first weight value; P is used to represent the percentage value; B is used to represent the second weight value. Here, the first weight value and the second weight value can be set according to actual application requirements, and the embodiments of the present disclosure do not limit this.

[0102] After obtaining the reference value, a time length value that is negatively correlated with the reference value can be obtained as the waiting time threshold. Specifically, the larger the reference value, the shorter the time length value can be obtained as the waiting time threshold; the smaller the reference value, the longer the time length value can be obtained as the waiting time threshold. In this way, a relatively simple calculation logic can be used to obtain the waiting time threshold to improve the execution efficiency of the message rendering method.

[0103] Through the above method, in the embodiment of the present disclosure, when it is detected that the human-computer interaction contact is located in the first target area or the second target area, it can be reasonably inferred that the user has a strong interest in the current consulting content. Therefore, the dwell time of the human-computer interaction contact can be recorded, and the waiting time threshold can be determined. Then, when the dwell time is greater than or equal to the waiting time threshold, the overall page content corresponding to the URL body part is rendered to encourage the user to increase his interest in the current consulting content. In this way, when the rendering method provided by the embodiment of the present disclosure is applied to the consulting scenario in the shopping field, the user's order conversion rate can be significantly improved.

[0104] In an optional implementation, the message rendering method may further include:

[0105] Store the target machine message at the end of the message rendering queue.

[0106] Based on this, in the above implementation, step S302-1, that is, "disassembling the target machine message to obtain at least one to-be-rendered part with a specific rendering order" may include:

[0107] The target machine message stored at the end of the message rendering queue is disassembled to obtain at least one to-be-rendered part having a specific rendering order.

[0108] In one example, before rendering the target machine message using the rendering processing module, the target machine message can be stored in the message rendering queue from the tail of the message rendering queue, that is, the target machine message is stored in the tail of the message rendering queue, and then the target machine message stored in the tail of the message rendering queue is rendered using the rendering processing module. For example, the target machine message stored in the tail of the message rendering queue is disassembled to obtain at least one to-be-rendered part with a specific rendering order (each to-be-rendered part in at least one to-be-rendered part has a corresponding message category); according to the specific rendering order, the target rendering part is determined from the at least one to-be-rendered part; based on the rendering method corresponding to the message category corresponding to the target rendering part, the target rendering part is rendered.

[0109] Please combine Figure 4 For example, the message temporary storage queue stores machine messages 1, 2, and 3 sent by the chat robot. First, machine message 1 can be extracted from the head of the message temporary storage queue as the target machine message, and the target machine message can be stored in the message rendering queue from the tail of the message rendering queue, and then the rendering processing module can be used to render the target machine message stored at the tail of the message rendering queue. After the rendering work for the target machine message is completed, machine message 2 can be extracted from the head of the message temporary storage queue as the new target machine message, and the new target machine message can be stored in the message rendering queue from the tail of the message rendering queue, and then the rendering processing module can be used to render the new target machine message stored at the tail of the message rendering queue. And so on, until the rendering work for all machine messages in the message temporary storage queue is completed.

[0110] It is understandable that in the embodiments of the present disclosure, the message temporary storage queue and the message rendering queue usually have more message storage locations, and are not limited to Figure 4 5 shown.

[0111] In the above manner, in the embodiment of the present disclosure, the target machine message can be stored at the end of the message rendering queue, and the target machine message stored at the end of the message rendering queue can be rendered using the rendering processing module. In this way, based on the persistent storage characteristics of the message rendering queue, the target machine message can be prevented from being damaged or lost, thereby ensuring the reliability of the message rendering method provided by the embodiment of the present disclosure.

[0112] Furthermore, in some optional implementations, the message rendering method may further include:

[0113] generating a consulting message in response to an input operation of a user;

[0114] When the rendering processing module is in a non-working state, the rendering processing module is used to store the consultation message at the end of the message rendering queue, and the consultation message stored at the end of the message rendering queue is used as the target consultation message to render the target consultation message.

[0115] The input operation may be a keyboard input operation, a touch input operation, or a voice input operation, which is not limited in the embodiments of the present disclosure.

[0116] After the consultation message is generated, the consultation message can be stored in the message rendering queue from the end of the message rendering queue using the rendering processing module when the rendering processing module is not in operation, and the consultation message stored at the end of the message rendering queue is used as the target consultation message to render the target consultation message. Figure 5 , continuing with the above example, machine message 1, machine message 2 and machine message 3 have been stored in the message rendering queue. Assuming that, thereafter, in response to the user's input operation, an advisory message 1 is generated, then, when the rendering processing module is in a non-working state, the rendering processing module can be used to store the advisory message 1 in the message rendering queue from the end of the message rendering queue, and the advisory message stored at the end of the message rendering queue is used as the target advisory message to render the target advisory message. Assuming again that, after the rendering work for the target advisory message is completed, in response to the user's input operation, an advisory message 2 is generated, then, when the rendering processing module is in a non-working state, the rendering processing module can be used to store the advisory message 2 in the message rendering queue from the end of the message rendering queue, and the advisory message stored at the end of the message rendering queue is used as the new target advisory message to render the new target advisory message.

[0117] It is understandable that in the embodiments of the present disclosure, the message temporary storage queue and the message rendering queue usually have more message storage locations, and are not limited to Figure 5 5 shown.

[0118] In addition, it should be noted that in the embodiment of the present disclosure, when the target consultation message is rendered using the rendering processing module, the global rendering state variable can be set to "1", and after the rendering work for the target consultation message is completed, the global rendering state variable can be set to "0".

[0119] Through the above method, in the embodiment of the present disclosure, after generating a consultation message in response to a user's input operation, when the rendering processing module is in a non-working state, the consultation message can be stored at the end of the message rendering queue using the rendering processing module, and the consultation message stored at the end of the message rendering queue can be used as the target consultation message to render the target consultation message. In this way, based on the persistent storage characteristics of the message rendering queue, the target consultation message can be prevented from being damaged or lost, thereby ensuring the reliability of the message rendering method provided by the embodiment of the present disclosure.

[0120] The following will be combined Figure 6 , the complete process of a message rendering method provided by an embodiment of the present disclosure is described.

[0121] Step S601: receiving at least one machine message sent by the chat robot, and storing at least one machine message in a temporary message queue.

[0122] The chatbot can be implemented by relying on a large language model integrated in a service device (e.g., a server, a workbench, a mainframe computer, or other similar computing device), and the large language model can be a pre-trained neural network model that has general language knowledge, world knowledge, and expertise in various fields, and is stored in the model in the form of parameters. Specifically, the large language model can be a pre-trained autoregressive generative model of a Transformer architecture.

[0123] After receiving at least one machine message sent by the chat robot, the at least one machine message may be stored in the message temporary storage queue from the tail of the message temporary storage queue according to the sending order of the at least one machine message.

[0124] Step S602: when the temporary message storage queue is not empty and the rendering processing module is in a non-working state, extract the target machine message from the temporary message storage queue.

[0125] The target machine message is the machine message stored at the head of the message temporary storage queue.

[0126] For the specific description of step S602, please refer to the related description in the aforementioned step S101, which will not be repeated here.

[0127] Step S603, storing the target machine message at the end of the message rendering queue.

[0128] That is, in the embodiment of the present disclosure, the target machine message may be stored in the message rendering queue from the tail of the message rendering queue.

[0129] Step S604: Utilize the rendering processing module to render the target machine message stored at the end of the message rendering queue.

[0130] In an optional implementation, the “rendering the target machine message” in step S604 may include:

[0131] Step S604-1, disassemble the target machine message stored at the end of the message rendering queue to obtain at least one to-be-rendered part with a specific rendering order.

[0132] Each of the at least one to-be-rendered portion has a corresponding message category.

[0133] For the specific description of step S604-1, please refer to the relevant description in the aforementioned step S102, and specifically, please refer to the relevant description in the aforementioned step S302-1, which will not be repeated here.

[0134] Step S604-2: determining a target rendering portion from at least one portion to be rendered according to a specific rendering order.

[0135] For the specific description of step S604-2, please refer to the relevant description in the aforementioned step S102, and specifically, please refer to the relevant description in the aforementioned step S302-2, which will not be repeated here.

[0136] Step S604-3, determining whether the message category corresponding to the target rendering part is a text category.

[0137] In one example, the "message category" field in the target rendering part can be used to determine whether the message category corresponding to the target rendering part is a text category. For example, when the "message category" field is "type: 'text'", the message category corresponding to the target rendering part can be determined to be a text category; when the "message category" field is not "type: 'text'" (for example, "type: 'url'", "type: 'tag'", or "type: 'image'"), the message category corresponding to the target rendering part can be determined to be a non-text category.

[0138] In addition, in the embodiment of the present disclosure, when the message category corresponding to the target rendering part is a text category, step SS604-4 is executed; when the message category corresponding to the target rendering part is a non-text category, step SS604-5 is executed.

[0139] Step S604 - 4 , rendering the target rendering part in a word-by-word printing manner.

[0140] For the specific description of step S604-4, please refer to the relevant description in the aforementioned step S102, and specifically, please refer to the relevant description in the aforementioned step S302-3, which will not be repeated here.

[0141] Step S604-5: Render the target rendering part in a manner of overall printing.

[0142] For the specific description of step S604-5, please refer to the relevant description in the aforementioned step S102, and specifically, please refer to the relevant description in the aforementioned step S302-3, which will not be repeated here.

[0143] Step S605: Generate a consultation message in response to the user's input operation.

[0144] The input operation may be a keyboard input operation or a mouse click operation, or a touch input operation, or a voice input operation, which is not limited in the embodiments of the present disclosure.

[0145] Step S606, when the rendering processing module is in a non-working state, the rendering processing module is used to store the consultation message at the end of the message rendering queue, and the consultation message stored at the end of the message rendering queue is used as the target consultation message to render the target consultation message.

[0146] In the disclosed embodiment, after the consultation message is generated, the consultation message can be stored in the message temporary storage queue from the tail of the message rendering queue using the rendering processing module when the rendering processing module is in a non-working state, and the consultation message stored at the tail of the message rendering queue can be used as the target consultation message to render the target consultation message.

[0147] It should be noted that, in the embodiment of the present disclosure, the execution order of the rendering steps of the machine message (step S601, step S602, step S603 and step S604) and the rendering steps of the consultation message (step S605 and step S606) can be determined according to the message storage time and the message generation time. For example, if the message storage time is earlier than the message generation time, the rendering step of the machine message can be executed first, and then the rendering step of the consultation message can be executed; if the message storage time is later than the message generation time, the rendering step of the consultation message can be executed first, and then the rendering step of the machine message can be executed. Among them, the message storage time is the time to receive at least one machine message sent by the chat robot and store at least one machine message in the message temporary queue; the message generation time is the time to generate the consultation message in response to the user's input operation.

[0148] Hereinafter, in conjunction with FIG. 7 , a complete example will be used to assist in explaining the integrity process of a message rendering method provided by an embodiment of the present disclosure.

[0149] Please combine Fig. 7A, the terminal device has received the machine message 1 sent by the chat robot, and uses the message rendering method provided in the embodiment of the present disclosure to render the machine message 1 in the conversation interface, and obtains the display content corresponding to the machine message 1 as "Hello, do you want to consult about the popular car models in 2024?". Thereafter, the terminal device generates a consultation message 1 in response to the user's input operation, and uses the message rendering method provided in the embodiment of the present disclosure to render the consultation message 1 in the conversation interface, and obtains the display content corresponding to the consultation message 1 as "Yes!". After the rendering work for the consultation message 1 is completed, the global rendering state variable can be set to "0" to indicate that the rendering processing module is in a non-working state.

[0150] Next, the terminal device successively receives machine message 2 and machine message 3 sent by the chat robot. Among them, machine message 2 includes part 1 to be rendered, part 2 to be rendered, part 3 to be rendered, part 4 to be rendered, and part 5 to be rendered; machine message 3 includes part 6 to be rendered.

[0151] In this example, the part 1 to be rendered includes:

[0152] type: 'text',

[0153] text: 'At present, there are models such as XXX, YYY, and ZZZ that perform well in the automobile market in 2024. These models have their own characteristics and advantages, providing consumers with a wealth of choices.

[0154] ',

[0155] value:",

[0156] needtype:true

[0157] Among them, "type: 'text'" is used to represent that the message category of the part to be rendered 1 is a text category; "text: 'At present, there are XXX, YYY, ZZZ and other models that have performed well in the automobile market in 2024. These models have their own characteristics and advantages, providing consumers with a wealth of choices.'" is used to represent that the display content of the part to be rendered 1 is "At present, there are XXX, YYY, ZZZ and other models that have performed well in the automobile market in 2024. These models have their own characteristics and advantages, providing consumers with a wealth of choices."; "value: "" is used to represent that the true value of the part to be rendered 1 is empty; "needtype: true" is used to represent that the display mode of the part to be rendered 1 is word-by-word printing.

[0158] In this example, the part to be rendered 2 includes the URL body part and the key content of the page corresponding to the URL body part. The URL body part includes:

[0159] type: 'url',

[0160] text: 'Click here to enter the 2024 popular car model introduction page',

[0161] value: 'https: / / www.pcmi.com',

[0162] needtype:false

[0163] Among them, "type: 'url'" is used to characterize that the message category of part 2 to be rendered is the URL category; "text: 'Click here to enter the 2024 popular car model introduction page'" is used to characterize that the display content of part 2 to be rendered is "Click here to enter the 2024 popular car model introduction page"; "value: 'https: / / www.pcmi.com'" is used to characterize that the true value of part 2 to be rendered is https: / / www.pcmi.com, that is, when the user clicks on the display content "Click here to enter the 2024 popular car model introduction page", it will enter the 2024 popular car model introduction page based on https: / / www.pcmi.com; "needtype: false" is used to characterize that the display mode of part 2 to be rendered is overall printing.

[0164] That is, the final displayed content of the rendered URL body part is "Click here to enter the 2024 popular car model introduction page"; and the key content of the page corresponding to the URL body part can be the key content extracted from the 2024 popular car model introduction page, which can be text content, picture content, video content, etc., and the present disclosed embodiment does not limit this.

[0165] In this example, the part 3 to be rendered includes:

[0166] type: 'tag',

[0167] text: 'Here are the models I'm interested in',

[0168] value:",

[0169] needtype:false

[0170] Among them, "type: 'tag'" is used to indicate that the message category of the part 3 to be rendered is a tag category; "text: 'Here are the car models I'm interested in'" is used to indicate that the display content of the part 3 to be rendered is that there are car models I'm interested in, and it belongs to a tag; "value: "" is used to indicate that the true value of the part 3 to be rendered is empty; "needtype: false" is used to indicate that the display mode of the part 3 to be rendered is overall printing.

[0171] In this example, the part 4 to be rendered includes:

[0172] type: 'tag',

[0173] text: 'I want to know more about car models',

[0174] value:",

[0175] needtype:false

[0176] Among them, "type: 'tag'" is used to represent that the message category of the part 4 to be rendered is a tag category; "text: 'I want to know more about car models'" is used to represent that the display content of the part 4 to be rendered is "I want to know more about car models" and it belongs to a tag; "value: "" is used to represent that the true value of the part 4 to be rendered is empty; "needtype: false" is used to represent that the display mode of the part 4 to be rendered is overall printing.

[0177] In this example, the part 5 to be rendered includes:

[0178] type: 'image',

[0179] text: 'A picture named "WWW Automobile Club Promotional Picture"',

[0180] value: ' / data / images / promotions / WWW Automobile Club Promotional Picture.jpg',

[0181] needtype:false

[0182] Among them, "type: 'image'" is used to represent that the message category of the part to be rendered 5 is the picture category; "text: 'A picture named "WWW Automobile Club Promotion Picture"'" is used to represent that the display content of the part to be rendered 5 is a picture named "WWW Automobile Club Promotion Picture"; "value: ' / data / images / promotions / WWW Automobile Club Promotion Picture.jpg'" is used to represent that the true value of the part to be rendered 5 is " / data / images / promotions / WWW Automobile Club Promotion Picture.jpg", which is specifically used to represent that the display content of the part to be rendered 5 can be obtained through the storage path " / data / images / promotions / WWW Automobile Club Promotion Picture.jpg"; "needtype: false" is used to represent that the display mode of the part to be rendered 5 is overall printing.

[0183] In this example, the part to be rendered 6 includes:

[0184] type: 'text',

[0185] text: 'I am very happy to share these wonderful car model information with you, and hope they can add some inspiration to your car buying journey. ',

[0186] value:",

[0187] needtype:true

[0188] Among them, "type: 'text'" is used to indicate that the message category of the part 6 to be rendered is a text category; "text: 'It is a great pleasure to share these wonderful car model information with you, and I hope they can add some inspiration to your car buying journey.'" is used to indicate that the display content of the part 6 to be rendered is "It is a great pleasure to share these wonderful car model information with you, and I hope they can add some inspiration to your car buying journey."; "value: "" is used to indicate that the true value of the part 6 to be rendered is empty; "needtype: true" is used to indicate that the display mode of the part 6 to be rendered is verbatim printing.

[0189] Please combine Figure 7B After receiving the machine message 2 and the machine message 3 sent by the chat robot, the machine message 2 and the machine message 3 can be stored in the message temporary storage queue from the tail of the message temporary storage queue according to the sending order of the machine message 2 and the machine message 3 (that is, first send the machine message 2, then send the machine message 3). After that, it will be detected that the message temporary storage queue is not empty, and when the message temporary storage queue is not empty and the rendering processing module is in a non-working state, the machine message 2 is extracted from the message temporary storage queue as the target machine message, and then the target machine message is stored at the tail of the message rendering queue. After storing the target machine message in the message rendering queue, the global rendering state variable can be set to "1" to indicate that the rendering processing module is in a working state. After the global rendering state variable is set to "1", the target machine message stored at the end of the message rendering queue can be disassembled to obtain multiple to-be-rendered parts with a specific rendering order (i.e., to-be-rendered part 1, to-be-rendered part 2, to-be-rendered part 3, to-be-rendered part 4, and to-be-rendered part 5), and the target rendering part is determined from the multiple to-be-rendered parts according to the specific rendering order, and then the target rendering part is rendered based on the rendering mode corresponding to the message category corresponding to the target rendering part, so as to obtain the following: Figure 7C The display effect shown is shown. Among them, the specific rendering order of the multiple parts to be rendered can be the arrangement order of them in the target machine message.

[0190] After the rendering work for the target machine message is completed, the global rendering state variable can be set to "0" to indicate that the rendering processing module is in a non-working state. After the global rendering state variable is set to "0", it will be detected that the message temporary storage queue is not empty, and when the message temporary storage queue is not empty and the rendering processing module is in a non-working state, the machine message 3 is extracted from the message temporary storage queue as a new target machine message, and then the new target machine message is stored at the end of the message rendering queue. After the new target machine message is stored in the message rendering queue, the global rendering state variable can be set to "1" to indicate that the rendering processing module is in a working state. After the global rendering state variable is set to "1", the new target machine message stored at the end of the message rendering queue can be disassembled to obtain a part to be rendered (that is, part 6 to be rendered), and the part to be rendered is determined as the target rendering part, and then the target rendering part is rendered based on the rendering method corresponding to the message category corresponding to the target rendering part to obtain the following. Fig.7D The display effect shown.

[0191] After the rendering work for the new target machine message is completed, the global rendering state variable may be set to "0" to indicate that the rendering processing module is in a non-working state.

[0192] In addition, in this example, after the rendering work for machine message 2 and machine message 3 is completed, when the user clicks on the display content of the to-be-rendered part 4, that is, the label "I want to know more about car models", by mouse or touch, the terminal device can generate consulting message 2, that is, "I want to know more about car models" in response to the user's input operation. After the consulting message 4 is generated, the rendering processing module can be used to store the consulting message 4 in the message rendering queue from the end of the message rendering queue when the rendering processing module is in a non-working state, and the consulting message 4 stored at the end of the message rendering queue is used as the target consulting message to render the target consulting message to obtain the following. Fig. 7E The display effect shown.

[0193] Furthermore, please combine Figure 7F In this example, when it is detected that the human-computer interaction touch point is located in the first target area where the URL body part is located, or in the second target area where the key content of the page corresponding to the URL body part is located, the residence time of the human-computer interaction touch point can be recorded, and the waiting time threshold can be determined, so as to render the overall page content corresponding to the URL body part when the residence time is greater than or equal to the waiting time threshold. Among them, the waiting time threshold can be set according to actual application requirements, and the embodiments of the present disclosure do not limit this.

[0194] See also Figure 8, which is a scenario diagram of a message rendering method provided in an embodiment of the present disclosure.

[0195] As mentioned above, the message rendering method provided by the embodiment of the present disclosure is applied to an electronic device. The electronic device may be a terminal device. Here, the terminal device may be a conventional computer (desktop computer, laptop computer, etc.), a car computer, a tablet computer, a smart phone, a personal digital assistant, or other similar computing devices.

[0196] Electronic devices are used for:

[0197] When the message temporary storage queue is not empty and the rendering processing module is in a non-working state, extracting a target machine message from the message temporary storage queue; wherein the message temporary storage queue is used to store at least one machine message sent by the chat robot; the target machine message is the machine message stored at the head of the message temporary storage queue;

[0198] The target machine message is rendered using the rendering processing module.

[0199] The chatbot can be implemented by relying on a large language model integrated in a service device (e.g., a server, a workbench, a mainframe computer, or other similar computing device), and the large language model can be a pre-trained neural network model that has general language knowledge, world knowledge, and expertise in various fields, and is stored in the model in the form of parameters. Specifically, the large language model can be a pre-trained autoregressive generative model of a Transformer architecture.

[0200] It should be noted that in the embodiments of the present disclosure, Figure 8 The scene diagram shown is only illustrative and not restrictive. Those skilled in the art can Figure 8 Various obvious changes and / or substitutions are made to the examples, and the obtained technical solutions still fall within the scope of the disclosure of the embodiments of the present disclosure.

[0201] In order to better implement the message rendering method, the embodiment of the present disclosure also provides a message rendering device, which can be integrated in an electronic device. The electronic device can be a terminal device. Here, the terminal device can be a conventional computer (desktop computer, laptop computer, etc.), a car computer, a tablet computer, a smart phone, a personal digital assistant or other similar computing device. Fig. 9 The schematic structural block diagram shown illustrates a message rendering device 900 provided in the disclosed embodiment.

[0202] The message rendering device 900 comprises:

[0203] The message extraction unit 901 is used to extract the target machine message from the temporary message storage queue when the temporary message storage queue is not empty and the rendering processing module is in a non-working state; wherein the temporary message storage queue is used to store at least one machine message sent by the chat robot; the target machine message is the machine message stored at the head of the temporary message storage queue;

[0204] The first message rendering unit 902 is used to render the target machine message by using the rendering processing module.

[0205] In some optional implementations, the first message rendering unit 902 is used to:

[0206] The target machine message is disassembled to obtain at least one to-be-rendered part having a specific rendering order; wherein each to-be-rendered part in the at least one to-be-rendered part has a corresponding message category;

[0207] Determine a target rendering portion from at least one portion to be rendered according to a specific rendering order;

[0208] The target rendering part is rendered based on the rendering mode corresponding to the message category corresponding to the target rendering part.

[0209] In some optional implementations, the first message rendering unit 902 is used to:

[0210] When the message category corresponding to the target rendering part is a text category, the target rendering part is rendered in a word-by-word printing manner;

[0211] Alternatively, when the message category corresponding to the target rendering part is a non-text category, the target rendering part is rendered in a manner of overall printing.

[0212] In some optional implementations, the non-text category is one of a URL category, a tag category, and a picture category.

[0213] In some optional implementations, the message category corresponding to the target rendering part is a non-text category, and the non-text category is a URL category; the target rendering part includes a URL body part, and a page key content corresponding to the URL body part; the first message rendering unit 902 is used to:

[0214] Rendering the URL body in the first target area of ​​the conversation interface in a manner of overall printing;

[0215] In the conversation interface, determining a second target area related to the first target area;

[0216] According to the overall printing method, the key content of the page is rendered in the second target area.

[0217] In some optional implementations, the message rendering device 900 further includes a page rendering unit, which is used to:

[0218] When it is detected that the human-computer interaction touch point is located in the first target area or the second target area, the residence time of the human-computer interaction touch point is recorded;

[0219] Determine the waiting time threshold;

[0220] When the dwell time is greater than or equal to the waiting time threshold, the overall page content corresponding to the URL body is rendered.

[0221] In some optional implementations, the page rendering unit is used to:

[0222] Get the duration of the current session;

[0223] Calculate the percentage of the number of consultation messages in the current session to the total number of messages in the current session;

[0224] Based on the duration and the percentage value, a waiting time threshold is obtained.

[0225] In some optional implementations, the message display unit further includes a message transfer unit, which is used to:

[0226] Store the target machine message at the end of the message rendering queue;

[0227] Wherein, the first message rendering unit 902 is used for:

[0228] The target machine message stored at the end of the message rendering queue is disassembled to obtain at least one to-be-rendered part having a specific rendering order.

[0229] In some optional implementations, the message rendering device 900 further includes a second message rendering unit, configured to:

[0230] generating a consulting message in response to an input operation of a user;

[0231] When the rendering processing module is in a non-working state, the rendering processing module is used to store the consultation message at the end of the message rendering queue, and the consultation message stored at the end of the message rendering queue is used as the target consultation message to render the target consultation message.

[0232] In the embodiment of the present disclosure, the specific functions and examples of each unit included in the message rendering device 900 can refer to the relevant description of the corresponding steps in the aforementioned message rendering method embodiment, which will not be repeated here.

[0233] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0234] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, an autonomous driving vehicle, a readable storage medium, and a computer program product.

[0235] Fig.10 A schematic block diagram of an example electronic device 1000 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as vehicle-mounted computing devices, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0236] like Fig.10 As shown, the device 1000 includes a computing unit 1001, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1002 or a computer program loaded from a storage unit 1008 to a random access memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation of the device 1000 can also be stored. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0237] A number of components in the device 1000 are connected to the I / O interface 1005, including: an input unit 1006, such as a keyboard, a mouse, etc.; an output unit 1007, such as various types of renderers, speakers, etc.; a storage unit 1008, such as a disk, an optical disk, etc.; and a communication unit 1009, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1009 allows the device 1000 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0238] The computing unit 1001 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSP), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1001 performs the various methods and processes described above, such as the message rendering method. For example, in some embodiments, the message rendering method may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 1008. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1000 via the ROM 1002 and / or the communication unit 1009. When the computer program is loaded into the RAM 1003 and executed by the computing unit 1001, one or more steps in the message rendering method described above may be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured as the message rendering method in any other appropriate manner (eg, by means of firmware).

[0239] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0240] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0241] 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, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, 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 RAM, a ROM, an erasable programmable read-only memory (EPROM) or a 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.

[0242] To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having: a rendering device (e.g., a cathode ray tube (CRT) renderer or a liquid crystal display (LCD)) for rendering information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices are also used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0243] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN), and the Internet.

[0244] The computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0245] The embodiment of the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the message rendering method.

[0246] The embodiment of the present disclosure also provides a computer program product, including a computer program, which implements the message rendering method when executed by a processor.

[0247] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in the present disclosure can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and this document is not limited here. In addition, in the present disclosure, relational terms such as "first", "second", "third", etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. In addition, "multiple" in the present disclosure can be understood as at least two.

[0248] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A message rendering method, comprising: When the message temporary storage queue is not empty and the rendering processing module is in a non-working state, extracting a target machine message from the message temporary storage queue; wherein the message temporary storage queue is used to store at least one machine message sent by the chat robot; the target machine message is the machine message stored at the head of the message temporary storage queue; The target machine message is rendered using the rendering processing module.

2. The method according to claim 1, wherein: The rendering of the target machine message includes: Decomposing the target machine message to obtain at least one to-be-rendered portion having a specific rendering order; wherein each to-be-rendered portion in the at least one to-be-rendered portion has a corresponding message category; Determine a target rendering portion from the at least one portion to be rendered according to the specific rendering order; The target rendering part is rendered based on a rendering mode corresponding to a message category corresponding to the target rendering part.

3. The method according to claim 2, wherein: The rendering of the target rendering part based on the rendering mode corresponding to the message category corresponding to the target rendering part includes: When the message category corresponding to the target rendering part is a text category, rendering the target rendering part in a word-by-word printing manner; Alternatively, when the message category corresponding to the target rendering part is a non-text category, the target rendering part is rendered in a manner of overall printing.

4. The method according to claim 3, wherein: The non-text category is one of a resource locator category, a tag category, and a picture category.

5. The method according to claim 3 or 4, wherein: The message category corresponding to the target rendering part is a non-text category, and the non-text category is a resource locator category; the target rendering part includes a resource locator body part, and a page key content corresponding to the resource locator body part; The step of rendering the target rendering part in a manner of overall printing includes: Rendering the resource locator body part in a first target area in the conversation interface in a manner of overall printing; In the conversation interface, determining a second target area related to the first target area; The key content of the page is rendered in the second target area in an overall printing manner.

6. The method according to claim 5, further comprising: When it is detected that the human-computer interaction touch point is located in the first target area or the second target area, recording the residence time of the human-computer interaction touch point; Determine the waiting time threshold; When the dwell time is greater than or equal to the waiting time threshold, the entire page content corresponding to the resource locator body is rendered.

7. The method according to claim 6, wherein: The step of determining the waiting time threshold comprises: Get the duration of the current session; Calculate the percentage of the number of consultation messages in the current session to the total number of messages in the current session; The waiting time threshold is obtained based on the duration and the percentage value.

8. The method according to claim 2, further comprising: Storing the target machine message at the end of the message rendering queue; The step of disassembling the target machine message to obtain at least one to-be-rendered part having a specific rendering order includes: The target machine message stored at the tail of the message rendering queue is disassembled to obtain at least one to-be-rendered part having a specific rendering order.

9. The method according to claim 8, further comprising: generating a consulting message in response to an input operation of a user; When the rendering processing module is in a non-working state, the rendering processing module is used to store the consultation message at the end of the message rendering queue, and the consultation message stored at the end of the message rendering queue is used as the target consultation message to render the target consultation message.

10. A message rendering device, comprising: A message extraction unit, configured to extract a target machine message from the temporary message storage queue when the temporary message storage queue is not empty and the rendering processing module is in a non-working state; wherein the temporary message storage queue is used to store at least one machine message sent by the chat robot; and the target machine message is a machine message stored at the head of the temporary message storage queue; The first message rendering unit is used to render the target machine message using the rendering processing module.

11. The device according to claim 10, wherein: The first message rendering unit is used for: Decomposing the target machine message to obtain at least one to-be-rendered portion having a specific rendering order; wherein each to-be-rendered portion in the at least one to-be-rendered portion has a corresponding message category; Determine a target rendering portion from the at least one portion to be rendered according to the specific rendering order; The target rendering part is rendered based on a rendering mode corresponding to a message category corresponding to the target rendering part.

12. The device according to claim 11, wherein: The first message rendering unit is used for: When the message category corresponding to the target rendering part is a text category, rendering the target rendering part in a word-by-word printing manner; Alternatively, when the message category corresponding to the target rendering part is a non-text category, the target rendering part is rendered in a manner of overall printing.

13. The device according to claim 12, wherein: The non-text category is one of a resource locator category, a tag category, and a picture category.

14. The device according to claim 12 or 13, wherein: The message category corresponding to the target rendering part is a non-text category, and the non-text category is a resource locator category; the target rendering part includes a resource locator body part, and a page key content corresponding to the resource locator body part; The first message rendering unit is used for: Rendering the resource locator body part in a first target area in the conversation interface in a manner of overall printing; In the conversation interface, determining a second target area related to the first target area; The key content of the page is rendered in the second target area in an overall printing manner.

15. The apparatus according to claim 14, further comprising a page rendering unit, configured to: When it is detected that the human-computer interaction touch point is located in the first target area or the second target area, recording the residence time of the human-computer interaction touch point; Determine the waiting time threshold; When the dwell time is greater than or equal to the waiting time threshold, the entire page content corresponding to the resource locator body is rendered.

16. The device according to claim 15, wherein: The page rendering unit is used for: Get the duration of the current session; Calculate the percentage of the number of consultation messages in the current session to the total number of messages in the current session; The waiting time threshold is obtained based on the duration and the percentage value.

17. The apparatus according to claim 10, further comprising a message transfer unit, configured to: Storing the target machine message at the end of the message rendering queue; The first message rendering unit is used for: The target machine message stored at the tail of the message rendering queue is disassembled to obtain at least one to-be-rendered part having a specific rendering order.

18. The apparatus according to claim 17, further comprising a second message rendering unit, configured to: generating a consulting message in response to an input operation of a user; When the rendering processing module is in a non-working state, the rendering processing module is used to store the consultation message at the end of the message rendering queue, and the consultation message stored at the end of the message rendering queue is used as the target consultation message to render the target consultation message.

19. An electronic device comprising: at least one processor; a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the method according to any one of claims 1 to 9.

20. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 9.

21. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 9.

Images