Method and device for sending service information, method and device for receiving service information

Abstract

An embodiment of the present application provides a method and device for sending, and a method and device for receiving service information. The sending method includes: obtaining service information corresponding to a service product, wherein the service information is information generated by a server based on pre-acquired product characteristics of the service product, and the service information is used to interact with a service object through one or more preset virtual images to display the product characteristics of the service product to the service object; sending the service information to a second terminal, wherein the second terminal is a terminal used by the service object to obtain the product characteristics of the service product; and displaying interaction data between the service object and the virtual image on the first terminal, wherein the interaction data includes conversation content between the service object and the virtual image.

Description

Technical Field

[0001] The present application relates to the field of data interaction technology, and in particular to a method and device for sending, and a method and device for receiving service information. Background Art

[0002] With the development of technology and the iteration of people's behavioral habits, the way service providers provide services to service recipients is also changing accordingly, and the effects of different service methods will also be different accordingly.

[0003] The ways in which service providers provide services to service recipients often include offline and online. For offline services, a better interaction effect can be formed between the service provider and the service recipient, but it is inevitably subject to the time and space constraints of both the service provider and the service recipient; for online services, the service provider can conveniently provide corresponding services to the service recipients through the Internet, but in the service process, on the one hand, it is difficult to completely get rid of the time constraints, and on the other hand, the online service method greatly limits the interaction effect between the service provider and the service recipient, which in turn causes the actual experience of the service recipient to be unsatisfactory.

[0004] Regarding the problem of poor service experience for service recipients in related technologies, there is no reasonable solution in related technologies. Summary of the Invention

[0005] The embodiments of the present application provide a method and device for sending, and a method and device for receiving service information, so as to at least solve the problem of poor service experience of the service object in the related art.

[0006] In one embodiment of the present application, a method for sending service information is proposed, which is applied to a first terminal and includes: obtaining service information corresponding to a service product, wherein the service information is information generated by a server based on pre-acquired product characteristics of the service product, and the service information is used to interact with a service object through one or more preset virtual images to display the product characteristics of the service product to the service object; sending the service information to a second terminal, wherein the second terminal is a terminal used by the service object to obtain the product characteristics of the service product; and displaying interaction data between the service object and the virtual image on the first terminal, wherein the interaction data includes conversation content between the service object and the virtual image.

[0007] In one embodiment of the present application, a method for receiving service information is also proposed, which is applied to a second terminal, including: receiving service information sent by a first terminal, wherein the service information is information generated by a server based on product characteristics of a service product obtained in advance, and the service information is used to interact with a service object through one or more preset virtual images to display the product characteristics of the service product to the service object; obtaining the characteristics of the service product through the virtual image; and sending interaction data of the service object interacting with the virtual image through the second terminal to the first terminal, wherein the interaction data includes the conversation content between the service object and the virtual image.

[0008] In one embodiment of the present application, a method for sending service information is also proposed, which is applied to a server and includes: generating service information based on pre-acquired product characteristics of a service product, wherein the service information is used to interact with a service object through one or more preset virtual images to display the product characteristics of the service product to the service object; and sending the service information to a first terminal, wherein the first terminal is a terminal for sending the service information to the service object.

[0009] In one embodiment of the present application, a service information sending device is also proposed, which is arranged at a first terminal and includes: a first acquisition module, configured to obtain service information corresponding to a service product, wherein the service information is information generated by a server based on pre-acquired product characteristics of the service product, and the service information is used to interact with a service object through one or more preset virtual images to display the product characteristics of the service product to the service object; a first sending module, configured to send the service information to a second terminal, wherein the second terminal is a terminal used by the service object to obtain the product characteristics of the service product; a display module, configured to display interaction data between the service object and the virtual image on the first terminal, wherein the interaction data includes the conversation content between the service object and the virtual image.

[0010] In one embodiment of the present application, a device for receiving service information is also proposed, which is arranged at a second terminal and includes: a receiving module, configured to receive service information sent by a first terminal, wherein the service information is information generated by a server based on product characteristics of a service product obtained in advance, and the service information is used to interact with a service object through one or more preset virtual images to display the product characteristics of the service product to the service object; a second acquisition module, configured to obtain the characteristics of the service product through the virtual image; a second sending module, configured to send interaction data of the service object interacting with the virtual image through the second terminal to the first terminal, wherein the interaction data includes the conversation content between the service object and the virtual image.

[0011] In one embodiment of the present application, a device for sending service information is also proposed, which is arranged on a server and includes: a generation module, configured to generate service information based on the product characteristics of a service product obtained in advance, wherein the service information is used to interact with a service object through one or more preset virtual images to display the product characteristics of the service product to the service object; a third sending module, configured to send the service information to a first terminal, wherein the first terminal is the terminal for sending the service information to the service object.

[0012] In one embodiment of the present application, a computer-readable storage medium is further provided, wherein the storage medium stores a computer program, wherein the computer program is configured to execute the steps of any of the above method embodiments when run.

[0013] In one embodiment of the present application, an electronic device is further proposed, comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0014] Through the embodiment of the present application, the first terminal obtains the service information corresponding to the service product and sends it to the second terminal, wherein the service information is information generated by the server based on the product characteristics of the service product obtained in advance, and the service information is used to interact with the service object through one or more preset virtual images to show the product characteristics of the service product to the service object, and to display the interaction data between the service object and the virtual image on the first terminal. The problem of poor service experience of the service object in the related art is solved. Through the solution provided by the embodiment of the present application, the corresponding service can be provided to the user through the virtual image simulating the real person in the process of service provision. Moreover, the virtual image simulates the real person in the process of providing services to the user, and is not restricted by the time and space restrictions of the service provider. Thus, while maintaining the freedom of online services, it greatly improves the interactivity of the two parties in the service process, significantly improves the user experience of the service object, and allows the service provider to grasp the interaction process between the service object and the virtual image, facilitating further intervention and improvement. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0016] Figure 1 This is a hardware structure block diagram of a mobile terminal for a method for sending or receiving service information according to an embodiment of the present application;

[0017] Figure 2 This is a flow chart of an optional method for sending service information according to an embodiment of the present application;

[0018] Figure 3 This is a flow chart of an optional method for receiving service information according to an embodiment of the present application;

[0019] Figure 4 This is a flow chart of an optional method for sending service information according to an embodiment of the present application;

[0020] Figure 5 This is a structural block diagram of an optional device for sending service information according to an embodiment of the present application;

[0021] Figure 6 This is a structural block diagram of an optional device for receiving service information according to an embodiment of the present application;

[0022] Figure 7 This is a structural block diagram of an optional device for sending service information according to an embodiment of the present application;

[0023] Figure 8is a schematic diagram of an optional electronic device structure according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that, unless there is a conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0025] It should be noted that the terms "first", "second", etc. in the description and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0026] In an example application scenario of an embodiment of the present application, taking the field of e-commerce marketing as an example, the marketing methods of most e-commerce platforms for products have gradually evolved from early graphic marketing to video marketing, and further developed to today's live broadcast marketing. Since the live broadcast marketing method is compared with the traditional marketing provision method, on the one hand, it can make consumers more intuitive and comprehensive understanding of the marketing products, and on the other hand, it enhances the interaction between the marketer and the consumer. Therefore, at present, the live broadcast marketing method has become one of the mainstream methods for various e-commerce platforms or service providers to carry out product marketing. However, live broadcast marketing relies on the anchor as the main body of the live broadcast, and it is inevitably subject to the limitations of the anchor. For example, the anchor cannot carry out live broadcast marketing all day long, and consumers can only watch the live broadcast during the specified live broadcast period; for example, there are inevitably certain restrictions on the marketing products during the live broadcast marketing process, and the products that consumers expect to buy may not be within the scope of the live broadcast. Therefore, although live broadcast marketing can achieve better marketing results, the actual experience of consumers is not ideal.

[0027] In another example application scenario of the embodiment of the present application, taking the field of education and training as an example, for offline training, although the teacher can form a good interactivity with the trainees during the training process, it is also inevitably subject to time and space constraints. Online training or remote training is relatively flexible compared to offline training. It is mostly in the form of live broadcast or recorded broadcast, with the relevant teachers broadcasting the course live or pre-recording it for the trainees to watch and learn. However, when training is conducted in the form of live broadcast, on the one hand, it is inevitably subject to the teacher's time constraints, and the trainees cannot watch the course at a suitable time. On the other hand, the interaction during the live broadcast often depends on the teacher's unilateral behavior, and it is difficult for the trainees to express their questions to the teacher in a timely manner; and as for recorded broadcast, although it overcomes the time constraint, it further limits the interactivity between the trainees and the teacher.

[0028] In another example application scenario of the embodiments of the present application, taking the field of promotion and publicity of public information as an example, currently, the promotion and publicity of public information is mostly achieved by the government or public institutions through materials such as documents and web pages, as well as by convening promotion targets for centralized publicity. Similar to the problems existing in other examples, in the above-mentioned methods, the method of government or public institutions promoting through materials such as documents and web pages often causes the promotion targets to unilaterally accept the above-mentioned publicity, and cannot ensure that the promotion targets understand the promotion content, nor can it enable the promotion targets to conveniently and flexibly explain their own confusion; and the method of convening promotion targets for centralized publicity, although it can form a good interactivity between the organization and the promotion targets, still needs to be carried out at a fixed time and place.

[0029] In order to solve the above technical problems, the embodiments of the present application provide a method and device for sending service information, and a method and device for receiving service information. The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a method for sending or receiving service information in an embodiment of the present application. The mobile terminal here can be the first terminal or the second terminal corresponding to the embodiment of the present application. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown) a processor 102 (the processor 102 may include but is not limited to a microprocessor MCU or a programmable logic device FPGA and other processing devices) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0030] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for sending service information in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, implementing the above-mentioned method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories may be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0031] The transmission device 106 is used to receive or send data via a network. A specific example of the aforementioned network may include a wireless network provided by the mobile terminal's communications provider. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0032] The methods involved in the embodiments of the present application can be implemented through any form of application, for example, based on an APP installed by the user, a cloud-based mini-program that can be used without downloading and installing (such as WeChat mini-programs, Alipay mini-programs, quick applications, etc.), or an inherent program installed in a preset terminal; optionally, it can be presented in the form of WeChat mini-programs or other similar mini-programs. Specifically, the methods involved in the embodiments of the present application can include the following interactive aspects:

[0033] The server is used to create or generate corresponding service information based on the content information of the service product uploaded by the service provider, as well as store and manage the service information. The server can be a cloud server or a local server, preferably a cloud server.

[0034] The service provider terminal, that is, the corresponding first terminal in the embodiment of the present application, is used by the service provider to obtain service information of the service product from the server by logging in (the service information can also be sent to the service provider terminal through the server, which is not limited to this embodiment of the present application), and forward the service information to the service object terminal; the service provider terminal includes but is not limited to mobile phones, tablets, PCs, etc.

[0035] The service target terminal, i.e., the corresponding second terminal in the embodiments of this application, is used to receive and display service information so that the service provider can provide corresponding services to the service target. Service target devices include but are not limited to mobile phones, tablets, PCs, wearable devices, indoor large-screen terminals, outdoor large-screen terminals, etc.

[0036] It should be noted that the service scenarios in the embodiments of the present application are not limited to the aforementioned marketing, education and public information fields. Any service object that needs to be provided by one party to another party with information as a carrier can be used as the application scenario involved in the embodiments of the present application. Accordingly, the service provider is the provider of information, and the service object is the receiver of information. In the aforementioned e-commerce marketing field, the service provider is the producer or seller of a marketing product, and the service object is the consumer or user. For example, when the service product is a financial product, the service provider corresponds to the bank or financial institution that sells the financial product, and the service object is the user who expects to buy the financial product; when the service product is a certain book, the service provider corresponds to the online e-commerce or offline bookstore that sells the book, and the service object is the user who expects to buy the book; when the service product is a certain car, the service provider corresponds to the vehicle manufacturer or dealer, and the service object is the user who expects to buy the car. In the aforementioned education and training field, the service provider is the training institution or teacher, and the service object is the trainee. In the aforementioned promotion and publicity field of public information, the service provider is the government or public institution, and the service object is the collective or individual involved in the public information.

[0037] In addition to the above examples, any category of goods sold online or offline on a daily basis, legal advice opinions issued by legal advisory agencies to consultants, and medical guidance services provided by medical institutions to patients can all be used as application scenarios of the embodiments of this application. That is, the service information sending method and device, and the receiving method and device involved in the embodiments of this application are not limited to use in a certain scenario, and can be used as a general solution in any service scenario.

[0038] Figure 2 This is a flow chart of an optional method for sending service information according to an embodiment of the present application. Figure 2 As shown, an embodiment of the present application provides a method for sending service information, which is applied to a first terminal, including:

[0039] Step S202: Acquire service information corresponding to the service product, wherein the service information is information generated by the server based on pre-acquired product features of the service product, and is used to interact with the service recipient through one or more preset avatars to display the product features of the service product to the service recipient;

[0040] Step S204: sending the service information to the second terminal, wherein the second terminal is a terminal used by the service object to obtain product features of the service product;

[0041] Step S206: displaying the interaction data between the service object and the virtual image on the first terminal, wherein the interaction data includes the conversation content between the service object and the virtual image.

[0042] The first terminal in the embodiment of the present application is equivalent to the aforementioned service provider terminal, and the second terminal in the embodiment of the present application is equivalent to the aforementioned service object terminal. The server can be a local server set up locally, or a cloud server set up in the cloud, and the server is communicated with the first terminal and the second terminal respectively. The server can obtain the product characteristics of the service product in advance through the service provider or the service provider's associated entity, such as through the service provider actively sending the product characteristics of the corresponding service product, or by querying or downloading on the platform corresponding to the service provider to obtain the product characteristics of the corresponding service product; the embodiment of the present application does not limit the way in which the server obtains product characteristics.

[0043] The product features of the aforementioned service products are used to indicate any characteristics that can describe the service product, specifically characteristics that the service provider needs to or may display to the service recipient, or characteristics that the service recipient needs to or may consult with the service provider. The product features of the aforementioned service products are described below using exemplary embodiments and are not further elaborated here.

[0044] It should be noted that the display of the interaction data between the service object and the virtual image on the first terminal can be real-time display, that is, the interaction process between the service object and the virtual image is sent to the first terminal in real time in the form of a dialog box or text or display screen or voice narration, or it can be non-real-time display, for example, the interaction process is sorted out and sent to the first terminal at regular time intervals.

[0045] In an embodiment of the present application, a virtual image is used to indicate a 2D or 3D image displayed on a terminal. Specifically, the above-mentioned virtual image can be a virtual digital person presented in the image of a real person, or a virtual cartoon person presented in the image of a cartoon. The embodiment of the present application does not limit the category and image of the virtual image.

[0046] It should be noted that the virtual image corresponds to the service system (Service System), which refers to the system that controls and processes service information. The service system can be set locally on the first terminal or the second terminal, or in the cloud, and this is not limited in the present embodiment. Taking voice interaction as an example, the interaction process between the service object and the virtual image is as follows: the service object provides voice consultation on a certain issue, and the automatic speech recognition technology (Automatic Speech Recognition, referred to as ASR) module integrated in the service system performs semantic recognition of the audio corresponding to the voice consultation to determine the consultation text corresponding to the consultation content of the service object; the BOT (robot) module integrated in the service system stores question and answer rules. The BOT module can query the answer text corresponding to the consultation text in the preset question and answer rules. After determining the answer text, the answer text is converted into the corresponding answer audio through the text to speech (TTS) module integrated in the service system and played to the service object. In the above process, for different answer audio, the virtual image has different interactive actions, for example, the mouth / face shape corresponds to the pronunciation rules of the answer audio, and the body movements correspond to the content of the answer audio. In this way, the virtual image can present the service system's recognition and answers to the service object's consultation questions in an anthropomorphic way, thereby achieving interaction with the service object. The working methods of the above-mentioned ASR module, BOT module, and TTS module are all well known to those skilled in the art and will not be repeated here.

[0047] In one embodiment, the service information includes at least one of the following: image display information, speech information, and virtual image action information; wherein the image display information is used to indicate an image used to display at least part of the product features of the service product, the speech information is used to indicate the speech used to interact with the service object, and the virtual image action information is used to indicate the body movements and / or facial movements of the virtual image.

[0048] It should be noted that image display information can include static images or dynamic videos (i.e., continuous images). Speech information can include speech logic rules set for different application scenarios. Avatar action information can include body movements and / or facial movements when introducing a product, as well as body movements and / or facial movements used when responding to users that correspond to the speech information.

[0049] For example, in the financial management application field, the image display information can be a display screen or video generated based on the text description of the financial product and the corresponding image materials. It can include a display screen introducing the financial product or a display screen containing an avatar. The speech information can include automatically generating corresponding response words based on the investor's possible concerns, such as investment form, investment cycle, expected return, handling fees, risk level, etc., and coordinating the generation of the image display information. The avatar movement information can include the body movements and / or facial movements corresponding to the financial product introduction, as well as the body movements and / or facial movements used when responding to user inquiries about the financial product corresponding to the speech information.

[0050] In the field of education and training, image display information can be a display screen or video generated based on the text introduction of the training course and the corresponding image materials, and can include a display screen introducing the course or a display screen containing a virtual image. The speech information can include automatically generating corresponding response speech based on the possible concerns of trainees, such as the course outline, course content, teacher profile, course purpose or value, etc., and cooperating with the generation of image display information. The virtual image action information can include the corresponding body movements and / or facial movements when introducing the training course, as well as the body movements and / or facial movements corresponding to the speech information used when responding to users' inquiries about the training course.

[0051] In the field of public services, for example, if a government investment promotion department wants to promote and explain a certain investment promotion policy, the image display information can be a display screen or video generated based on the text description of the policy and the corresponding image materials, and can include a display screen introducing a course or a display screen containing a virtual image. The speech information can include automatically generating corresponding response speech based on the possible concerns of the enterprise, such as the applicable objects of the investment promotion policy, the effective and deadline time of the policy, the materials or procedures required by the enterprise, the policies and tax incentives that the enterprise can enjoy, etc., and cooperating with the generation of image display information. The virtual image action information can include the corresponding body movements and / or facial movements when promoting the policy, as well as the body movements and / or facial movements corresponding to the speech information used when responding to the enterprise's policy inquiries.

[0052] In one embodiment, sending the service information to the second terminal may be achieved by the following steps:

[0053] The media information including the service information is sent to the second terminal, so that the second terminal obtains the service information according to the media information.

[0054] It should be noted that the above media information depends on the form of the application. Taking a local application as an example, the media information is the local application link corresponding to the service information. Taking a mini program as an example, the media information is the mini program link corresponding to the service information.

[0055] In one embodiment, sending the media information including the service information to the second terminal may be achieved by the following steps:

[0056] Determine the matching degree between service products and service objects according to preset rules;

[0057] Determine the target service object that matches the service product according to the matching degree, wherein the target service object includes one or more service objects;

[0058] The media information is sent to the second terminal corresponding to the target service object, wherein the media information includes service information matching the target service object.

[0059] It should be noted that, in the above embodiment, determining the matching degree between the service product and the service object according to the preset rule indicates that the service provider determines the matching degree between the service product and the service object according to the service product and the service object.

[0060] In one example, the preset rules may be determined based on statistical rules. For example, the number of times a certain type of service product is used / purchased by a corresponding group of service objects is counted to determine the matching degree of the service object group to the type of service product based on the use / purchase frequency.

[0061] In another example, the preset rules can also be determined based on the characteristics of the service product and the characteristics of the service recipients. For example, the service product is a financial product, where Category A financial products have higher returns and correspondingly lower risks, while Category B financial products have lower returns and correspondingly higher risks. The service provider pre-profiling multiple service recipients to determine that Service Providers A and B prefer low-risk, low-return investments, while Service Providers C and D prefer high-return, high-risk investments. Based on this, the service provider can then, through preset group classification, target the service information corresponding to Category A financial product to Service Providers A and B, and target the service information corresponding to Category B financial product to Service Providers C and D.

[0062] It should be noted that in the embodiments of the present application, the above-mentioned process of determining the matching degree between the service product and the service object according to preset rules, and determining the target service object that matches the service product according to the matching degree can be automatically executed by a computer program stored in a computer-readable storage medium. For example, the tendency of the service object is determined based on the public information of the service object, and the matching degree between the service object and the service product is further calculated based on the product characteristics of the service product.

[0063] Since the method for sending service information in the embodiment of the present application can realize the specific sending of service information, through the method in the above embodiment, efficient service can be achieved for service objects matching a certain service product, thereby significantly improving the targeted nature of the service.

[0064] In one embodiment, after sending the service information to the second terminal, the method further includes:

[0065] Acquiring operation information input by the service object to the second terminal, wherein the operation information includes at least one of the following: option confirmation, text input, voice input, and image input;

[0066] In response to the operation information, image display information is provided to the service object, and the virtual image interacts with the service object according to the speech information and the virtual image action information.

[0067] In the aforementioned operation information, option confirmation may include providing the service recipient with pre-set options, displaying them on the second terminal, and allowing the service recipient to directly select them. Text input may include text input by the service recipient on a text input interface. Voice input may include audio input by the service recipient on a voice input interface. Image input may include using a camera on the second terminal to capture the service recipient's facial information or body movements for confirmation or matching the facial information with historical data in a database.

[0068] In one embodiment, after obtaining the operation information of the service object, the method further includes:

[0069] When it is determined that the service object requires intervention by the first terminal, synchronously displaying the image displayed on the second terminal on the first terminal;

[0070] A first annotation operation performed on the first terminal is synchronously displayed on the second terminal, and a second annotation operation performed on the second terminal is synchronously displayed on the first terminal.

[0071] In the embodiment of the present application, the first annotation operation is used to indicate an annotation operation performed by the service provider on the first terminal through touch or other means, for example, underlining or circling a certain text displayed on the first terminal. The second annotation operation is used to indicate an annotation operation performed by the service recipient on the second terminal through touch or other means, for example, underlining or circling a certain text displayed on the second terminal.

[0072] Generally speaking, the first annotation operation is a response to the second annotation operation. In one example, after the screen displayed on the second terminal is synchronously displayed on the first terminal, the service object has an ambiguous understanding of the meaning of paragraph A, so the service object circles paragraph A by touch on the second terminal to form a second annotation operation; at this time, the first terminal will synchronously display the second annotation operation, and the service provider will clarify the service object's ambiguity in understanding paragraph A based on the second annotation operation and the service object's voice, and explain it. In the above explanation process, the understanding of paragraph A involves paragraph B of the previous text, so the service provider circles paragraph B by touch on the first terminal to form the first annotation operation; at this time, the second terminal will synchronously display the first annotation operation to allow the service object to understand the meaning of paragraph A through the circled paragraph B.

[0073] In this way, while the service provider provides corresponding services to the service recipient, it can significantly improve the communication effect through the above-mentioned operational interactions to further improve the service quality.

[0074] In one embodiment, it is determined that the service object requires intervention by the first terminal in at least one of the following ways:

[0075] Obtaining an operation instruction from the service object, and determining, based on the operation instruction, that the service object requires intervention by the first terminal;

[0076] When detecting that the number of repeated operations issued by the service object exceeds a first preset threshold, determining that the service object requires intervention by the first terminal;

[0077] By matching historical interaction data with current interaction data, the service target's engagement intention rate is detected. If the engagement intention rate exceeds a second preset threshold, it is determined that the service target requires intervention by the first terminal. The engagement intention rate indicates the probability that the service target will become a potential customer after the first terminal's intervention. A potential customer can be a customer who intends to purchase a product, and the target service target can be a user who is suitable for pushing the current product.

[0078] It should be noted that the above-mentioned operation instruction for obtaining the service object means that the service object has actively selected the need for intervention by the first terminal; in this case, the service provider can intervene through the first terminal to answer the service object.

[0079] If the number of times the service subject detects repeated operations exceeds a first preset threshold, it indicates that the service subject has repeatedly performed the operation. In this case, the avatar does not provide the service subject's expected response to the service subject's inquiry or operation. In this case, it can be determined that the service subject is likely to require human intervention, and the service provider may intervene through the first terminal to provide the service subject with an answer. The first preset threshold can typically be set to three times.

[0080] In the above embodiment, the intervention intention rate can be calculated and determined based on historical interaction data. In one example, the historical interaction data for a service product includes 100 original conversation samples. Among these 100 original conversation samples, conversation samples in which the service recipient actively requested manual intervention or triggered manual intervention are recorded as manual intervention conversation samples. Therefore, there are 10 manual intervention conversation samples among the 100 conversation samples. Furthermore, among these 10 manual intervention conversation samples, 5 conversation samples meet preset high-intention event characteristics. Such high-intention events may include: manual intervention resolving the service recipient's special requirements, or the service recipient achieving an expected transaction through manual intervention. These 5 conversation samples are recorded as high-intention event conversation samples. Correspondingly, among the remaining 5 manual intervention conversation samples, 3 manual intervention conversation samples completed multiple interactions after medium manual intervention, and the service recipient terminated the interaction. These 3 manual intervention conversation samples are recorded as medium-intention event conversation samples. 2 manual intervention conversation samples completed one or two interactions after manual intervention, and the service recipient terminated the interaction. These 2 manual intervention conversation samples are recorded as low-intention event conversation samples.

[0081] Therefore, among the above 100 conversation samples, the intervention intention rate of high-intention event conversation samples is 100%, the intervention intention rate of medium-intention event conversation samples is 70%, and the intervention intention rate of low-intention event conversation samples is 50%. For the remaining original conversation samples, different intervention intention rates can also be assigned according to the number of interactions.

[0082] In the above embodiment, historical interaction data is matched with current interaction data, that is, whether the current interaction data is similar to the historical interaction data is detected. Specifically, the text similarity between the current interaction data of the service object and the historical interaction data can be calculated, such as the text similarity calculation based on cosine similarity, to determine the similarity between the current interaction data and each historical interaction data, and the historical interaction data with the highest similarity is selected as the reference object of the current interaction data. Based on the determination of the reference object of the current interaction data, the intervention intention rate of the reference object is the intervention intention rate of the current interaction data. For example, if the above high-intention event dialogue sample does not have the intervention intention rate of the current interaction data, then the intervention intention rate of the current interaction data is 100%.

[0083] In addition, in the process of calculating the intervention intention rate, if the intervention intention rate corresponding to the interaction data at the latest moment is greater than or equal to the intervention intention rate corresponding to the interaction data at the previous moment, it means that the service object's intention to the service product is increasing. At this time, the intervention intention rate corresponding to the interaction data at the latest moment and the second preset threshold are used for judgment.

[0084] If the engagement intention rate corresponding to the latest interaction data is lower than the engagement intention rate corresponding to the previous interaction data, further differentiation and judgment are required:

[0085] In the above situation, if the intervention intention rate corresponding to the interaction data at the latest moment is reduced by 30% (or other preset threshold) compared with the intervention intention rate corresponding to the interaction data at the previous moment, then the service object does not have much intention for the service product during the interaction process. At this time, the average of the above two intervention intention rates is taken as the determined intervention intention rate and the second preset threshold is used for judgment.

[0086] In the above scenario, if the reduction in the engagement intention rate corresponding to the most recent interaction data is less than 30% (or other preset thresholds) compared to the engagement intention rate corresponding to the previous interaction data, then although the service recipient's interest in the service product has declined during the interaction, it may be affected by other factors, and there is a high possibility that the interest will rebound. In this case, the product of the preset coefficient K1 and the average of the two engagement intention rates is used as the determined engagement intention rate and the second preset threshold for judgment. K1 can be between 1.2 and 1.4. Therefore, if the engagement intention rate calculated after introducing K1 is still less than the second preset threshold, it indicates that the service recipient's interest in the service product is minimal, and therefore no manual intervention is required. If the engagement intention rate calculated after introducing K1 is greater than the second preset threshold, manual intervention can be used to provide further manual services or marketing. This can facilitate service when the service recipient's interest is disturbed by external factors.

[0087] In the above example, the 100 original conversation samples correspond to different conversations with the same service object, or different conversations with different service objects. Therefore, in the above embodiment, when detecting the service object's involvement intention rate, on the one hand, the current interaction data can be matched with the historical interaction data according to the above process. On the other hand, the matching degree between the service object in the historical interaction data and the current service object can also be introduced to comprehensively determine the involvement intention rate. This is explained below:

[0088] The aforementioned embodiments describe a technical solution for providing service products tailored to the service recipients of a corresponding group based on the degree of match between the characteristics of the service product and the characteristics of the service recipients. Based on this, the inclination of the service recipients of each original conversation sample can be analyzed. Thus, in the aforementioned calculation of the intervention intention rate, if the determined intervention intention rate is obtained and the inclination of the current service recipient matches the inclination of the service recipient corresponding to the reference text, the determined intervention intention rate can be compared with a second preset threshold. If the current service recipient's inclination is likely to be higher in favor of the current service product than the inclination of the service recipient corresponding to the reference text, the determined intervention intention rate can be multiplied by a preset coefficient K2 and compared with the second preset threshold. K2 can be 1.2 to 1.4. If the current service recipient's inclination is likely to be lower in favor of the current service product than the inclination of the service recipient corresponding to the reference text, the determined intervention intention rate can be multiplied by a preset coefficient K3 and compared with the second preset threshold. K3 can be 0.7 to 0.9.

[0089] In this way, when calculating the intervention intention rate, we can comprehensively consider both the service object itself and its interaction data, so as to further improve the help of the intervention intention rate in promoting services.

[0090] In addition, the above process can be further implemented based on statistical rules.

[0091] In one embodiment, the method in the embodiment of the present application further includes:

[0092] Acquiring interaction process data between the service object and the avatar, wherein the interaction process data includes at least one of the following: access time of a service product, interaction rounds, hit counts, interaction data between the service object and the avatar, and number of views of the same service product by the service object;

[0093] Determine target service objects that match potential customers or service products based on interaction process data.

[0094] It should be noted that, in the above embodiment, the interaction process data is used to indicate the interaction records generated during the process of the service object receiving the service. In the above interaction process data, the access time of the service product is used to indicate the time when the service object uses the service information; the interaction round is used to indicate the round of text or voice interaction between the service object and the virtual image, wherein a complete answer to the service object's consultation is considered a round. The number of hits is used to indicate the number of times the virtual image correctly identifies and answers the service object's consultation during the interaction process. The interaction data between the service object and the virtual image is used to indicate the specific interaction content between the service object and the virtual image; the number of views of the service object on the same service product is used to indicate whether the service object has visited the same product multiple times and the specific number of visits.

[0095] The above interaction data can be used by the service provider to collect statistics on the personal characteristics of the service recipients on the one hand, and can also be used as statistical rules to implement the above calculation process of the intervention intention rate on the other hand. Specifically, statistics may be collected on the interaction process data of the service object in each original conversation sample to obtain records of interaction process data of the corresponding category. Thus, in the above-mentioned process of calculating the intervention intention rate, if the interaction process data of the current service object matches the interaction process data of the service object corresponding to the reference text, the determined intervention intention rate may be compared with a second preset threshold. If the interaction process data of the current service object is significantly increased compared with the interaction process data of the service object corresponding to the reference text, for example, at least two of the access time, interaction rounds, hit counts, and page views are greater than the interaction process data of the service object corresponding to the reference text, the determined intervention intention rate may be multiplied by a preset coefficient K2 and compared with the second preset threshold. K2 may be 1.2 to 1.4. If the interaction process data of the current service object is significantly decreased compared with the interaction process data of the service object corresponding to the reference text, for example, at least two of the access time, interaction rounds, hit counts, and page views are less than the interaction process data of the service object corresponding to the reference text, the determined intervention intention rate may be multiplied by a preset coefficient K3 and compared with the second preset threshold. K3 may be 0.7 to 0.9.

[0096] In this way, by acquiring the interactive process data of the service object, it can be used as a reverse calculation method for the intervention intention rate, which can serve as a basis for whether the service provider needs manual intervention.

[0097] In addition, in S206 above, while displaying the interaction data between the service object and the avatar on the first terminal, the service object's propensity to use / purchase the service can be further displayed on the first terminal based on the calculation conclusion of the above-mentioned intervention intention rate. For example, in the above example, when the interaction process data of the current service object is significantly smaller than the interaction process data of the service object corresponding to the reference text, if the determined intervention intention rate multiplied by the preset coefficient K3 is greater than the second preset threshold, it means that the service object has a greater propensity to use / purchase the service, but is still in the hesitation stage. At this time, the user's intention can be displayed to the service provider at the first terminal to help the service provider provide targeted services based on the service object's psychological state after manual intervention. This method can be applied to the calculation examples of each intervention intention rate in the above examples and will not be repeated here.

[0098] Through the solution provided by the embodiments of the present application, whether it is the interaction between financial product providers and users in the financial field, the interaction between training course providers and trainees in the education field, or the interaction between policy propagandists and audiences in the public service field, or any other field to which the solution provided by the embodiments of the present application can be applied, in the process of service provision, corresponding services are provided to users through virtual images simulating real people, and the above-mentioned virtual images simulating real people in the process of providing services to users are not restricted by the time and space constraints of the service provider, thereby greatly improving the interactivity of the two service parties in the service process while maintaining the freedom of online services, significantly improving the user experience of the service recipients, and allowing the service provider to grasp the interaction process between the service recipients and the virtual images, facilitating further intervention and improvement.

[0099] Figure 3 This is a flow chart of an optional method for receiving service information according to an embodiment of the present application. Figure 3 As shown, an embodiment of the present application provides a method for receiving service information, which is applied to a second terminal, including:

[0100] Step S302: receiving service information sent by the first terminal, wherein the service information is information generated by the server based on pre-acquired product features of the service product, and the service information is used to interact with the service recipient through one or more preset virtual images to display the product features of the service product to the service recipient;

[0101] Step S304, obtaining characteristics of the service product through the virtual image;

[0102] Step S306 : sending the interaction data of the service object interacting with the virtual image through the second terminal to the first terminal, wherein the interaction data includes the conversation content between the service object and the virtual image.

[0103] In one embodiment, the service information includes at least one of the following: image display information, speech information, and virtual image action information; wherein the image display information is used to indicate an image used to display at least part of the product features of the service product, the speech information is used to indicate the speech used to interact with the service object, and the virtual image action information is used to indicate the body movements and / or facial movements of the virtual image.

[0104] In one embodiment, receiving the service information sent by the first terminal may be achieved by the following steps:

[0105] receiving media information including the service information sent by the first terminal;

[0106] The service information is acquired according to the medium information.

[0107] In one embodiment, after receiving the service information sent by the first terminal, the method further includes:

[0108] Get the operation information input by the service object;

[0109] Sending operation information to the first terminal, wherein the operation information includes at least one of the following: option confirmation, text input, voice input, and image input;

[0110] Obtain a display screen corresponding to the operation information and an execution instruction of the virtual object generated by the first terminal, wherein the execution instruction of the virtual object is used to instruct the virtual image to interact with the service object according to the speech information and the virtual image action information.

[0111] In one embodiment, after obtaining the operation information input by the service object, the method further includes:

[0112] When it is determined that the service object requires intervention by the first terminal, synchronously sending the picture displayed on the second terminal to the first terminal;

[0113] The first annotation operation performed on the first terminal is synchronously displayed on the second terminal, and the first annotation operation performed on the first terminal is synchronously displayed on the second terminal.

[0114] In one embodiment, it is determined that the service object requires intervention by the first terminal in at least one of the following ways:

[0115] Obtaining an operation instruction from the service object, and determining, based on the operation instruction, that the service object requires intervention by the first terminal;

[0116] When detecting that the number of repeated operations issued by the service object exceeds a first preset threshold, determining that the service object requires intervention by the first terminal;

[0117] By matching historical interaction data with current interaction data, the intervention intention rate of the service object is detected. When the intervention intention rate exceeds a second preset threshold, it is determined that the service object requires intervention by the first terminal, wherein the intervention intention rate is used to indicate the probability that the service object will become an intended customer after the first terminal intervenes.

[0118] In one embodiment, the method in the embodiment of the present application further includes:

[0119] Obtaining interaction process data between the service object and the avatar, wherein the interaction process data includes at least one of the following: access time of the service product, interaction rounds, number of hits, interaction data between the service object and the avatar, and number of views of the service object on the same service product;

[0120] The interaction process data is sent to the second terminal, so that the second terminal determines the intended customer or the target service object that matches the service product according to the interaction process data.

[0121] Figure 4 This is a flow chart of an optional method for sending service information according to an embodiment of the present application. Figure 4 As shown, according to another embodiment of the present application, a method for sending service information is also provided, which is applied to a server and includes:

[0122] Step S402: generating service information based on the pre-acquired product features of the service product, wherein the service information is used to interact with the service recipient through one or more preset virtual images to present the product features of the service product to the service recipient;

[0123] Step S404: Send service information to the first terminal, where the first terminal is a terminal that sends service information to the service object.

[0124] In one embodiment, the service information includes at least one of the following: image display information, speech information, and avatar action information;

[0125] Among them, the image display information is used to indicate the image used to display at least part of the product features of the service product, the speech information is used to indicate the speech used to interact with the service object, and the virtual image action information is used to indicate the body movements and / or facial movements of the virtual image.

[0126] In one embodiment, the service information also includes:

[0127] Area division information of the display interface, wherein the display interface includes at least a first area and a second area, the first area is used to display the content of the service product through an image screen, and the second area is used to display the actions of the virtual image, and the area division information is used to indicate the positional relationship between the first area and the second area in the display interface.

[0128] The first area and the second area can be set up and down, left and right, or superimposed on the display interface, or set with a translucent effect, or displayed through a large and a small display window. The embodiment of the present application does not limit this.

[0129] In one embodiment, generating service information based on pre-acquired product features of a service product includes:

[0130] Generate virtual image action information based on image display information and / or speech information, wherein the virtual image action information at least includes: the action of the virtual image when displaying the image corresponding to the image display information, and / or the action of the virtual image when interacting with the service object according to the speech information.

[0131] In one embodiment, generating avatar action information based on image display information and speech information includes:

[0132] Selecting a first action module corresponding to the image display information from a preset avatar action database according to the image display information, wherein the first action module is used to indicate an action of the avatar when displaying the image corresponding to the image display information;

[0133] Selecting a second action module corresponding to the speech information from the virtual image action database according to the speech information, the second action module is used to indicate the action of the virtual image when interacting with the service object according to the speech information;

[0134] Determining avatar action information through the first action module and / or the second action module;

[0135] The avatar action database includes a plurality of preset action modules, wherein each action module corresponds to a body movement and / or facial movement of a avatar.

[0136] It should be noted that the above-mentioned avatar action database can be established in advance, and the avatar action database includes: different avatar action modules, namely the first action module and the second action module in the above-mentioned embodiment.

[0137] The virtual image action module corresponding to the first action module respectively indicates the actions corresponding to the virtual image under different image display information; for example, if the content of the image display information is the title page of a book, then the virtual image action module corresponding to the image display information is the action of opening the book; if the content of the image display information is the end of a book, then the virtual image action module corresponding to the image display information is the action of closing the book.

[0138] The virtual image action module corresponding to the second action module respectively indicates the actions corresponding to the virtual image under different speech information; for example, if the content of the speech information is "Welcome to pay attention to this product", then the virtual image action module corresponding to the speech information is the body movement of the welcome gesture and the lip movement of "Welcome to pay attention to this product"; if the content of the speech information is "Thank you for your browsing", then the virtual image action module corresponding to the speech information is the body movement of waving goodbye and the lip movement of "Thank you for your browsing".

[0139] The avatar action modules corresponding to the first action module / second action module can be produced based on common image content and speech to form the avatar action database. For those skilled in the art, the generation of avatar corresponding actions is well known and will not be repeated here.

[0140] In one embodiment, selecting a second action module corresponding to the speech information from the avatar action database according to the speech information includes:

[0141] Acquiring voice data input by the service object through a second terminal, wherein the voice data includes real-time voice data and / or non-real-time voice data, and the second terminal is a terminal used by the service object to obtain product features of the service product;

[0142] Selecting a target second action module corresponding to the voice data from the avatar action database according to the voice data and the speech information;

[0143] Push the target second action module to the second terminal.

[0144] In one embodiment, before pushing the target second action module to the second terminal, the method further includes:

[0145] The second action module in the avatar action database is set on a content delivery network (CDN) node, wherein each node corresponds to a uniform resource locator URL address.

[0146] It should be noted that, in the above embodiment, the corresponding multiple second action modules in the virtual image action database can be respectively set on a corresponding CDN node, and the corresponding URL address of the CDN node corresponds to the second action module.

[0147] In one embodiment, pushing the target second action module to the second terminal includes:

[0148] After selecting the target second action module corresponding to the voice data, the target URL address corresponding to the CDN node where the target second action module is located is sent to the second terminal to instruct the second terminal to obtain the target second action module through the target URL address.

[0149] The following describes the process of pushing the target second action module to the second terminal in an exemplary manner in combination with the working mode of the aforementioned service system:

[0150] In one example, the service system utilizes a non-real-time voice function. In this example, a service recipient provides voice consultation regarding a specific question. The system's integrated ASR module performs semantic recognition on the audio corresponding to the voice consultation to determine the corresponding consultation text. The system's integrated BOT module stores question-and-answer rules, which it then searches for the corresponding answer text within the pre-set Q&A rules. Once the answer text is determined, the target second action module corresponding to the answer text is identified within the avatar action database.

[0151] The service system sends the target URL address corresponding to the above-mentioned target second action module to the second terminal, and the second terminal can automatically download the target second action module from the corresponding CDN node to the second terminal through the target URL address, so that when the service system converts the answer text into the corresponding answer audio through the TTS module integrated in the service system and plays it to the service object, the virtual image can interact with the service object according to the target second action module.

[0152] Compared to the related art solutions that require real-time rendering of the virtual image required for interaction with the service object locally or on the service side before streaming, the technical solution in the above embodiment can significantly reduce the possible latency and hardware costs. After testing, the technical solution in the above embodiment can actually reduce the latency by 10 to 20ms compared to the related art. Because the services corresponding to the service information sending method in the embodiments of the present application often have extremely high real-time requirements, the above embodiment can significantly improve the user experience when providing services to the service object.

[0153] In one embodiment, sending service information to the first terminal includes:

[0154] In response to a login request from a first account, sending service information of a service product corresponding to the first account to the first terminal, wherein the first account is an account logged in on the first terminal, and the first account has a corresponding relationship with one or more service products; and / or,

[0155] The media information including the service information is sent to the first terminal, so that the first terminal obtains the service information according to the media information.

[0156] In one embodiment, the service user enters operational information on the second terminal, which is then parsed by the server and relayed to the first terminal. The server receives instructions from the first terminal and provides the second terminal with corresponding display images or speech information. The server can also send the interaction data between the second terminal and the avatar to the first terminal for display in real time.

[0157] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0158] Regarding the interaction process in the embodiment of the present application, it can be achieved through the following steps.

[0159] S1: The server receives content information of a service product uploaded by a service provider. The content information includes the following:

[0160] A. Textual description of the service product; B. Image material corresponding to each textual description of the service product.

[0161] Specifically, a textual description of a service product provides a detailed introduction to the service product, including any aspects of the service recipient that might be of interest. For example, if the service product is a book, the textual description provided by the service provider should include the book's introduction, price, author, and author's biography. If the service product is a course, the textual description provided by the service provider should include the course's content, instructor, instructor's biography, and the course's purpose or value. Graphics correspond to textual descriptions, meaning they present the textual description through images.

[0162] It should be noted that the text introduction and / or image material is only a conventional example of the embodiment of the present application and is not a necessary object that the service provider needs to upload. The content information can provide a detailed introduction to the service product and is not limited to any form of information carrier.

[0163] S2: The server generates corresponding service information based on the content information uploaded in S1. The service information may include the following:

[0164] A. Image / video information; B. Speech information; C. Action information of the digital human (equivalent to the aforementioned virtual image).

[0165] In the aforementioned S2, the image / video information in the service information indicates the presentation of the service product via images / videos. During the generation of the image / video information, if the image material in S1 can already effectively present a certain aspect of the service product, the image material in S1 can be directly used as the image information. If the image material in S1 does not provide an ideal presentation effect, or if the content information in S1 does not include an image material, the corresponding image / video information can be manually designed or automatically generated based on a preset image / video template.

[0166] The speech information indicates the speech used during voice interaction with the service recipient. For example, if the service recipient inputs "How much is the price?" via voice, the corresponding speech response is "The price is 100 yuan." The response to the service recipient's input is the speech information. During the generation of speech information, the service recipient's input can be manually set or captured through the internet, so as to list as many possible inputs as possible for a particular point of interest. For the corresponding response, the corresponding response speech can be manually or automatically generated based on the content information in S1.

[0167] The action information of the digital human is used to indicate the digital human portion of the on-screen software in the embodiments of this application. The digital human is one of the core components that distinguishes the on-screen software involved in the embodiments of this application from most other service provision methods. The digital human is a virtual character image that, during use by the service recipient, can generate corresponding actions in response to the service recipient's operations or voice input. The above-mentioned speech information is also output in the form of the digital human speaking. On the page consisting of service information, the area where the digital human is located can be defined as the first area, and the area where the image / video information is located can be positioned as the second area. In one example, the first area and the second area can be displayed in a vertical or horizontal arrangement on the terminal page, that is, the digital human and the image / video information are displayed separately on the page. In another example, the first area can be displayed overlapping the second area, that is, the digital human is placed in a preset manner within the image / video information. The embodiments of this application do not limit the display or arrangement position of the digital human.

[0168] During the process of generating the digital human's motion information, a database can be pre-established. This database stores the motion modules corresponding to the digital human using different motions, as well as the corresponding relationships between different motion modules and response dialogues / user operations. Based on the response dialogues set in the aforementioned dialogue information and the possible operations that the user may perform on the product, the corresponding motion module can be selected from the database based on the corresponding relationships. The different motion modules together constitute the digital human's motion information.

[0169] It should be noted that the actual actions of the digital human in the above-mentioned different action modules are closely related to the corresponding reply words / user operations; specifically, after clarifying a certain reply wording, the digital human's movement changes, including its lips, expressions, and body postures, can be adjusted according to the possible actions of a real person when expressing the content of the wording, so that when the digital human replies, the changes in its lips, expressions, and body postures all correspond to the reply words, so as to form an interactive feeling close to that of a real person.

[0170] It should be noted that the above-mentioned rapid generation of digital human action information based on the correspondence between different action modules and reply words / user operations in the database is only a preferred example of the embodiment of this application. During actual operation, it is also possible to choose to adjust the digital human's actions in real time according to the reply words in the background during the service object's use of the product.

[0171] S3, the server uploads the service information in S2 to the server so that the service provider terminal can obtain the service information corresponding to the service product when logging into the server. After the service provider terminal obtains the service information corresponding to a service product, it can send the service information to the service recipient terminal.

[0172] After the server uploads the service information in S2 to the server, an account can be assigned to the corresponding service provider. After the person logs in to the server through the service provider terminal account, he can browse the service information corresponding to each service product under the person's account, which is the process of obtaining the service information corresponding to the service product in S3.

[0173] After browsing the service information corresponding to each service product under their account, service providers can select the corresponding target service recipient based on the service product and then send the service information of a particular service product to the corresponding service recipient or group of service recipients. Specifically, this can be done by sending a link to the service information of a particular service product in the form of a QR code to the corresponding service recipient or group of service recipients. It should be noted that this method of sending can also be used in the form of an electronic card or poster.

[0174] It should be noted that the way in which the service provider obtains service information in the above S3 is only an optional example of an embodiment of the present application. During actual operation, the server can also directly send the service information of a certain service product to the corresponding service provider terminal, etc.

[0175] In addition, the same person's account can contain service information corresponding to multiple service products. In addition to the aforementioned sharing operations, the person can manage multiple service products accordingly under the account.

[0176] S4, after receiving the service information, the service object terminal can display the service information in the service object terminal.

[0177] After receiving the service information, the service recipient can open the service information on the service recipient terminal to enter the page corresponding to the service product. On this page, the digital human will provide corresponding services to the service recipient based on the service product through voice interaction with the service recipient and presentation of corresponding image / video information, and answer any questions that the service recipient may have. If necessary, it can also switch to the service provider for manual communication; based on this, the service provider can provide corresponding services to the service recipient.

[0178] During the communication process between the service recipient and the digital human, the service recipient's voice input is first converted into text using Automatic Speech Recognition (ASR) technology. This text is then analyzed using Natural Language Processing (NLP) technology. The recognition results are compared with the previously set verbal information to determine the corresponding response verbal information. Alternatively, Spoken Language Understanding (SLU) technology can be used to directly identify the service recipient's intent from their voice and determine the corresponding verbal information. Once the verbal information is determined, the digital human can respond to the service recipient via voice. The digital human's verbal responses can also be anthropomorphized. Specifically, when the digital human converts the text content of a given verbal response into the corresponding verbal output, a text-to-speech (TTS) neural network model can be pre-trained based on real-life speech sample data. This model enables the digital human's speech to resemble that of a real person, further enhancing the interactive experience between the digital human and the user.

[0179] S5. When the service object terminal displays service information, the service object can ask questions and communicate with the digital human through touch or voice input, and the digital human will interact with the service object in response to the service object's input. During the interaction between the service object and the digital human, the service provider terminal presents the dialogue between the service object and the digital human in the form of a dialogue to facilitate the service provider to understand the service object's intention.

[0180] During the interaction between the service recipient and the digital human, ASR technology can be used to convert the service recipient's and the digital human's speech into text (since the digital human's response script is pre-generated by the server, its text content can also be directly obtained). The converted text is then displayed on the service provider's terminal in the form of a conversation. Therefore, while the service recipient's terminal displays the service product to the service recipient, the service provider's terminal always works in sync with the service recipient's terminal, displaying the conversation and communication records between the service recipient and the digital human to the service provider, making it easier for the service provider to understand the service recipient's intentions.

[0181] S6. If the service recipient requires manual intervention, the service provider's terminal responds to the service recipient's request and initiates a voice call with the service recipient's terminal, allowing the service provider to address the service recipient's needs through the voice call. During the voice call, the service recipient and / or the service provider can make annotations on their respective terminal interfaces, and the annotations will be displayed simultaneously on both terminals.

[0182] In some cases, the digital human, following the pre-set script, cannot ideally address the service recipient's needs. In such cases, the service provider may intervene manually. In one example, the service recipient can proactively select the manual intervention option to send a request for manual intervention to the service provider's terminal. In another example, the system can detect whether the service recipient's actions meet pre-set conditions. For example, if the service recipient repeats the same question to the digital human three times, the system will determine that the service recipient requires manual intervention and send a request for manual intervention to the service provider's terminal. In another example, the system can also detect the service recipient's intervention intention rate and, if the intervention intention rate exceeds a pre-set threshold, send a request for manual intervention to the service provider's terminal.

[0183] After receiving the manual intervention request, the service provider terminal can intervene in the marketing process of the service object through voice dialogue, and the service provider can directly answer or communicate the needs of the service object.

[0184] During a voice call between a service recipient and a service provider, the service recipient's terminal is displayed on the same screen as the service provider's terminal, i.e., the page content displayed on the service recipient's terminal is the page content currently displayed on the service provider's terminal. At the same time, during the above communication process, both parties need to mark the relevant service information displayed in the interface to assist in communication. For example, during the communication between the service provider and the service recipient, the service provider wishes to emphasize the promotional discount for a certain book, so the discount-related information is circled and marked on the service provider's terminal by touch. In this case, the discount-related information on the service recipient's terminal can also be circled and marked. Conversely, the annotations made by the service recipient on the service recipient's terminal will also be displayed on the service provider's terminal.

[0185] In addition, the service provider can also actively intervene to enable voice calls.

[0186] S7, during the interaction between the service object in S5 and the digital human, the background can record the communication record of the service object and display it on the service provider terminal so that the service provider can make corresponding decisions.

[0187] The above communication records may specifically include: product access time, interaction rounds, number of hits, specific interaction information between the service object and the digital human, and the number of times the service object browses the same product, etc.

[0188] The aforementioned product access time refers to the time from when the service recipient opens the service information corresponding to the service product to when they actively close it or exit by timeout. The aforementioned interaction rounds indicate the number of times the digital human fully elaborates on a particular point of interest. A higher number of rounds indicates a longer interaction time between the customer and the digital human. The aforementioned hit count indicates the number of times the digital human responds to the service recipient's questions. A higher number indicates a lower probability that the digital human will fail to recognize the service recipient's keywords.

[0189] Based on these communication records, the service provider's terminal can automatically generate a user's interest in a particular service product. For example, thresholds can be set for product access time, interaction rounds, and hit count. If at least one of these three is greater than the first threshold, the user is defined as having high interest. If at least one of these three is greater than the second threshold and less than the first threshold, the user is defined as having medium interest. If all three are less than the second threshold, the user is defined as having low interest. This helps the service provider further determine the target audience for the service product, allowing them to improve service information or adjust the target audience.

[0190] It should be noted that the above communication records are only examples. Depending on the application scenario, other different records can also be selected for decision-making.

[0191] According to another aspect of the embodiments of the present application, a device for sending service information for implementing the above-mentioned method for sending service information is also provided. The device is used to implement the above-mentioned embodiments and preferred embodiments, and the details that have been described will not be repeated here. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated. Figure 5 is a structural block diagram of an optional device for sending service information according to an embodiment of the present application, such as Figure 5 As shown, the device is provided at the first terminal and includes:

[0192] A first acquisition module 502 is configured to acquire service information corresponding to a service product, wherein the service information is information generated by the server based on pre-acquired product features of the service product, and the service information is used to interact with the service recipient through one or more preset virtual images to display the product features of the service product to the service recipient;

[0193] A first sending module 504 is configured to send service information to a second terminal, wherein the second terminal is a terminal used by the service object to obtain product features of the service product;

[0194] The display module 506 is configured to display the interaction data between the service object and the virtual image on the first terminal, wherein the interaction data includes the conversation content between the service object and the virtual image.

[0195] Figure 6 is a structural block diagram of an optional device for receiving service information according to an embodiment of the present application, such as Figure 6 As shown, the device is provided at the second terminal and includes:

[0196] Receiving module 602 is configured to receive service information sent by the first terminal, wherein the service information is information generated by the server based on pre-acquired product features of the service product, and the service information is used to interact with the service recipient through one or more preset virtual images to display the product features of the service product to the service recipient;

[0197] The second acquisition module 604 is configured to acquire the characteristics of the service product through the virtual image;

[0198] The second sending module 606 is configured to send the interaction data of the service object interacting with the virtual image through the second terminal to the first terminal, wherein the interaction data includes the conversation content between the service object and the virtual image.

[0199] Figure 7 is a structural block diagram of an optional device for sending service information according to an embodiment of the present application, such as Figure 7 As shown, the device is set on the server and includes:

[0200] A generating module 702 is configured to generate service information based on the pre-acquired product features of the service product, wherein the service information is used to interact with the service object through one or more preset virtual images to display the product features of the service product to the service object;

[0201] The third sending module 704 is configured to send service information to the first terminal, wherein the first terminal is a terminal that sends service information to a service target.

[0202] The embodiments of the present application illustrate specific application scenarios of the embodiments of the present application through the following exemplary embodiments, but are not intended to limit the application scenarios of the embodiments of the present application.

[0203] Exemplary embodiment 1

[0204] In this exemplary embodiment, a financial institution as a service provider wishes to market a certain financial product as an example for explanation. The service objects in this exemplary embodiment are investors who wish to purchase the financial product.

[0205] S1: The server receives the content information of the financial product uploaded by the financial institution. The content information includes the following:

[0206] A. Textual introduction to the financial product; B. Image material corresponding to each textual introduction of the financial product.

[0207] The text description of the aforementioned financial products shall include, but not be limited to, the investment form, investment period, expected returns, handling fees, risk level, etc. of the financial products, as well as any other relevant information required to be disclosed to investors in accordance with relevant laws and regulations. Any of the above text descriptions may be presented with corresponding image materials.

[0208] S2: The server generates corresponding financial product information based on the content information uploaded in S1. The financial product information may include the following:

[0209] A. Image / video information; B. Speech information; C. Digital human action information;

[0210] The above-mentioned image / video information may be directly generated based on the image material in S1, or may be manually designed, or the corresponding image / video information may be automatically generated according to a preset image / video template.

[0211] During the process of generating the above-mentioned speech information, the possible concerns of investors can be determined first, such as the form of investment, investment cycle, expected return, handling fees, and risk level; taking the investment cycle as an example, the possible voice inputs of investors include: how long is the cycle, how long is the investment cycle, how long is required to invest, how long it takes to redeem, etc., through manual settings or Internet crawling, all possible inputs of investors for the above-mentioned concerns can be listed as much as possible; accordingly, the specific time of the investment cycle in S1 can be combined to manually or automatically generate corresponding reply speech about the investment cycle.

[0212] After determining the response words, the action modules corresponding to each response word can be searched in a pre-established database based on the response words, and the action information of the digital human that matches each response word can be generated. In this exemplary embodiment, the first area where the digital human is located and the second area where the image / video information is located are arranged in an upper and lower arrangement.

[0213] S3, the server uploads the financial product information in S2 to the server, and then allocates an account to the corresponding financial institution personnel, for example, the marketing manager responsible for the financial product. After the marketing manager logs into the server through the financial institution terminal, he can browse the financial product information corresponding to each financial product under the account.

[0214] After browsing the financial product information corresponding to each financial product under their account, the marketing manager can select corresponding target investors based on the financial product and then send the financial product information of a certain financial product to one or more corresponding investors. For example, if the financial product has a low risk level and a low rate of return, the financial product information of this financial product can be sent to investors with a conservative investment tendency. If the financial product has a high risk level and a high rate of return, the financial product information of this financial product can be sent to investors with a profit investment tendency, thereby providing targeted marketing services. Specifically, the financial product information can be sent to the corresponding investors in the form of a QR code page of the WeChat mini program.

[0215] In addition, the same marketing manager's account can contain financial product information corresponding to multiple financial products. In addition to the aforementioned sharing operations, the person can manage multiple financial products under the account, such as deleting and monitoring.

[0216] S4. After the investor terminal receives the service information, the financial product information can be displayed in the investor terminal.

[0217] After receiving the financial product information, the investor can open the financial product information on the investor terminal to enter the page corresponding to the financial product information.

[0218] S5. During the display of the wealth management product on the investor terminal, the investor can ask questions and communicate with the digital human through touch or voice input, and the digital human will interact with the investor in response to the investor's input. For example, the investor inputs "How much is the handling fee" through voice, and after the background recognizes the voice, according to the preset words, the digital human will respond to the investor with corresponding actions and coordination, "This wealth management product has zero handling fees."

[0219] At the same time, during the interaction between investors and digital humans, the interaction content between the two parties can be presented in the form of a dialogue on the marketing manager's financial institution terminal to facilitate the marketing manager's understanding of the investor's intentions.

[0220] S6. If the investor requires manual intervention, for example, by proactively selecting the manual intervention option, or by the system detecting that the investor's actions or intervention intention rate meet pre-set conditions, the investor's terminal initiates a manual intervention request to the financial institution's terminal. The financial institution's terminal responds to the investor's request and directs the marketing manager to address the investor's needs via a voice call. Alternatively, the marketing manager can proactively intervene, further enabling a voice call.

[0221] During a voice call between an investor and a marketing manager, the investor's terminal is displayed on the same screen as the financial institution's terminal, that is, the page content displayed on the investor's terminal is the page content currently displayed on the financial institution's terminal.

[0222] S7. During the interaction between the investor and the digital human in the above S5, the background can record the investor's communication history and display it on the financial institution's terminal so that the marketing manager can make corresponding decisions.

[0223] In addition to the aforementioned examples, the content contained in the communication record can be further adapted according to the scenario. For example, in this exemplary embodiment, the investor's investment tendency can be recorded as a label for the investor. The label can be used to subsequently promote other financial products to the investor, and can also be used as sample data to train the recommendation system.

[0224] Exemplary embodiment 2

[0225] In this exemplary embodiment, a training institution as a service provider that wishes to conduct online training for a certain course is used as an example for explanation. The service objects in this exemplary embodiment are the students who wish to receive the training.

[0226] S1: The server receives the content information of the training course uploaded by the training institution. The content information includes the following:

[0227] A. Textual introduction of the training course; B. Image materials corresponding to each textual introduction in the training course.

[0228] The text description of the above training courses includes but is not limited to the training course outline, course content, teacher profile, course objectives or value, etc. The text description of any of the above content can be presented by corresponding image materials.

[0229] S2: The server generates corresponding training course information based on the content information uploaded in S1. The training course information may include the following contents:

[0230] A. Image / video information; B. Speech information; C. Digital human action information;

[0231] The above-mentioned image / video information may be directly generated based on the image material in S1, or may be manually designed, or the corresponding image / video information may be automatically generated according to a preset image / video template.

[0232] During the generation of the above-mentioned speech information, the possible concerns of the trainees can be determined first, such as the course outline, course content, teacher profile, course purpose or value, etc.; taking the teacher profile as an example, the possible voice inputs of the trainees include: who is the teacher, which teacher is the teacher, can you introduce the course teacher, what achievements has the teacher made before, etc., through manual setting or crawling through the Internet, all possible inputs of the trainees for the above-mentioned concerns can be listed as much as possible; accordingly, the specific time of the investment cycle in S1 can be combined to manually or automatically generate the corresponding response speech for the investment cycle.

[0233] After determining the response words, the action modules corresponding to each response word can be searched in a pre-established database based on the response words, and the action information of the digital human that matches each response word can be generated. In this exemplary embodiment, the first area where the digital human is located and the second area where the image / video information is located are arranged in an upper and lower arrangement.

[0234] S3, the server uploads the training course information in S2 to the server, and then allocates an account to the corresponding training institution personnel, for example, the teacher in charge of the training course. After the teacher logs into the server through the training institution terminal, he can browse the training course information corresponding to each training course under the account.

[0235] After browsing the training course information corresponding to each training course under their account, teachers can select corresponding target trainees based on the training course and then send the training course information of a certain training course to one or more corresponding trainees. For example, if the training course content is early childhood education for infants and toddlers aged 0 to 6, the training course information of this training course can be sent to parents of children of corresponding ages. If the training course content is for a certain professional qualification examination, the training course information of this training course can be sent to personnel in the corresponding profession. The specific sending method can be to send the training course information of the training course to the corresponding trainees in the form of a QR code page of the WeChat mini program.

[0236] In addition, the same teacher's account can contain training course information corresponding to multiple training courses. In addition to the aforementioned sharing operations, the teacher can manage multiple training courses under the account, such as deleting and monitoring.

[0237] S4, after the trainee terminal receives the service information, the training course information can be displayed in the trainee terminal.

[0238] After receiving the training course information, the trainees can open the training course information on the trainee terminal to enter the page corresponding to the training course information.

[0239] S5: When the trainee terminal displays the training course, the trainee can ask questions and communicate with the digital human through touch or voice input, and the digital human will interact with the trainee in response to the trainee's input; for example, the trainee inputs "How long is the course cycle" through voice, and after the background recognizes the voice, according to the preset words, the digital human will respond to the trainee with corresponding actions and cooperate with the trainee. "The approximate learning time for this training course is 60 hours."

[0240] At the same time, during the interaction between trainees and digital humans, the interactive content of the two parties can be presented in the form of a dialogue on the teacher's training institution terminal to facilitate the teacher's understanding of the trainees' intentions.

[0241] S6: If the trainee requires manual intervention, for example, by actively selecting the manual intervention option, or by the system detecting that the trainee's operation or intervention intention rate has reached a preset condition, the trainee's terminal will initiate a manual intervention request to the training institution's terminal. The training institution's terminal will respond to the trainee's request and enable the teacher to address the trainee's need through a voice call. Alternatively, the teacher can proactively intervene to facilitate a voice call.

[0242] During a voice call between a trainee and a teacher, the trainee's terminal is displayed on the same screen as the training institution's terminal, that is, the page content displayed on the trainee's terminal is the page content currently displayed on the training institution's terminal.

[0243] S7, during the interaction between trainees and digital humans in the above S5, the background can record the trainees' communication records and display them on the training institution's terminal so that teachers can make corresponding decisions.

[0244] In addition to the aforementioned examples, the content of the communication record can be further adapted according to the scenario. For example, in this exemplary embodiment, the learning progress of the trainees or the number of questions asked on a certain question can be recorded to determine the learning patterns and progress of the trainees so that the training institution can provide targeted adjustments for them.

[0245] Exemplary embodiment 3

[0246] In this exemplary embodiment, the government investment promotion department as the service provider hopes to promote and explain a certain investment promotion policy, and the service objects in this exemplary embodiment are enterprises that hope to settle in the area.

[0247] S1: The server receives the policy information uploaded by the investment promotion department. The content information includes the following:

[0248] A. Textual introduction of the policy statement; B. Image material corresponding to each textual introduction in the policy statement.

[0249] The text description of the above policy description includes but is not limited to the applicable targets of the investment promotion policy, the policy's effective and expiration dates, the materials or procedures required by the enterprise, and the policies and tax incentives that the enterprise can enjoy. The text description of any of the above content can be presented with corresponding image materials.

[0250] S2: The server generates corresponding policy description information based on the content information uploaded in S1. The policy description information may include the following contents:

[0251] A. Image / video information; B. Speech information; C. Digital human action information;

[0252] The above-mentioned image / video information may be directly generated based on the image material in S1, or may be manually designed, or the corresponding image / video information may be automatically generated according to a preset image / video template.

[0253] During the process of generating the above-mentioned speech information, the possible concerns of the enterprise can be determined first, such as the applicable objects of the investment promotion policy, the effective and deadline time of the policy, the materials or procedures that the enterprise needs to handle, the policies and tax incentives that the enterprise can enjoy, etc.; taking the materials or procedures that the enterprise needs to handle as an example, the possible voice inputs of the enterprise docking personnel include: what materials need to be handled, what procedures need to be handled, how to handle the procedures, what is the process, etc., through manual settings or Internet crawling, all possible inputs of the enterprise docking personnel for the above-mentioned concerns can be listed as much as possible; accordingly, the specific time of the investment cycle in S1 can be combined to manually or automatically generate corresponding reply speech about the investment cycle.

[0254] After determining the response words, the action modules corresponding to each response word can be searched in a pre-established database based on the response words, and the action information of the digital human that matches each response word can be generated. In this exemplary embodiment, the first area where the digital human is located and the second area where the image / video information is located are arranged in an overlapping manner.

[0255] S3, the server uploads the policy description information in S2 to the server, and then allocates an account to the corresponding department promotion personnel, for example, the department promotion personnel responsible for the policy description. After the department promotion personnel logs into the server through the investment promotion department terminal, they can browse the policy description information corresponding to each policy description under the account.

[0256] After browsing the policy descriptions corresponding to each policy description under their account, department promoters can select the corresponding target enterprise contact person based on the policy description, and then send the policy description information of a certain policy description to one or more corresponding enterprise contact persons. For example, if the investment promotion policy is aimed at the new energy vehicle industry, the policy description information of the policy description can be sent to related enterprises in the new energy vehicle industry. If the investment promotion policy is aimed at the integrated circuit industry, the policy description information of the policy description can be sent to relevant personnel in the integrated circuit industry. The specific sending method can be to send the policy description information of the policy description to the corresponding enterprise contact person in the form of a QR code page of the WeChat mini program.

[0257] In addition, a promoter in the same department can have multiple policy descriptions under their account. In addition to the aforementioned sharing operations, the promoter can manage multiple policy descriptions under their account, such as deleting and monitoring them.

[0258] S4. After the enterprise docking personnel terminal receives the service information, the policy description information can be displayed in the enterprise docking personnel terminal.

[0259] After receiving the policy description information, the enterprise docking personnel can open the policy description information on the enterprise docking personnel terminal to enter the page corresponding to the policy description information.

[0260] S5. During the process of displaying the policy description on the terminal of the enterprise docking personnel, the enterprise docking personnel can ask questions and communicate with the digital human through touch or voice input, and the digital human will interact with the enterprise docking personnel in response to the input of the enterprise docking personnel; for example, the enterprise docking personnel inputs "What are the tax incentives" through voice, and after the background recognizes the voice, according to the preset words, the digital human will respond to the enterprise docking personnel with the corresponding actions and coordination, "You can enjoy a 10% tax incentive in the first three years."

[0261] At the same time, during the interaction between the enterprise docking personnel and the digital human, the interaction content between the two parties can be presented in the form of a dialogue on the investment promotion department terminal of the department promotion personnel, so as to facilitate the department promotion personnel to understand the intentions of the enterprise docking personnel.

[0262] S6: If the business matchmaker requires manual intervention, for example, by the business matchmaker proactively selecting the manual intervention option; or if the system detects that the business matchmaker's actions or intervention intention rate have reached a preset condition, the business matchmaker's terminal will initiate a manual intervention request to the investment department terminal. The investment department terminal will respond to the business matchmaker's request and instruct the department's marketing staff to address the business matchmaker's request via a voice call. Alternatively, the department's marketing staff can proactively intervene, thereby enabling a voice call.

[0263] During a voice call between the enterprise docking personnel and the department promotion personnel, the enterprise docking personnel terminal is displayed on the same screen as the investment promotion department terminal, that is, the page content displayed on the enterprise docking personnel terminal is the page content currently displayed on the investment promotion department terminal.

[0264] S7. During the interaction between the enterprise docking personnel in S5 and the digital human, the background can record the communication records of the enterprise docking personnel and display them on the investment promotion department terminal so that the department promotion personnel can make corresponding decisions.

[0265] In addition to the aforementioned examples, the content of the communication records can be further adapted according to the scenario. For example, in this exemplary embodiment, the number of questions asked by corporate liaisons about certain specific areas can be recorded to determine the level of attention paid by the company to the area, and then adjustments can be made within the government to meet the investment conditions for the area.

[0266] According to another aspect of the embodiment of the present application, an electronic device for implementing the above-mentioned method for sending service information is also provided. The above-mentioned electronic device can be applied to, but is not limited to, a server. Figure 8As shown, the electronic device includes a memory 802 and a processor 804. The memory 802 stores a computer program, and the processor 804 is configured to execute the steps in any of the above method embodiments through the computer program.

[0267] Optionally, in this embodiment, the electronic device may be located in at least one network device among a plurality of network devices of a computer network.

[0268] Optionally, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0269] S1, obtaining service information corresponding to a service product, wherein the service information is information generated by a server based on pre-acquired product features of the service product, and the service information is used to interact with a service recipient through one or more preset virtual images to display the product features of the service product to the service recipient;

[0270] S2, sending service information to a second terminal, wherein the second terminal is a terminal used by the service object to obtain product features of the service product;

[0271] S3. Displaying interaction data between the service object and the virtual image on the first terminal, wherein the interaction data includes conversation content between the service object and the virtual image.

[0272] Optionally, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0273] S1, receiving service information sent by a first terminal, wherein the service information is information generated by a server based on pre-acquired product features of a service product, and the service information is used to interact with a service recipient through one or more preset virtual images to display the product features of the service product to the service recipient;

[0274] S2, obtaining service product characteristics through virtual images;

[0275] S3, sending the interaction data of the service object interacting with the virtual image through the second terminal to the first terminal, wherein the interaction data includes the conversation content between the service object and the virtual image.

[0276] Optionally, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0277] S1, generating service information based on pre-acquired product features of a service product, wherein the service information is used to interact with a service object through one or more preset virtual images to present the product features of the service product to the service object;

[0278] S2: Send service information to the first terminal, where the first terminal is a terminal that sends service information to the service object.

[0279] Alternatively, those skilled in the art will appreciate that Figure 8 The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (MID), a PAD, or other terminal devices. Figure 8 It does not limit the structure of the above electronic device. For example, the electronic device may also include Figure 8 More or fewer components (such as network interfaces, etc.) as shown in, or with Figure 8 Different configurations shown.

[0280] Among them, the memory 802 can be used to store software programs and modules, such as the program instructions / modules corresponding to the method and device for sending service information in the embodiment of the present application. The processor 804 executes various functional applications and data processing by running the software programs and modules stored in the memory 802, that is, to implement the above-mentioned method. The memory 802 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 802 may further include a memory remotely located relative to the processor 804, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned networks include but are not limited to the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. Among them, the memory 802 can specifically be, but is not limited to, used to store program steps of a training method for a speech recognition neural network model. As an example, Figure 8 As shown, the memory 802 may include, but is not limited to, the first acquisition module 502, the first sending module 504, the display module 506, etc. In addition, it may also include, but is not limited to, other module units in the above apparatus, which will not be described in detail in this example.

[0281] Optionally, the transmission device 806 is configured to receive or send data via a network. Specific examples of the network may include a wired network and a wireless network. In one embodiment, the transmission device 806 includes a network interface controller (NIC), which can be connected to other network devices and a router via a network cable to communicate with the Internet or a local area network. In one embodiment, the transmission device 806 is a radio frequency (RF) module, which is configured to communicate with the Internet wirelessly.

[0282] In addition, the electronic device further includes: a display 808 and a connection bus 810 for connecting various module components in the electronic device.

[0283] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when run.

[0284] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0285] S1, obtaining service information corresponding to a service product, wherein the service information is information generated by a server based on pre-acquired product features of the service product, and the service information is used to interact with a service recipient through one or more preset virtual images to display the product features of the service product to the service recipient;

[0286] S2, sending service information to a second terminal, wherein the second terminal is a terminal used by the service object to obtain product features of the service product;

[0287] S3. Displaying interaction data between the service object and the virtual image on the first terminal, wherein the interaction data includes conversation content between the service object and the virtual image.

[0288] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0289] S1, receiving service information sent by a first terminal, wherein the service information is information generated by a server based on pre-acquired product features of a service product, and the service information is used to interact with a service recipient through one or more preset virtual images to display the product features of the service product to the service recipient;

[0290] S2, obtaining service product characteristics through virtual images;

[0291] S3, sending the interaction data of the service object interacting with the virtual image through the second terminal to the first terminal, wherein the interaction data includes the conversation content between the service object and the virtual image.

[0292] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0293] S1, generating service information based on pre-acquired product features of a service product, wherein the service information is used to interact with a service object through one or more preset virtual images to present the product features of the service product to the service object;

[0294] S2: Send service information to the first terminal, where the first terminal is a terminal that sends service information to the service object.

[0295] Optionally, the storage medium is further configured to store a computer program for executing the steps included in the method in the above embodiment, which will not be described in detail in this embodiment.

[0296] Optionally, in this embodiment, a person of ordinary skill in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing the hardware related to the terminal device through a program, and the program may be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0297] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0298] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above-mentioned computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which can be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application.

[0299] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0300] In the several embodiments provided in this application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, and can be electrical or other forms.

[0301] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0302] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0303] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for sending service information, applied to a first terminal, characterized in that: include: Upload the content information of the service product to the server; Obtaining service information corresponding to the service product fed back by the server, wherein the service information is information generated by the server based on pre-acquired product features of the service product, and the service information is used to interact with the service object through one or more preset virtual images to display the product features of the service product to the service object, wherein the product features are features that need to be displayed to the service object, or features consulted by the service object based on the service product; the service information includes at least one of the following: image display information, speech information, and virtual image action information; wherein the image display information is used to indicate an image used to display at least part of the product features of the service product, the speech information is used to indicate speech used to interact with the service object, and the virtual image action information is used to indicate body movements and / or facial movements of the virtual image; Sending the service information to a second terminal, wherein the second terminal is a terminal used by the service object to obtain product features of the service product; Obtaining operation information input by the service object to the second terminal, and if it is determined that the service object requires intervention by the first terminal, synchronously displaying the screen displayed on the second terminal on the first terminal; wherein the operation information includes at least one of the following: option confirmation, text input, voice input, and image input; Synchronously displaying a first annotation operation performed on the first terminal on the second terminal, and synchronously displaying a second annotation operation performed on the second terminal on the first terminal; the first annotation operation is used to indicate the annotation operation performed by the service provider on the first terminal, and the second annotation operation is used to indicate the annotation operation performed by the service recipient on the second terminal, and the content circled in the first annotation operation is used to explain the content circled in the second annotation operation; Providing image display information to the service object in response to the operation information, and interacting with the service object through the virtual image according to the speech information and the virtual image action information; Interaction data between the service object and the virtual image is displayed on the first terminal, wherein the interaction data includes conversation content between the service object and the virtual image.

2. The method according to claim 1, characterized in that The sending the service information to the second terminal includes: sending media information containing the service information to the second terminal, so that the second terminal obtains the service information according to the media information.

3. The method according to claim 2, characterized in that The sending of the media information including the service information to the second terminal includes: Determine the matching degree between the service product and the service object according to preset rules; Determine a target service object that matches the service product according to the matching degree, wherein the target service object includes one or more service objects; The media information is sent to the second terminal corresponding to the target service object, wherein the media information includes the service information matching the target service object.

4. The method according to claim 1, wherein Determining that the service object requires intervention by the first terminal in at least one of the following ways: obtaining an operation instruction of the service object, and determining, according to the operation instruction, that the service object requires intervention of the first terminal; When detecting that the number of repeated operations issued by the service object exceeds a first preset threshold, determining that the service object requires intervention by the first terminal; By matching historical interaction data with current interaction data, the intervention intention rate of the service object is detected. When the intervention intention rate exceeds a second preset threshold, it is determined that the service object requires intervention by the first terminal, wherein the intervention intention rate is used to indicate the probability that the service object will become an intended customer after the intervention of the first terminal.

5. The method according to claim 1, wherein The method further includes: acquiring interaction process data between the service object and the virtual image, wherein the interaction process data includes at least one of the following: access time of a service product, interaction rounds, hit counts, interaction data between the service object and the virtual image, and number of views of the same service product by the service object; Determine the intended customer or the target service object that matches the service product based on the interaction process data.

6. A method for receiving service information, applied to a second terminal, characterized in that: include: Receive service information sent by a first terminal, wherein the service information is information generated and fed back by the server based on pre-acquired product features of the service product after the first terminal uploads content information of the service product to the server, and the service information is used to interact with a service object through one or more preset virtual images to display the product features of the service product to the service object, wherein the product features are features that need to be displayed to the service object, or features consulted by the service object based on the service product; the service information includes at least one of the following: image display information, speech information, and virtual image action information; wherein the image display information is used to indicate an image used to display at least part of the product features of the service product, the speech information is used to indicate speech used to interact with the service object, and the virtual image action information is used to indicate body movements and / or facial movements of the virtual image; obtaining the characteristics of the service product through the virtual image; Sending operation information input by the service object to the second terminal to the first terminal, and synchronously displaying the screen displayed on the second terminal on the first terminal if it is determined that the service object requires intervention by the first terminal; wherein the operation information includes at least one of the following: option confirmation, text input, voice input, and image input; Synchronously displaying a second annotation operation performed on the second terminal on the first terminal, and synchronously displaying a first annotation operation performed on the first terminal on the second terminal; the first annotation operation is used to indicate the annotation operation performed by the service provider on the first terminal, and the second annotation operation is used to indicate the annotation operation performed by the service recipient on the second terminal, and the content circled in the first annotation operation is used to explain the content circled in the second annotation operation; Obtaining a display screen generated by the first terminal and corresponding to the operation information and an execution instruction of the virtual image, wherein the execution instruction of the virtual image is used to instruct the virtual image to interact with the service object according to the speech information and the virtual image action information; The interaction data of the service object interacting with the virtual image through the second terminal is sent to the first terminal, wherein the interaction data includes the conversation content between the service object and the virtual image.

7. The method according to claim 6, characterized in that The receiving service information sent by the first terminal includes: receiving media information including the service information sent by the first terminal; The service information is acquired according to the medium information.

8. The method according to claim 6, characterized in that Determining that the service object requires intervention by the first terminal by at least one of the following methods: obtaining an operation instruction of the service object, and determining that the service object requires intervention by the first terminal according to the operation instruction; When detecting that the number of repeated operations issued by the service object exceeds a first preset threshold, determining that the service object requires intervention by the first terminal; By matching historical interaction data with current interaction data, the intervention intention rate of the service object is detected. When the intervention intention rate exceeds a second preset threshold, it is determined that the service object requires intervention by the first terminal, wherein the intervention intention rate is used to indicate the probability that the service object will become an intended customer after the intervention of the first terminal.

9. The method according to claim 6, characterized in that The method further comprises: Acquiring interaction process data between the service object and the virtual image, wherein the interaction process data includes at least one of the following: access time of a service product, interaction rounds, hit counts, interaction data between the service object and the virtual image, and number of views of the same service product by the service object; The interaction process data is sent to the second terminal, so that the second terminal determines the intended customer or the target service object that matches the service product according to the interaction process data.

10. A method for sending service information, applied to a server, characterized in that: include: Receiving content information of a service product sent by the first terminal; Generate service information based on pre-acquired product features of a service product, wherein the service information is used to interact with a service object through one or more preset virtual images to display the product features of the service product to the service object, wherein the product features are features that need to be displayed to the service object, or features that the service object inquires about based on the service product; the service information includes at least one of the following: image display information, speech information, and virtual image action information; wherein the image display information is used to indicate an image used to display at least part of the product features of the service product, the speech information is used to indicate speech used to interact with the service object, and the virtual image action information is used to indicate body movements and / or facial movements of the virtual image; Send the service information to the first terminal so that the first terminal sends the service information to the second terminal, and obtains the operation information input by the service object to the second terminal. When it is determined that the service object requires intervention from the first terminal, the screen displayed on the second terminal is synchronously displayed on the first terminal, and the first annotation operation performed on the first terminal is synchronously displayed on the second terminal, and the second annotation operation performed on the second terminal is synchronously displayed on the first terminal; in response to the operation information, image display information is provided to the service object, and the virtual image interacts with the service object according to the speech information and the virtual image action information through the virtual image, so that the interaction data between the service object and the virtual image is displayed on the first terminal; wherein, the first terminal is the terminal that sends the service information to the service object, and the second terminal is the terminal used by the service object to obtain the product features of the service product; the operation information includes at least one of the following: option determination, text input, voice input, image input; the interaction data includes the conversation content between the service object and the virtual image.

11. The method according to claim 10, characterized in that The service information also includes: Area division information of a display interface, wherein the display interface includes at least a first area and a second area, the first area is used to display the content of the service product through an image screen, and the second area is used to display the actions of the virtual image, and the area division information is used to indicate the positional relationship between the first area and the second area in the display interface.

12. The method according to claim 10, characterized in that Generating service information according to the pre-acquired product features of the service product includes: The virtual image action information is generated according to the image display information and / or the speech information, wherein the virtual image action information includes at least: the action of the virtual image when displaying the image corresponding to the image display information, and / or the action of the virtual image when interacting with the service object according to the speech information.

13. The method according to claim 12, characterized in that Generating the avatar action information according to the image display information and the speech information includes: Selecting a first action module corresponding to the image display information from a preset avatar action database based on the image display information, wherein the first action module is used to indicate the action of the avatar when the image corresponding to the image display information is displayed; selecting a second action module corresponding to the speech information from the avatar action database based on the speech information, wherein the second action module is used to indicate the action of the avatar when interacting with the service object according to the speech information; The virtual image action information is determined by the first action module and / or the second action module; wherein the virtual image action database includes a plurality of preset action modules, wherein each of the action modules corresponds to a body movement and / or facial movement of a virtual image.

14. The method according to claim 13, characterized in that The selecting, from the virtual image action database according to the speech information, a second action module corresponding to the speech information comprises: Acquiring voice data input by the service object through a second terminal, wherein the voice data includes real-time voice data and / or non-real-time voice data, and the second terminal is a terminal used by the service object to obtain product features of the service product; Selecting a target second action module corresponding to the voice data in the avatar action database according to the voice data and the speech information; Push the target second action module to the second terminal.

15. The method according to claim 14, characterized in that Before pushing the target second action module to the second terminal, the method further includes: The second action module in the virtual image action database is set on a content delivery network CDN node, wherein each CDN node corresponds to a uniform resource locator URL address.

16. The method according to claim 15, characterized in that Pushing the target second action module to the second terminal includes: After selecting the target second action module corresponding to the voice data, the target URL address corresponding to the CDN node where the target second action module is located is sent to the second terminal to instruct the second terminal to obtain the target second action module through the target URL address.

17. The method according to claim 10, wherein: The sending the service information to the first terminal includes: In response to a login request from a first account, service information of a service product corresponding to the first account is sent to the first terminal, wherein the first account is an account logged in on the first terminal, and the first account has a corresponding relationship with one or more of the service products; and / or, media information containing the service information is sent to the first terminal, so that the first terminal obtains the service information based on the media information.

18. A device for sending service information, provided in a first terminal, characterized in that: include: A first acquisition module is configured to acquire service information corresponding to a service product, wherein the service information is information generated by the server based on pre-acquired product features of the service product after the first terminal uploads the content information of the service product to the server, and the service information is used to interact with the service object through one or more preset virtual images to display the product features of the service product to the service object, wherein the product features are features that need to be displayed to the service object, or features consulted by the service object based on the service product; the service information includes at least one of the following: image display information, speech information, and virtual image action information; wherein the image display information is used to indicate an image used to display at least part of the product features of the service product, the speech information is used to indicate the speech used to interact with the service object, and the virtual image action information is used to indicate the body movements and / or facial movements of the virtual image; A first sending module is configured to send the service information to a second terminal, wherein the second terminal is a terminal used by the service object to obtain product features of the service product; The display module is configured to obtain the operation information input by the service object to the second terminal, and when it is determined that the service object requires intervention of the first terminal, synchronously display the screen displayed on the second terminal on the first terminal; synchronously display the first annotation operation performed on the first terminal to the second terminal, and synchronously display the second annotation operation performed on the second terminal on the first terminal; provide image display information to the service object in response to the operation information, and interact with the service object through the virtual image according to the speech information and the virtual image action information; display the interaction data between the service object and the virtual image on the first terminal, wherein the operation information includes at least one of the following: option determination, text input, voice input, image input; the first annotation operation is used to indicate the annotation operation performed by the service provider on the first terminal, and the second annotation operation is used to indicate the annotation operation performed by the service object on the second terminal, and the content circled by the first annotation operation is used to explain the content circled by the second annotation operation; the interaction data includes the conversation content between the service object and the virtual image.

19. A device for receiving service information, provided in a second terminal, characterized in that: include: A receiving module is configured to receive service information sent by a first terminal, wherein the service information is information generated by the server based on pre-acquired product features of the service product after the first terminal uploads content information of the service product to the server, and the service information is used to interact with the service object through one or more preset virtual images to display the product features of the service product to the service object, and the product features are features that need to be displayed to the service object, or features consulted by the service object based on the service product; the service information includes at least one of the following: image display information, speech information, and virtual image action information; wherein the image display information is used to indicate an image used to display at least part of the product features of the service product, the speech information is used to indicate the speech used to interact with the service object, and the virtual image action information is used to indicate the body movements and / or facial movements of the virtual image; a second acquisition module configured to acquire the characteristics of the service product through the virtual image; The second sending module is configured to send the operation information input by the service object to the second terminal to the first terminal, and if it is determined that the service object requires intervention from the first terminal, synchronously display the screen displayed on the second terminal on the first terminal; synchronously display the second annotation operation performed on the second terminal to the first terminal, and synchronously display the first annotation operation performed on the first terminal on the second terminal; obtain the display screen corresponding to the operation information and the execution instruction of the virtual image generated by the first terminal, and send the interaction data of the service object interacting with the virtual image through the second terminal to the first terminal, wherein the operation information includes at least one of the following: option confirmation, text input, voice input, and image input; the first annotation operation is used to indicate the annotation operation performed by the service provider on the first terminal, and the second annotation operation is used to indicate the annotation operation performed by the service object on the second terminal, and the content circled by the first annotation operation is used to explain the content circled by the second annotation operation; the execution instruction of the virtual image is used to instruct the virtual image to interact with the service object according to the speech information and the virtual image action information; and the interaction data includes the conversation content between the service object and the virtual image.

20. A device for sending service information, provided on a server, characterized in that: include: A generation module is configured to generate service information based on pre-acquired product features of a service product, wherein the service information is used to interact with a service object through one or more preset virtual images to display the product features of the service product to the service object, wherein the product features are features that need to be displayed to the service object, or features that the service object inquires about based on the service product; the service information includes at least one of the following: image display information, speech information, and virtual image action information; wherein the image display information is used to indicate an image used to display at least part of the product features of the service product, the speech information is used to indicate speech used to interact with the service object, and the virtual image action information is used to indicate body movements and / or facial movements of the virtual image; The third sending module is configured to send the service information to the first terminal so that the first terminal sends the service information to the second terminal, and obtains the operation information input by the service object to the second terminal. When it is determined that the service object requires intervention by the first terminal, the screen displayed on the second terminal is synchronously displayed on the first terminal, and the first annotation operation performed on the first terminal is synchronously displayed on the second terminal, and the second annotation operation performed on the second terminal is synchronously displayed on the first terminal; in response to the operation information, image display information is provided to the service object, and the virtual image interacts with the service object according to the speech information and the virtual image action information through the virtual image, so that the interaction data between the service object and the virtual image is displayed on the first terminal; wherein, the first terminal is the terminal that sends the service information to the service object, and the second terminal is the terminal used by the service object to obtain the product features of the service product; the operation information includes at least one of the following: option determination, text input, voice input, image input; the interaction data includes the conversation content between the service object and the virtual image.

21. A computer-readable storage medium, characterized in that The storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 17 when executed.

22. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 17.

Images