Information processing method and device, computer readable storage medium and electronic equipment

Abstract

The invention discloses an information processing method and device, a computer readable storage medium and electronic equipment. Relates to the field of artificial intelligence. The method comprises the steps that service demand information of a user of a to-be-handled service is acquired, process text information associated with a target service is determined according to the service demand information, the target service is a service pointed by the service demand information, and the process text information is used for describing process content of the target service; inputting the process text information associated with the target service into a first text video model, and performing video generation processing based on the process text information through the first text video model to obtain a process demonstration video of the target service; and displaying the process demonstration video to the user, the process demonstration video being used for guiding the user to handle the target business. Through application of the method and the device, the problem of high labor cost caused by dependence on manual guiding of the user for business handling in the related technology when the user handles the business is solved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and more specifically, to an information processing method, device, computer-readable storage medium, and electronic device. Background Art

[0002] In the traditional business handling process of financial institutions, users often need to rely on the on-site guidance of financial institution staff to complete complex business processes, such as account opening, loan application, investment consultation, etc. Although this model that relies on manual guidance can provide personalized services and ensure that users get the necessary help and explanations when handling business, it also brings significant efficiency and cost issues. Especially during business peak periods, the inefficiency of manual guidance and extended waiting time have become the norm, which not only increases the bank's labor costs, but may also affect the user experience and lead to a decline in customer satisfaction.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The main purpose of the present application is to provide an information processing method, device, computer-readable storage medium and electronic device to solve the problem in the related art that when users handle business, they rely on manual guidance to handle business, resulting in high labor costs.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, an information processing method is provided. The method includes: obtaining the business demand information of the user to be processed, and determining the process text information associated with the target business according to the business demand information, wherein the target business is the business pointed to by the business demand information, and the process text information is used to describe the process content of the target business; inputting the process text information associated with the target business into the first text video model, performing video generation processing based on the process text information by the first text video model, and obtaining a process demonstration video of the target business; showing the process demonstration video to the user, wherein the process demonstration video is used to guide the user to process the target business.

[0006] Furthermore, the information processing method also includes: upon receiving a business guidance request from a user, determining whether a sign language collection request from the user is received; upon receiving a sign language collection request from the user, collecting a sign language video of the user based on an image acquisition device; and recognizing and processing the sign language video based on a sign language recognition model to obtain business demand information.

[0007] Furthermore, the information processing method also includes: if the business demand information is determined based on the user's sign language video, then generating a sign language demonstration video of the target business according to the process text information associated with the target business; integrating the sign language demonstration video and the process demonstration video to obtain the target demonstration video; and displaying the target demonstration video to the user.

[0008] Furthermore, the information processing method also includes: obtaining first process text information associated with each of the multiple first businesses, and obtaining multiple first process images associated with each of the first process text information; inputting the first process text information and the multiple first process images associated with the first process text information into the second Vincent video model to obtain a first demonstration video; inputting the first process text information into the third Vincent video model to obtain a second demonstration video, wherein the model parameter values ​​of the third Vincent video model and the second Vincent video model are the same; calculating the loss value based on a preset loss function, the first demonstration video and the second demonstration video; when the loss value is greater than a preset threshold, updating the model parameter values ​​of the third Vincent video model, and repeatedly executing the step of inputting the first process text information into the updated third Vincent video model to obtain the second demonstration video, until the loss value is less than or equal to the preset threshold, the updated third Vincent video model is determined as the first Vincent video model.

[0009] Furthermore, the information processing method further includes: inputting each first process text information into the text graph model respectively to obtain a plurality of first process images corresponding to each first process text information.

[0010] Furthermore, the information processing method also includes: obtaining multiple third demonstration videos, and obtaining the second process text information corresponding to each third demonstration video; using the third demonstration video as the first training sample, using the second process text information as the true label corresponding to the first training sample, and constructing a first training sample set based on the first training sample and the true label corresponding to the first training sample; training an initial Wensheng video model based on the first training sample set to obtain a second Wensheng video model, and constructing a third Wensheng video model based on the model parameter values ​​of the second Wensheng video model.

[0011] Furthermore, the information processing method also includes: obtaining multiple second process text information, and obtaining second process images corresponding to each second process text information; using the second process text information as a second training sample, using the second process image as a true label corresponding to the second training sample, and constructing a second training sample set based on the second training sample and the true label corresponding to the second training sample; training an initial text graph model based on the second training sample set to obtain a text graph model.

[0012] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an information processing device is provided. The device includes: a first acquisition module, which is used to acquire the business demand information of the user to be processed, and determine the process text information associated with the target business according to the business demand information, wherein the target business is the business pointed to by the business demand information, and the process text information is used to describe the process content of the target business; a first processing module, which is used to input the process text information associated with the target business into the first Wensheng video model, and perform video generation processing based on the process text information through the first Wensheng video model to obtain a process demonstration video of the target business; a second processing module, which is used to show the process demonstration video to the user, wherein the process demonstration video is used to guide the user to handle the target business.

[0013] Furthermore, the first acquisition module also includes: a judgment submodule, which is used to determine whether a sign language collection request from the user is received when a business guidance request from the user is received; a collection submodule, which is used to collect the user's sign language video based on the image collection device when a sign language collection request from the user is received; and a recognition submodule, which is used to recognize and process the sign language video based on a sign language recognition model to obtain business demand information.

[0014] Furthermore, the second processing module also includes: a generation sub-module, which is used to generate a sign language demonstration video of the target business according to the process text information associated with the target business if the business demand information is determined based on the user's sign language video; a first processing sub-module, which is used to integrate the sign language demonstration video and the process demonstration video to obtain a target demonstration video; and a second processing sub-module, which is used to display the target demonstration video to the user.

[0015] Furthermore, the information processing device also includes: a second acquisition module, which is used to acquire first process text information associated with each of the multiple first businesses, and acquire multiple first process images associated with each of the first process text information; a third processing module, which is used to input the first process text information and the multiple first process images associated with the first process text information into the second Vincent video model to obtain a first demonstration video; a fourth processing module, which is used to input the first process text information into the third Vincent video model to obtain a second demonstration video, wherein the model parameter values ​​of the third Vincent video model and the second Vincent video model are the same; a calculation module, which is used to calculate the loss value based on a preset loss function, the first demonstration video and the second demonstration video; a fifth processing module, which is used to update the model parameter value of the third Vincent video model when the loss value is greater than a preset threshold, and repeatedly execute the step of inputting the first process text information into the updated third Vincent video model to obtain the second demonstration video, until the loss value is less than or equal to the preset threshold, and the updated third Vincent video model is determined as the first Vincent video model.

[0016] Furthermore, the second acquisition module also includes: a third processing submodule, which is used to input each first process text information into the text graph model respectively to obtain a plurality of first process images corresponding to each first process text information.

[0017] Furthermore, the information processing device also includes: a third acquisition module, used to acquire multiple third demonstration videos, and acquire the second process text information corresponding to each third demonstration video; a sixth processing module, used to use the third demonstration video as the first training sample, and the second process text information as the true label corresponding to the first training sample, and construct a first training sample set based on the first training sample and the true label corresponding to the first training sample; a seventh processing module, used to train an initial Wensheng video model based on the first training sample set, obtain a second Wensheng video model, and construct a third Wensheng video model based on the model parameter values ​​of the second Wensheng video model.

[0018] Furthermore, the information processing device also includes: a fourth acquisition module, used to acquire multiple second process text information, and acquire the second process image corresponding to each second process text information; an eighth processing module, used to use the second process text information as the second training sample, and the second process image as the real label corresponding to the second training sample, and construct a second training sample set based on the second training sample and the real label corresponding to the second training sample; a ninth processing module, used to train the initial Wensheng graph model based on the second training sample set to obtain the Wensheng graph model.

[0019] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer-readable storage medium is provided, and the computer-readable storage medium includes a stored executable program, wherein when the executable program runs, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned information processing method.

[0020] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an electronic device is provided, the electronic device comprising a memory storing an executable program; and a processor for running the program, wherein the above-mentioned information processing method is executed when the program is running.

[0021] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer program product is provided, including computer instructions, which implement the steps of the above-mentioned information processing method when executed by a processor.

[0022] In an embodiment of the present application, by determining the process text information associated with the target business based on the business demand information of the user of the business to be processed, the process content of the business that the user expects to handle is effectively determined, and by inputting the process text information associated with the target business into the first text video model, a process demonstration video of the target business is obtained, and the use of artificial intelligence technology is realized to generate a corresponding video demonstration based on the text description of the relevant business process. By showing the process demonstration video to the user, process guidance for the user based on the automatically generated process demonstration video is realized, thereby reducing manual guidance work and reducing labor costs.

[0023] It can be seen that the solution provided by this application achieves the purpose of automatically generating a process demonstration video according to user needs to guide users to handle business, and solves the problem of relying on manual guidance of users to handle business in related technologies, resulting in high labor costs. Thus, the effect of reducing labor costs is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0025] Figure 1 is a hardware structure block diagram of a computer terminal provided according to an embodiment of the present application;

[0026] Figure 2 is a flowchart of an information processing method provided according to an embodiment of the present application;

[0027] Figure 3 is a flowchart of obtaining a first text video model through training according to an embodiment of the present application;

[0028] Figure 4 is a schematic diagram of an information processing device provided according to an embodiment of the present application;

[0029] Figure 5 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] It should be noted that the collected information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, user portrait data, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with relevant laws, regulations and standards, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation entrances are provided for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions to provide users with corresponding operation entrances for users to choose to agree or refuse the results of automated decision-making; if the user chooses to refuse, the expert decision-making process will be entered.

[0033] Example 1

[0034] According to an embodiment of the present application, an embodiment of an information processing method is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0035] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal (or mobile device) for implementing an information processing method. Figure 1As shown, the computer terminal 10 (or mobile device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can 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 above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0036] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0037] The memory 104 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the information processing method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the above-mentioned information processing 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 examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 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.

[0038] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0039] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0040] Under the above operating environment, this application provides Figure 2 The information processing method shown. Figure 2 is a flowchart of an information processing method provided according to an embodiment of the present application, such as Figure 2 As shown, the information processing method includes the following steps:

[0041] Step S201, obtain the business demand information of the user to be processed, and determine the process text information associated with the target business according to the business demand information, wherein the target business is the business pointed to by the business demand information, and the process text information is used to describe the process content of the target business.

[0042] Optionally, electronic devices, application systems, servers and other devices may be used as the execution subject of the present application. In this embodiment, the target processing system is used as the execution subject to execute the information processing method.

[0043] In some embodiments, the user's business demand information may be determined by the target processing system based on the text content input by the user, or may be obtained by the target processing system based on the user's sign language video recognition. Optionally, the business demand information includes text content for describing the business that the user desires to handle.

[0044] Optionally, after determining the business demand information, the target processing system can determine the process text information associated with the target business according to the business demand information, for example, input the business demand information into a natural language processing model, and then perform semantic analysis through the natural language processing model to identify the business pointed to by the business demand information (i.e., the target business), and determine the process text information associated with it based on the target business. In some embodiments, the natural language processing model can be a large language model, and the large language model can be associated with a process knowledge base, which stores the process text information corresponding to each business in the target financial institution, and the target financial institution refers to a financial institution that handles business for the user.

[0045] Among them, the above-mentioned natural language processing model can be pre-trained through a third training sample set, the training samples in the third training sample set include sample business demand information of sample users, the real labels corresponding to the training samples in the third training sample set are the business that the sample users actually expect to handle, and the process text information associated with the business.

[0046] Optionally, the process text information is used to describe the process content of the target business. For example, if the target business is a card opening business, the process text information can be "1. Customer identity verification: the customer needs to first present a valid certificate for identity verification; 2. Fill in the application form: the customer should fill in the card opening application form and provide personal information, such as name, address, telephone number, etc.; 3. Review information: the staff will check the information provided by the customer; 4. Select the card type; 5. Set the transaction password and query password; 6. Complete the card opening".

[0047] Step S202: input the process text information associated with the target business into the first text-generated video model, and perform video generation processing based on the process text information through the first text-generated video model to obtain a process demonstration video of the target business.

[0048] Optionally, the process text information may include at least one sub-text information, and the target processing system may input the process text information associated with the target business into the first text-generated video model to obtain a process demonstration video. Wherein, based on the difference in process text information, the process demonstration video output by the first text-generated video model may be one or more, and there is no absolute correlation between the number of process demonstration videos and the number of sub-text information. For example, if there are three sub-text information in the process text information, the number of process demonstration videos may be 1, 2, or 3.

[0049] Optionally, the process demonstration video includes image information and text information related to the process of the target business. For example, assuming that the target business is a card activation business, the process demonstration video can display a user information filling interface, and make additional notes or marks (such as: highlighting, box selection, step marking), etc. for each content that needs to be filled in the user information filling interface.

[0050] Step S203: showing a process demonstration video to the user, wherein the process demonstration video is used to guide the user to handle the target business.

[0051] Optionally, when there is only one process demonstration video, the target processing system can directly display the video to the user, or it can pre-process the video (such as adding filters, adjusting text size, generating audio corresponding to the text content in the video, etc.) before displaying it to the user. Optionally, when there are multiple process demonstration videos, the target processing system can splice the multiple process demonstration videos into a complete process demonstration video, and then display the complete video to the user, or it can pre-process the complete video before displaying it to the user. The splicing order of the multiple process demonstration videos can be random, or it can be determined by the target processing system after matching the text content in the process demonstration video with the process text information.

[0052] Optionally, after obtaining the process demonstration video, the target processing system can show the process demonstration video to the user. For example, if the user handles the business offline, the user sends the business demand information to the target business system through the counter of the target financial institution, and the target processing system can show the video to the user through the counter of the target financial institution. For another example, if the user handles the business online, the user sends the business demand to the target business system through the terminal device held by the user, and the target processing system can send the process demonstration video to the terminal device held by the user to show the process demonstration video to the user.

[0053] Optionally, after receiving the process demonstration video, the user can quickly understand the process of handling the target business based on the video content of the process demonstration video, thereby improving business handling efficiency and user experience.

[0054] In an embodiment of the present application, by determining the process text information associated with the target business based on the business demand information of the user of the business to be processed, the process content of the business that the user expects to handle is effectively determined, and by inputting the process text information associated with the target business into the first text video model, a process demonstration video of the target business is obtained, and the use of artificial intelligence technology is realized to generate a corresponding video demonstration based on the text description of the relevant business process. By showing the process demonstration video to the user, process guidance for the user based on the automatically generated process demonstration video is realized, thereby reducing manual guidance work and reducing labor costs.

[0055] It can be seen that the solution provided by this application achieves the purpose of automatically generating a process demonstration video according to user needs to guide users to handle business, and solves the problem of relying on manual guidance of users to handle business in related technologies, resulting in high labor costs. Thus, the effect of reducing labor costs is achieved.

[0056] Optionally, in the information processing method provided in the embodiment of the present application, business demand information of the user to be processed is obtained, including: when receiving the user's business guidance request, determining whether the user's sign language collection request is received; when receiving the user's sign language collection request, collecting the user's sign language video based on the image acquisition device; and recognizing and processing the sign language video based on the sign language recognition model to obtain business demand information.

[0057] Optionally, in the actual application process, the user may be a deaf-mute user. Therefore, in order to provide effective services for the deaf-mute user, the target processing system may determine whether the user's sign language collection request is received when the user's business guidance request is received. For example, when the user's business guidance request is received, the business demand information input page is displayed to the user, and a sign language collection button may be provided in the business demand information input page. The target processing system may determine that the user's sign language collection request is received when it is detected that the user triggers the sign language collection button, otherwise, it is determined that the user's sign language collection request is not received.

[0058] Optionally, if the user's sign language collection request is not received, the target processing system may receive text information sent by the user through the business requirement information input page, thereby determining the text information sent by the user as the user's business requirement information.

[0059] Optionally, if a user's sign language collection request is received, the target processing system collects the user's sign language video based on an image collection device. The image collection device can be a camera of the target financial institution or a camera on a terminal device held by the user.

[0060] Optionally, after acquiring the user's sign language video, the target processing system may perform recognition processing on the sign language video based on a sign language recognition model to obtain business demand information, where the business demand information is in text form.

[0061] In some embodiments, the sign language recognition model can be trained based on a fourth training sample set. The training samples in the fourth training sample set can be videos with sign language, and the true labels of the training samples in the fourth training sample set can be text content corresponding to the sign language in the video.

[0062] In some embodiments, the sign language recognition model may be a neural network model, such as a correlation network (CorrNet) model.

[0063] It should be noted that, through the above method, the needs of deaf-mute users can be accurately understood and personalized services can be provided to deaf-mute users, thereby improving the applicability of this application.

[0064] Optionally, in the information processing method provided in the embodiment of the present application, a process demonstration video is displayed to the user, including: if the business demand information is determined based on the user's sign language video, generating a sign language demonstration video of the target business according to the process text information associated with the target business; integrating the sign language demonstration video and the process demonstration video to obtain the target demonstration video; and displaying the target demonstration video to the user.

[0065] Optionally, when the business demand information is determined based on the user's sign language video, it is determined that the user is a deaf-mute user. In this case, it is determined that a mobile game demonstration video needs to be generated for the user. For example, the target processing system can obtain a sign language video generation model, and then input the process text information associated with the target business into the sign language video generation model, and perform sign language video generation processing according to the process text information through the sign language video generation model, thereby obtaining a sign language demonstration video of the target business. In some embodiments, the sign language video generation model is a neural network model, for example, the sign language video generation model can be a Sign LLM model.

[0066] Optionally, the sign language video generation model may be obtained by training based on the fifth training sample set. The training samples in the fifth training sample set may be text content, and the true labels of the training samples in the fifth training sample set may be sign language videos corresponding to the text content.

[0067] Optionally, after obtaining the sign language demonstration video, the target processing system can integrate the sign language demonstration video and the process demonstration video to obtain the target demonstration video. For example, the sign language demonstration video is imported into the corners of the process demonstration video (such as the upper left corner, the upper right corner, the lower left corner, the lower right corner, etc.) to obtain the target demonstration video, thereby showing the target demonstration video to the user. Optionally, if there are multiple process demonstration videos, the multiple process demonstration videos can be spliced ​​into multiple to obtain a complete process demonstration video, and then the sign language demonstration video can be imported into the corners of the complete process demonstration video to obtain the target demonstration video.

[0068] In some embodiments, the target processing system may also import the process text information into the target demonstration video to obtain a processed target demonstration video, thereby displaying the processed target demonstration video to the user.

[0069] It should be noted that, through the above method, when it is determined that the user is a deaf-mute user, a demonstration video with sign language is generated for the user, thereby further improving the applicability of the present application and improving the user experience.

[0070] Optionally, in the information processing method provided in the embodiment of the present application, the first Vincent video model is obtained in the following manner: obtaining first process text information associated with each of the multiple first businesses, and obtaining multiple first process images associated with each of the first process text information; inputting the first process text information and the multiple first process images associated with the first process text information into the second Vincent video model to obtain a first demonstration video; inputting the first process text information into the third Vincent video model to obtain a second demonstration video, wherein the model parameter values ​​of the third Vincent video model and the second Vincent video model are the same; calculating the loss value based on a preset loss function, the first demonstration video, and the second demonstration video; when the loss value is greater than a preset threshold, updating the model parameter values ​​of the third Vincent video model, and repeatedly executing the step of inputting the first process text information into the updated third Vincent video model to obtain the second demonstration video, until the loss value is less than or equal to the preset threshold, the updated third Vincent video model is determined as the first Vincent video model.

[0071] Optionally, the first business is a business in a financial scenario, and the first process text information associated with each of the multiple first businesses may be preset in the database by the staff. Optionally, the first process image associated with the first process text information may be preset in the database by the staff, or may be generated according to the first process text information through a text graph model. That is, the first process text information and the first process image are equivalent to sample data, and the first business is equivalent to a sample business.

[0072] After obtaining the first process text information and the first process image, the target processing system can input the first process text information and the multiple first process images associated with the first process text information into the second text video model to obtain the first demonstration video. The second text video model is a pre-trained model.

[0073] After obtaining the first process text information, the target processing system may input the first process text information into a third cultural video model to obtain a second demonstration video, wherein the model parameter values ​​of the third cultural video model and the second cultural video model are the same.

[0074] Furthermore, the target processing system may calculate the loss value based on a preset loss function, the first demonstration video, and the second demonstration video. Optionally, the preset loss function may be an optical flow loss function, a mean square error function, a perceptual loss function, a structural similarity loss function, and the like.

[0075] Optionally, when the loss value is greater than a preset threshold, the target processing system may update the model parameter values ​​of the third cultural video model based on the loss value to obtain an updated third cultural video model, and then input the first process text information into the updated third cultural video model to obtain a new second demonstration video, and calculate a new loss value based on the new second demonstration video, the first demonstration video and a preset loss function, and then continue to determine whether the new loss value is greater than the preset threshold, and repeat this process until the loss value is less than or equal to the preset threshold, and then determine the updated third cultural video model as the first cultural video model.

[0076] It should be noted that by comparing the differences between the first demonstration video generated based on image labels and text labels and the second demonstration video generated based on text labels, the parameters of the third cultural video model can be optimized. The second demonstration video output by the updated third cultural video model can be closer to the first demonstration video, thereby improving the accuracy of the third cultural video model. In actual application, the role of image labels can be ignored, and the two-stage process of generating images from text and generating videos from images can be avoided. Instead, an accurate demonstration video can be generated directly through cultural videos in one step, thereby improving the efficiency of generating demonstration videos.

[0077] Optionally, in the information processing method provided in the embodiment of the present application, in the process of obtaining multiple first process images associated with each first process text information, the target processing system can input each first process text information into the text graph model respectively to obtain multiple first process images corresponding to each first process text information.

[0078] Optionally, the Wensheng graph model can be obtained by training with a second training sample set, the second training sample in the second training sample set is the second process text information, the real label corresponding to the second training sample is the second process image, and the second process text information and the second process image can be preset by the staff, that is, the second process text information and the second process image are equivalent to sample data, and the second process text information is different from the first process text information, and the second process image is different from the first process image.

[0079] Optionally, the target processing system may input each first process text information into the Wensheng graph model respectively, and then the Wensheng graph model performs image generation processing according to the first process text information, thereby obtaining a plurality of first process images corresponding to each first process text information. Optionally, the number of first process images corresponding to the first process text information may be the same as or different from the number of sub-text information in the first process text information.

[0080] In some embodiments, Figure 3is a flowchart of obtaining a first text video model through training according to an embodiment of the present application, such as Figure 3 As shown, the target processing system can first obtain the first process text information associated with each of the multiple first businesses, and then input each first process text information into the Vincent graph model to obtain multiple first process images corresponding to each first process text information, and then input the first process text information and the multiple first process images associated with the first process text information into the second Vincent video model to obtain a first demonstration video, and input the first process text information into the third Vincent video model to obtain a second demonstration video, thereby calculating the loss value based on the first demonstration video and the second demonstration video, updating the third Vincent video model based on the loss value, and then determining the updated third Vincent video model as the first Vincent video model when the loss value is less than or equal to a preset threshold.

[0081] It should be noted that, through the above process, it is avoided to manually generate the corresponding first process image for each first process text information, thereby further reducing the labor cost.

[0082] Optionally, in the information processing method provided in the embodiment of the present application, the second Vincent video model and the third Vincent video model are obtained in the following manner: obtaining multiple third demonstration videos, and obtaining the second process text information corresponding to each third demonstration video; using the third demonstration video as the first training sample, using the second process text information as the true label corresponding to the first training sample, and constructing a first training sample set based on the first training sample and the true label corresponding to the first training sample; training the initial Vincent video model based on the first training sample set to obtain the second Vincent video model, and constructing the third Vincent video model based on the model parameter values ​​of the second Vincent video model.

[0083] Optionally, the third demonstration video and the second process text information corresponding to the third demonstration video are preset by the staff, and the third demonstration video and the second process text information corresponding to the third demonstration video can be understood as sample data. The third demonstration video can be obtained by recording the business processing interface during the process of handling the business. In some embodiments, the second process text information is different from the first process text information.

[0084] Optionally, the target processing system can use the third demonstration video as the first training sample, the second process text information as the true label corresponding to the first training sample, and construct a first training sample set based on the first training sample and the true label corresponding to the first training sample, thereby training the initial Wensheng video model based on the first training sample set to obtain a second Wensheng video model.

[0085] Optionally, after obtaining the second language video model, the target processing system may construct a third language video model based on the model parameter values ​​of the second language video model, so that the model parameter values ​​of the third language video model are the same as those of the second language video model.

[0086] It should be noted that, through the above process, effective pre-training of the second and third cultural video models is achieved, thereby improving the accuracy of the first cultural video model obtained by training the third cultural video model, and further improving the accuracy of the generated process demonstration video.

[0087] Optionally, in the information processing method provided in the embodiment of the present application, the Wensheng graph model is obtained in the following manner: obtaining multiple second process text information, and obtaining the second process image corresponding to each second process text information; using the second process text information as the second training sample, using the second process image as the true label corresponding to the second training sample, and constructing a second training sample set based on the second training sample and the true label corresponding to the second training sample; training the initial Wensheng graph model based on the second training sample set to obtain the Wensheng graph model.

[0088] Optionally, the second process text information and the second process image may be preset by the staff, that is, the second process text information and the second process image are equivalent to sample data, and the second process text information is different from the first process text information, and the second process image is different from the first process image.

[0089] In some embodiments, the second process image may be extracted from the third demonstration video.

[0090] Optionally, the target processing system can use the second process text information as the second training sample, the second process image as the true label corresponding to the second training sample, and construct a second training sample set based on the second training sample and the true label corresponding to the second training sample, thereby training the initial text graph model based on the second training sample set to obtain the text graph model.

[0091] It should be noted that, through the above process, the processing accuracy of the trained Vincent graph model is effectively improved, thereby improving the training effect of the third Vincent video model, and further improving the model performance of the obtained first Vincent video model.

[0092] In an optional embodiment, in order to realize the above functions based on the original equipment of the target financial institution, a non-intrusive method can be adopted. For example, the mobile terminal is a tablet with a high-definition camera, and the entire device of Vincent Video is basically completely developed with software. Customers can input text content by typing to generate corresponding demonstration videos, and customers can operate according to the process on their smart phones; special groups, such as deaf-mute people, can input text content, and at the same time, they can also inform the business requirements to be handled in the form of sign language within the camera acquisition range, which will be converted into process text information by the model, and the requirements will be confirmed to be correct according to the text interaction, and then the corresponding demonstration sign language video will be generated.

[0093] It can be seen that the solution provided by this application achieves the purpose of automatically generating a process demonstration video according to user needs to guide users to handle business, and solves the problem of relying on manual guidance of users to handle business in related technologies, resulting in high labor costs. Thus, the effect of reducing labor costs is achieved.

[0094] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0095] Example 2

[0096] The embodiment of the present application also provides an information processing device. It should be noted that the information processing device of the embodiment of the present application can be used to execute the information processing method provided by the embodiment of the present application. The information processing device provided by the embodiment of the present application is introduced below.

[0097] According to an embodiment of the present application, there is also provided an information processing device for implementing the above information processing method. Figure 4 is a schematic diagram of an information processing device provided according to an embodiment of the present application, such as Figure 4 As shown, the device comprises:

[0098] The first acquisition module 401 is used to acquire the business demand information of the user of the business to be processed, and determine the process text information associated with the target business according to the business demand information, wherein the target business is the business pointed to by the business demand information, and the process text information is used to describe the process content of the target business;

[0099] The first processing module 402 is used to input the process text information associated with the target business into the first text-generated video model, and perform video generation processing based on the process text information through the first text-generated video model to obtain a process demonstration video of the target business;

[0100] The second processing module 403 is used to show the user a process demonstration video, wherein the process demonstration video is used to guide the user to handle the target business.

[0101] In an embodiment of the present application, by determining the process text information associated with the target business based on the business demand information of the user of the business to be processed, the process content of the business that the user expects to handle is effectively determined, and by inputting the process text information associated with the target business into the first text video model, a process demonstration video of the target business is obtained, and the use of artificial intelligence technology is realized to generate a corresponding video demonstration based on the text description of the relevant business process. By showing the process demonstration video to the user, process guidance for the user based on the automatically generated process demonstration video is realized, thereby reducing manual guidance work and reducing labor costs.

[0102] It can be seen that the solution provided by this application achieves the purpose of automatically generating a process demonstration video according to user needs to guide users to handle business, and solves the problem of relying on manual guidance of users to handle business in related technologies, resulting in high labor costs. Thus, the effect of reducing labor costs is achieved.

[0103] Optionally, in the information processing device provided in the embodiment of the present application, the first acquisition module also includes: a judgment submodule, which is used to determine whether a sign language collection request from the user is received when a business guidance request from the user is received; a collection submodule, which is used to collect the user's sign language video based on the image collection device when a sign language collection request from the user is received; and a recognition submodule, which is used to recognize and process the sign language video based on a sign language recognition model to obtain business demand information.

[0104] Optionally, in the information processing device provided in the embodiment of the present application, the second processing module also includes: a generation sub-module, which is used to generate a sign language demonstration video of the target business according to the process text information associated with the target business if the business demand information is determined based on the user's sign language video; a first processing sub-module, which is used to integrate the sign language demonstration video and the process demonstration video to obtain a target demonstration video; and a second processing sub-module, which is used to display the target demonstration video to the user.

[0105] Optionally, in the information processing device provided in the embodiment of the present application, the information processing device also includes: a second acquisition module, which is used to acquire first process text information associated with each of the multiple first businesses, and acquire multiple first process images associated with each of the first process text information; a third processing module, which is used to input the first process text information and the multiple first process images associated with the first process text information into the second Vincent video model to obtain a first demonstration video; a fourth processing module, which is used to input the first process text information into the third Vincent video model to obtain a second demonstration video, wherein the model parameter values ​​of the third Vincent video model and the second Vincent video model are the same; a calculation module, which is used to calculate the loss value based on a preset loss function, the first demonstration video and the second demonstration video; a fifth processing module, which is used to update the model parameter value of the third Vincent video model when the loss value is greater than a preset threshold, and repeatedly execute the step of inputting the first process text information into the updated third Vincent video model to obtain the second demonstration video, until the loss value is less than or equal to the preset threshold, and the updated third Vincent video model is determined as the first Vincent video model.

[0106] Optionally, in the information processing device provided in the embodiment of the present application, the second acquisition module also includes: a third processing submodule, which is used to input each first process text information into the text graph model respectively to obtain multiple first process images corresponding to each first process text information.

[0107] Optionally, in the information processing device provided in the embodiment of the present application, the information processing device also includes: a third acquisition module, used to acquire multiple third demonstration videos, and acquire the second process text information corresponding to each third demonstration video; a sixth processing module, used to use the third demonstration video as the first training sample, and the second process text information as the true label corresponding to the first training sample, and construct a first training sample set based on the first training sample and the true label corresponding to the first training sample; a seventh processing module, used to train an initial Vincent video model based on the first training sample set to obtain a second Vincent video model, and construct a third Vincent video model based on the model parameter values ​​of the second Vincent video model.

[0108] Optionally, in the information processing device provided in the embodiment of the present application, the information processing device also includes: a fourth acquisition module, used to acquire multiple second process text information, and acquire the second process image corresponding to each second process text information; an eighth processing module, used to use the second process text information as the second training sample, and the second process image as the true label corresponding to the second training sample, and construct a second training sample set based on the second training sample and the true label corresponding to the second training sample; a ninth processing module, used to train the initial Wensheng graph model based on the second training sample set to obtain a Wensheng graph model.

[0109] It should be noted that the first acquisition module 401, the first processing module 402, and the second processing module 403 correspond to steps S201 to S203 in Example 1, and the three modules and the corresponding steps implement the same examples and application scenarios, but are not limited to the contents disclosed in the above-mentioned Example 1. It should be noted that the above-mentioned modules or units may be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n), and the above-mentioned modules may also be part of the device and may be run in the computer terminal 10 provided in Example 1.

[0110] Example 3

[0111] An embodiment of the present application may provide an electronic device, Figure 5 is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 5 As shown, the electronic device may include: one or more ( Figure 5 (only one is shown) processor 1002, memory 1004, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0112] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned method. The memory 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 may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the 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.

[0113] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: obtain the business demand information of the user who is to handle the business, and determine the process text information associated with the target business based on the business demand information, wherein the target business is the business pointed to by the business demand information, and the process text information is used to describe the process content of the target business; input the process text information associated with the target business into the first text video model, and perform video generation processing based on the process text information through the first text video model to obtain a process demonstration video of the target business; show the process demonstration video to the user, wherein the process demonstration video is used to guide the user to handle the target business.

[0114] The processor can also call the information and applications stored in the memory through the transmission device to perform the following steps: when receiving the user's business guidance request, determine whether the user's sign language collection request is received; when receiving the user's sign language collection request, collect the user's sign language video based on the image acquisition device; based on the sign language recognition model, recognize and process the sign language video to obtain business demand information.

[0115] The processor can also call the information and applications stored in the memory through the transmission device to perform the following steps: if the business demand information is determined based on the user's sign language video, generate a sign language demonstration video of the target business based on the process text information associated with the target business; integrate the sign language demonstration video and the process demonstration video to obtain the target demonstration video; and display the target demonstration video to the user.

[0116] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: obtain the first process text information associated with each of the multiple first businesses, and obtain the multiple first process images associated with each of the first process text information; input the first process text information and the multiple first process images associated with the first process text information into the second Vincent video model to obtain a first demonstration video; input the first process text information into the third Vincent video model to obtain a second demonstration video, wherein the model parameter value of the third Vincent video model is the same as that of the second Vincent video model; calculate the loss value based on a preset loss function, the first demonstration video and the second demonstration video; when the loss value is greater than a preset threshold, update the model parameter value of the third Vincent video model, and repeatedly perform the step of inputting the first process text information into the updated third Vincent video model to obtain the second demonstration video, until the loss value is less than or equal to the preset threshold, and the updated third Vincent video model is determined as the first Vincent video model.

[0117] The processor may also call the information and application program stored in the memory through the transmission device to perform the following steps: input each first process text information into the text graph model respectively to obtain multiple first process images corresponding to each first process text information.

[0118] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: obtain multiple third demonstration videos, and obtain the second process text information corresponding to each third demonstration video; use the third demonstration video as the first training sample, use the second process text information as the true label corresponding to the first training sample, and construct a first training sample set based on the first training sample and the true label corresponding to the first training sample; train the initial Wensheng video model based on the first training sample set to obtain the second Wensheng video model, and construct a third Wensheng video model based on the model parameter values ​​of the second Wensheng video model.

[0119] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: obtain multiple second process text information, and obtain the second process image corresponding to each second process text information; use the second process text information as the second training sample, use the second process image as the real label corresponding to the second training sample, and construct a second training sample set based on the second training sample and the real label corresponding to the second training sample; train the initial Wensheng graph model based on the second training sample set to obtain the Wensheng graph model.

[0120] In an embodiment of the present application, by determining the process text information associated with the target business based on the business demand information of the user of the business to be processed, the process content of the business that the user expects to handle is effectively determined, and by inputting the process text information associated with the target business into the first text video model, a process demonstration video of the target business is obtained, and the use of artificial intelligence technology is realized to generate a corresponding video demonstration based on the text description of the relevant business process. By showing the process demonstration video to the user, process guidance for the user based on the automatically generated process demonstration video is realized, thereby reducing manual guidance work and reducing labor costs.

[0121] It can be seen that the solution provided by this application achieves the purpose of automatically generating a process demonstration video according to user needs to guide users to handle business, and solves the problem of relying on manual guidance of users to handle business in related technologies, resulting in high labor costs. Thus, the effect of reducing labor costs is achieved.

[0122] It can be understood by those skilled in the art that Figure 5 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 (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 5 The structure of the electronic device is not limited. Figure 5 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 5 Different configurations shown.

[0123] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0124] Example 4

[0125] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the information processing method provided in the first embodiment.

[0126] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0127] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing the program of the information processing method steps.

[0128] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0129] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0130] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that 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, which can be electrical or other forms.

[0131] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0132] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0133] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, 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, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0134] The above is only a preferred implementation 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. An information processing method, characterized in that: include: Acquire business demand information of a user of a business to be handled, and determine process text information associated with a target business according to the business demand information, wherein the target business is the business pointed to by the business demand information, and the process text information is used to describe the process content of the target business; Inputting the process text information associated with the target business into the first text-generated video model, and performing video generation processing based on the process text information by the first text-generated video model to obtain a process demonstration video of the target business; The process demonstration video is shown to the user, wherein the process demonstration video is used to guide the user to handle the target business.

2. The method according to claim 1, characterized in that: Obtain the business demand information of the user to be processed, including: In the case of receiving the service guidance request of the user, determining whether a sign language collection request of the user is received; When receiving a sign language acquisition request from the user, acquiring a sign language video of the user based on an image acquisition device; The sign language video is recognized and processed based on a sign language recognition model to obtain the business demand information.

3. The method according to claim 1, characterized in that Showing the process demonstration video to the user includes: If the business demand information is determined based on the user's sign language video, generating a sign language demonstration video of the target business according to the process text information associated with the target business; Integrate the sign language demonstration video and the process demonstration video to obtain a target demonstration video; The target demonstration video is shown to the user.

4. The method according to claim 1, characterized in that: The first cultural video model is obtained by: Acquire first process text information associated with each of the plurality of first services, and acquire a plurality of first process images associated with each of the first process text information; Inputting the first process text information and a plurality of first process images associated with the first process text information into a second video model to obtain a first demonstration video; Inputting the first process text information into a third cultural video model to obtain a second demonstration video, wherein the model parameter values ​​of the third cultural video model and the second cultural video model are the same; Calculating a loss value based on a preset loss function, the first demonstration video, and the second demonstration video; When the loss value is greater than a preset threshold, the model parameter value of the third Vincent video model is updated, and the step of inputting the first process text information into the updated third Vincent video model to obtain a second demonstration video is repeated, until the loss value is less than or equal to the preset threshold, the updated third Vincent video model is determined as the first Vincent video model.

5. The method according to claim 4, characterized in that Acquiring a plurality of first process images associated with each first process text information includes: Each first process text information is input into the text graph model respectively to obtain a plurality of first process images corresponding to each first process text information.

6. The method according to claim 4, characterized in that The second video model and the third video model are obtained by: Obtain multiple third demonstration videos, and obtain second process text information corresponding to each third demonstration video; Using the third demonstration video as a first training sample, using the second process text information as a true label corresponding to the first training sample, and constructing a first training sample set based on the first training sample and the true label corresponding to the first training sample; An initial Vincent video model is trained based on the first training sample set to obtain the second Vincent video model, and the third Vincent video model is constructed based on the model parameter values ​​of the second Vincent video model.

7. The method according to claim 5, characterized in that The Wensheng graph model is obtained in the following way: Acquire multiple second process text information, and acquire second process images corresponding to each second process text information; Using the second process text information as a second training sample, using the second process image as a true label corresponding to the second training sample, and constructing a second training sample set based on the second training sample and the true label corresponding to the second training sample; An initial text graph model is trained based on the second training sample set to obtain the text graph model.

8. An information processing device, characterized in that: include: A first acquisition module is used to acquire business demand information of a user of a to-be-processed business, and determine process text information associated with a target business according to the business demand information, wherein the target business is the business pointed to by the business demand information, and the process text information is used to describe the process content of the target business; A first processing module, configured to input the process text information associated with the target business into a first Wensheng video model, and perform video generation processing based on the process text information through the first Wensheng video model to obtain a process demonstration video of the target business; The second processing module is used to show the process demonstration video to the user, wherein the process demonstration video is used to guide the user to handle the target business.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is executed, the device where the computer-readable storage medium is located is controlled to execute the information processing method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: A memory storing an executable program; A processor, configured to run the program, wherein the program, when running, executes the information processing method according to any one of claims 1 to 7.

11. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the information processing method according to any one of claims 1 to 7 are implemented.

Images