Content subscription method and device, electronic equipment, readable storage medium and computer program product

Abstract

The invention provides a content subscription method and device, electronic equipment, a readable storage medium and a computer program product, and relates to the field of intelligent search, in particular to the field of content subscription based on a large model. According to the implementation scheme, initial user intention data is obtained based on initial user subscription information by using an intention recognition model; obtaining user intention result data based on the initial user intention data; determining an information source corresponding to the user intention result data; and obtaining subscription content corresponding to the user intention result data in the information source.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent search, and in particular to the field of content subscription based on a large model, and specifically to a content subscription method, device, electronic device, computer-readable storage medium, and computer program product. Background Art

[0002] With the continuous development of computer technology, network information has also exploded. In view of the massive amount of Internet information, the way of obtaining information is also quietly changing. Subscription services provide users with personalized information subscription experience. Obtaining regularly updated content through subscription is currently a common way to obtain information. Although the existing technology can provide users with content subscription services through information aggregation, it has deficiencies in user experience and personalized services, especially limited support for accurate push and automated processing of diversified content.

[0003] Artificial intelligence is a discipline that studies how to use computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.). It includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions. Summary of the invention

[0004] The present disclosure provides a content subscription method, apparatus, electronic device, computer-readable storage medium, and computer program product.

[0005] According to one aspect of the present disclosure, a content subscription method is provided, comprising: utilizing an intent recognition model to obtain initial user intent data based on initial user subscription information; obtaining user intent result data based on the initial user intent data; determining an information source corresponding to the user intent result data; and obtaining subscription content corresponding to the user intent result data in the information source.

[0006] According to a second aspect of the present disclosure, a content subscription device is provided, comprising: an initial user intention data acquisition module, used to obtain initial user intention data based on initial user subscription information by utilizing an intention recognition model; a user intention result data acquisition module, used to obtain user intention result data based on the initial user intention data; an information source acquisition module, used to determine an information source corresponding to the user intention result data; and a subscription content acquisition module, used to obtain subscription content corresponding to the user intention result data in the information source.

[0007] According to a third aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned content subscription method.

[0008] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the processor implements the content subscription method as described above.

[0009] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program implements the above-mentioned content subscription method when executed by a processor.

[0010] According to one or more embodiments of the present disclosure, an intent recognition model is used to analyze the user's intent, dynamically adjust the content subscription source and recommendation direction, and provide an efficient automatic content subscription method and device.

[0011] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings exemplarily illustrate the embodiments and constitute a part of the specification, and together with the text description of the specification, are used to explain the exemplary implementation of the embodiments. The embodiments shown are for illustrative purposes only and do not limit the scope of the claims. In all drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0013] Figure 1 A schematic diagram showing an exemplary system in which the various methods described herein may be implemented according to an embodiment of the present disclosure;

[0014] Figure 2 A flow chart of a content subscription method according to an embodiment of the present disclosure is shown;

[0015] Figure 3 Shown according to Figure 2 The training step diagram of the intent recognition model in step S202 is shown;

[0016] Figure 4 A block diagram of a content subscription device according to an embodiment of the present disclosure is shown;

[0017] Figure 5 A block diagram of an intent recognition model according to an embodiment of the present disclosure is shown;

[0018] Figure 6 A structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0019] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0020] In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, temporal relationship, or importance relationship of these elements, and such terms are only used to distinguish one element from another element. In some examples, the first element and the second element may refer to the same instance of the element, and in some cases, based on the description of the context, they may also refer to different instances.

[0021] The terms used in the description of various examples in this disclosure are only for the purpose of describing specific examples and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element can be one or more. In addition, the term "and / or" used in this disclosure covers any one of the listed items and all possible combinations.

[0022] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0023] Figure 1 FIG. 1 is a schematic diagram of an exemplary system 100 in which various methods and apparatuses described herein may be implemented according to an embodiment of the present disclosure. Figure 1 , the system 100 includes one or more client devices 101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. The client devices 101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.

[0024] In an embodiment of the present disclosure, the server 120 may run one or more services or software applications that enable execution of the content subscription method.

[0025] In some embodiments, server 120 may also provide other services or software applications, which may include non-virtualized environments and virtualized environments. In some embodiments, these services may be provided as web-based services or cloud services, such as provided to users of client devices 101, 102, 103, 104, 105, and / or 106 under a software as a service (SaaS) model.

[0026] exist Figure 1 In the configuration shown, the server 120 may include one or more components that implement the functions performed by the server 120. These components may include software components, hardware components, or a combination thereof that can be executed by one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 may in turn utilize one or more client applications to interact with the server 120 to utilize the services provided by these components. It should be understood that a variety of different system configurations are possible, which may differ from the system 100. Therefore, Figure 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

[0027] The user may use client devices 101, 102, 103, 104, 105 and / or 106 to subscribe to content. The client device may provide an interface that enables the user of the client device to interact with the client device. The client device may also output information to the user via the interface. Figure 1 Only six client devices are depicted, but one skilled in the art will appreciate that the present disclosure may support any number of client devices.

[0028] Client devices 101, 102, 103, 104, 105 and / or 106 may include various types of computer devices, such as portable handheld devices, general-purpose computers (such as personal computers and laptop computers), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, game systems, thin clients, various messaging devices, sensors or other sensing devices, etc. These computer devices may run various types and versions of software applications and operating systems, such as MICROSOFT Windows, APPLE iOS, UNIX-like operating systems, Linux or Linux-like operating systems (such as GOOGLE Chrome OS); or include various mobile operating systems, such as MICROSOFT Windows Mobile OS, iOS, Windows Phone, Android. Portable handheld devices may include cellular phones, smart phones, tablet computers, personal digital assistants (PDAs), etc. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. Game systems may include various handheld game devices, Internet-enabled game devices, etc. Client devices are capable of executing various different applications, such as various Internet-related applications, communication applications (such as email applications), short message service (SMS) applications, and may use various communication protocols.

[0029] The network 110 may be any type of network known to those skilled in the art that may support data communications using any of a variety of available protocols, including but not limited to TCP / IP, SNA, IPX, etc. By way of example only, the one or more networks 110 may be a local area network (LAN), an Ethernet-based network, a token ring, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a blockchain network, a public switched telephone network (PSTN), an infrared network, a wireless network (e.g., Bluetooth, WIFI), and / or any combination of these and / or other networks.

[0030] Server 120 may include one or more general purpose computers, dedicated server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running virtual operating systems, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that may be virtualized to maintain a server's virtual storage device). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0031] The computing units in the server 120 may run one or more operating systems including any of the above operating systems and any commercially available server operating systems. The server 120 may also run any of a variety of additional server applications and / or middle-tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

[0032] In some implementations, server 120 may include one or more applications to analyze and consolidate data feeds and / or event updates received from users of client devices 101, 102, 103, 104, 105, and / or 106. Server 120 may also include one or more applications to display data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and / or 106.

[0033] In some embodiments, the server 120 may be a server of a distributed system, or a server combined with a blockchain. The server 120 may also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. A cloud server is a host product in a cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and virtual private servers (VPS) services.

[0034] The system 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. The databases 130 may reside in various locations. For example, the database used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. The databases 130 may be of different types. In some embodiments, the databases used by the server 120 may be, for example, relational databases. One or more of these databases may store, update, and retrieve data to and from the databases in response to commands.

[0035] In some embodiments, one or more of the databases 130 may also be used by applications to store application data. The databases used by the applications may be different types of databases, such as a key-value store, an object store, or a conventional store backed by a file system.

[0036] Figure 1The system 100 may be configured and operated in various ways to enable the application of various methods and apparatuses described in the present disclosure.

[0037] Figure 2 2 is a flowchart showing a content subscription method 200 according to an embodiment of the present disclosure. Figure 2 As shown, the content subscription method may include: step S202, using the intent recognition model to obtain initial user intent data based on initial user subscription information; step S204, obtaining user intent result data based on the initial user intent data; step S206, determining an information source corresponding to the user intent result data; and, step S208, obtaining subscription content corresponding to the user intent result data in the information source.

[0038] In the content subscription method according to the embodiment of the present disclosure, an intent recognition model is utilized to analyze the user subscription intent based on the initial user subscription information, and the source of content subscription is dynamically adjusted according to the analysis result to provide users with personalized content subscription based on the user subscription intent, thereby effectively improving the accuracy of content subscription.

[0039] In some embodiments, in step S202, the initial user subscription information may be text information input by the user to indicate subscription, for example, it may be "Please push me news about AI technology in the past day at 10 o'clock today"; it may also be voice information, picture information, and other formats of information that can be used to indicate content subscription.

[0040] In some embodiments, in step S204, obtaining user intention result data based on the initial user intention data includes: in response to determining that there is first modification request data in the initial user intention data, obtaining first subscription modification information corresponding to the first modification request data; and based on the initial user subscription information and the first subscription modification information, obtaining first user intention update data, and setting the first user intention update data as the user intention result data.

[0041] Exemplarily, in response to the initial subscription information sent by the user as "Push the singing competition essays of the past day to me every day", according to the first modification request data, a message is sent to the user saying "Please provide the specific time for push, such as 9 am or 3 pm".

[0042] In this embodiment, for scenarios where the initial user subscription information is insufficient to determine the user's intention, the user is prompted to supplement or modify the subscription information by sending the first modification request data, thereby accurately analyzing the user's subscription intention and effectively improving the robustness of the content subscription method.

[0043] In some embodiments, obtaining the first user intention update data based on the initial user subscription information and the first subscription modification information includes: setting the first subscription modification information as user subscription modification information; executing user subscription information modification judgment, the executing user subscription information modification judgment includes: using the intention recognition model to obtain second user intention update data based on the initial user subscription information and the current user subscription modification information, and setting the second user intention update data as the user intention result data; in response to determining that the user intention result data has second modification request data, obtaining second subscription modification information corresponding to the second modification request data; and updating the user subscription modification information based on the current user subscription modification information and the second subscription modification information; and looping the executing user subscription modification information judgment until it is determined that the user intention result data does not have modification request data.

[0044] In this embodiment, for scenarios where the initial user subscription information is insufficient to determine the user's intention, multiple rounds of prompts are provided to supplement the subscription information until the user's subscription intention can be clearly determined, thereby improving the accuracy of content subscription.

[0045] In some embodiments, the first modification request data includes at least one of supplemental request data and replacement request data, and the second modification request data includes at least one of supplemental request data and replacement request data.

[0046] In this embodiment, for scenarios where the subscription information is missing or unclear, information supplementation and information modification prompts are provided to improve the accuracy of content subscription.

[0047] Figure 3 Shown according to Figure 2 The training steps of the intent recognition model in step S202 are shown in FIG. Figure 3 As shown, the intent recognition model is trained through the following steps: step S302, obtaining an intent word slot library and a model training sample; step S304, processing the model training sample to obtain training sample data, wherein the training sample data includes model role data, subscription information sample data, scenario limitation data, and sample intent data corresponding to the subscription information sample data; and step S306, training the intent recognition model based on the intent word slot library and the training sample data.

[0048] In this embodiment, the model is trained in a targeted manner according to subscription indication sample data and intent word slot library under specified roles and limited scenarios to improve the adaptability of the intent recognition model, and the trained model is scored based on the first sample intent data to improve the generalization ability of the model.

[0049] In some embodiments, the intention word slot library is composed of an intention word slot sequence, and the intention word slot sequence includes an intention, an intention description corresponding to the intention, and an intention word slot.

[0050] Exemplarily, corresponding to the intent of "playing music", the intent description is "the user requires the system to remind the user to complete something, or the user requires the system to complete a specified task at a specific time, or the user requires to subscribe to certain content", and the corresponding intent word slots include "singer", "song title" and "music type description"; the intent word slot value corresponding to the intent word slot "singer" is the singer of the song the user wants to play, the intent word slot value corresponding to the intent word slot "song title" is the name of the song the user wants to play, and the intent word slot value corresponding to the intent word slot "music type description" is a description of the music type and style of the song the user wants to play.

[0051] In some embodiments, the model training samples include prompt corpus training samples and predefined training samples. The model training samples include model role samples, subscription information samples, scenario definition samples, and intent description samples corresponding to the subscription information sample data.

[0052] Exemplarily, the model training sample is: "You are an expert specializing in task-based dialogue systems, and have rich experience in multiple rounds of rewriting, intent recognition, intent word slot filling or modification, and multiple rounds of clarification guidance; I will give you a dialogue context (user input and system response), and you need to complete the following tasks based on the dialogue context and the intent word slot"; among them, "expert specializing in task-based dialogue systems" is a model role sample, "has rich experience in multiple rounds of rewriting, intent recognition, intent word slot filling or modification, and multiple rounds of clarification guidance" is a scenario-limited sample, "user input" in the "context" is a subscription information sample, and "system response" in the "context" is an intent description sample.

[0053] In this embodiment, the prompt corpus training samples ensure the number of training samples, and the predefined training samples can supplement the scenarios not covered by the prompt corpus training samples, which helps the intent recognition model learn more comprehensive features and patterns, thereby improving the adaptability of the intent recognition model.

[0054] In some embodiments, the training of the intent recognition model based on the intent word slot library and the training sample data includes: determining whether at least one intent word slot in the intent word slot library exists in the subscription information sample data; in response to determining that the subscription information sample data does not contain at least one intent word slot corresponding to the intent word slot library, sending subscription information modification request data corresponding to the subscription information sample data, otherwise, obtaining the sample intent result data corresponding to at least one intent word slot in the intent word slot library; and using a dialogue capability scoring model to calculate the correlation between the user sample intent result data and the sample intent data, wherein the training of the intent recognition model is terminated when the correlation meets a set threshold.

[0055] Exemplarily, the scoring corpus sample is "You are a master of scoring large-model dialogue capabilities, especially scoring relevance. Your scoring criteria will strictly follow the following evaluation dimensions, score the user sample intent result data and sample intent data, and obtain the relevance value"; when the relevance value is greater than or equal to 9, it indicates that the evaluation dimension is highly correlated; when the relevance value is greater than or equal to 6 and less than 9, it indicates that the evaluation dimension is partially correlated; when the relevance value is less than 6, it indicates that the evaluation dimension is not correlated. The set threshold for the end of training of the intent recognition model is that the value of the relevance falls within the scoring range for the evaluation dimension with a highly correlated degree. The above description is only exemplary and is not intended to limit the setting of the threshold for the end of training of the intent recognition model.

[0056] In this embodiment, when the training sample data is insufficient to express the user's intention, an intent clarification is sent to the user; when the intent word slot value in the training sample data and the intent word slot do not match or the intent word slot value is missing, an intent word slot clarification is sent, which can effectively improve the accuracy of content subscription.

[0057] In some embodiments, obtaining the sample intent result data corresponding to at least one intent word slot in the intent word slot library includes: determining whether there is a first intent word slot value corresponding to the at least one intent word slot in the subscription information sample data; in response to determining that there is no first intent word slot value corresponding to the at least one intent word slot in the subscription information sample data, based on the logical relationship between the subscription information sample data and the first intent word slot value, sending subscription information modification request data corresponding to the first intent word slot value; in response to determining that there is a first intent word slot value corresponding to the at least one intent word slot in the training sample data, obtaining the intent word slot sequence corresponding to the first intent word slot in the intent word slot library; and obtaining sample intent result data based on the intent word slot sequence.

[0058] In this embodiment, the conversation ability scoring model is trained by using the relevance corpus to improve the accuracy of the conversation ability scoring model, thereby ensuring the effectiveness of the user intent recognition model training.

[0059] In some embodiments, the dialogue ability scoring model is trained based on a large model and a relevance scoring corpus.

[0060] In this embodiment, the scoring corpus is composed of scoring corpus samples. For example, the scoring corpus samples are "You are a master of scoring large model dialogue ability, especially scoring relevance. Your scoring criteria will strictly follow the following evaluation dimensions to score the relevance of ideal answers and actual answers"; and indicate that the ideal answer is "The weather is good today", and the actual answer is "Today is 25 degrees, the weather is clear, and there is no wind"; set the evaluation dimensions to include extremely high relevance, partial relevance, and no relevance, and provide scoring ranges corresponding to different evaluation dimensions.

[0061] In this embodiment, the conversation ability scoring model is trained by using the relevance corpus to improve the accuracy of the conversation ability scoring model, thereby ensuring the effectiveness of the user intent recognition model training.

[0062] In some embodiments, the logical relationship between the user conversation sample data and the first intent word slot value of the at least first intent word slot includes at least one of replacing the intent word slot value and supplementing the intent word slot value.

[0063] In this embodiment, for the case where the intent word slot value is missing or the intent word slot value is unclear in the training sample data, intent word slot replacement and supplement functions are provided to improve the robustness of the intent recognition model.

[0064] In some embodiments, the content subscription method further includes: after obtaining the subscription content corresponding to the user intention result data in the information source, using a generative artificial intelligence model to obtain a content overview corresponding to the subscription content. In this embodiment, the content overview can also be personalized according to the user's reading habits and needs to highlight key information.

[0065] In this embodiment, a content overview of the subscribed content is extracted to provide the user with clear content push, thereby improving the user experience and reducing the loss of data transmission resources in the process of pushing the subscribed content, thereby improving the efficiency of content subscription.

[0066] In some embodiments, after extracting the content overview of the subscribed content, the user subscribed content and the content overview corresponding to the subscribed content are pushed to the user in accordance with the user's instructions, and multi-channel push is achieved through the data synchronization function of the mobile application. The pushed subscription content supports seamless switching between multiple devices, ensuring that the user can obtain the latest subscription information anytime and anywhere, effectively improving the convenience of content subscription.

[0067] In the content subscription method of the embodiment of the present invention, through the intent recognition model, based on the initial user subscription information and the subscription information supplemented or modified by the user, the user's subscription intention can be accurately analyzed, and the content subscription source can be dynamically adjusted according to the analysis results, so as to provide users with personalized content subscription based on user intention, thereby effectively improving the accuracy of content subscription.

[0068] Figure 4 4 is a block diagram showing a content subscription device 400 according to an embodiment of the present disclosure. Figure 4 As shown, the content subscription device 400 includes: an initial user intention data acquisition module 402, which is used to obtain initial user intention data based on initial user subscription information using an intention recognition model; a user intention result data acquisition module 404, which is used to obtain user intention result data based on the initial user intention data; an information source acquisition module 406, which is used to determine an information source corresponding to the user intention result data; and a subscription content acquisition module 408, which is used to obtain subscription content corresponding to the user intention result data in the information source.

[0069] It should be noted that Figure 4 The various modules of the apparatus 400 shown in FIG. Figure 2 The steps in the method 200 described above correspond to each other. Therefore, the operations, features and advantages described above for the method 200 are also applicable to the device 400 and the modules and units included therein. For the sake of brevity, some operations, features and advantages are not repeated here.

[0070] Figure 5 is a block diagram showing a graph recognition model according to an embodiment of the present disclosure. Figure 5 As shown, the intent recognition model includes: a training sample acquisition unit 502, used to acquire an intent word slot library and a model training sample; a sample intent data acquisition unit 504, used to process the model training sample to obtain training sample data, wherein the training sample data includes model role data, subscription information sample data, scenario limitation data and sample intent data corresponding to the subscription information sample data; and a model training unit 506, used to train the intent recognition model based on the intent word slot library and the training sample data.

[0071] It should be noted that Figure 5The various modules of the apparatus 500 shown in FIG. Figure 3 The steps in the method 300 described above correspond to each other. Therefore, the operations, features and advantages described above for the method 300 are also applicable to the device 500 and the modules and units included therein. For the sake of brevity, some operations, features and advantages are not repeated here.

[0072] According to an embodiment of the present disclosure, an electronic device, a readable storage medium and a computer program product are also provided.

[0073] refer to Figure 6 , a block diagram of an electronic device 600 that can be used as a server or client of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0074] like Figure 6 As shown, the electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0075] Multiple components in the electronic device 600 are connected to the I / O interface 605, including: an input unit 606, an output unit 607, a storage unit 608, and a communication unit 609. The input unit 606 can be any type of device that can input information to the electronic device 600. The input unit 606 can receive input digital or character information and generate key signal input related to user settings and / or function control of the electronic device, and can include but is not limited to a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and / or a remote controller. The output unit 607 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 608 can include but is not limited to a disk, an optical disk. The communication unit 609 allows the electronic device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth device, an 802.11 device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0076] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as method 200. For example, in some embodiments, the method 200 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the method 200 described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the method 200 in any other appropriate manner (e.g., by means of firmware).

[0077] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0078] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0079] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0080] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0081] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0082] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0083] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be performed in parallel, sequentially or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document is not limited here.

[0084] Although the embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above-mentioned methods, systems and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but only by the claims after authorization and their equivalent scope. Various elements in the embodiments or examples can be omitted or replaced by their equivalent elements. In addition, each step can be performed in an order different from that described in the present disclosure. Further, the various elements in the embodiments or examples can be combined in various ways. It is important that with the evolution of technology, many elements described herein can be replaced by equivalent elements that appear after the present disclosure.

Claims

1. A content subscription method, comprising: Using the intent recognition model, initial user intent data is obtained based on initial user subscription information; Obtaining user intention result data based on the initial user intention data; Determining an information source corresponding to the user intent result data; as well as Obtain subscription content corresponding to the user intent result data in the information source.

2. The content subscription method according to claim 1, wherein: The obtaining of user intention result data based on the initial user intention data comprises: In response to determining that first modification request data exists in the initial user intent data, acquiring first subscription modification information corresponding to the first modification request data; and Based on the initial user subscription information and the first subscription modification information, first user intention update data is obtained, and the first user intention update data is set as the user intention result data.

3. The content subscription method according to claim 2, wherein: The obtaining the first user intention update data based on the initial user subscription information and the first subscription modification information comprises: Setting the first subscription modification information as user subscription modification information; Executing a user subscription information modification judgment, wherein the executing user subscription information modification judgment comprises: Using the intention recognition model, obtaining second user intention update data based on the initial user subscription information and the current user subscription modification information, and setting the second user intention update data as the user intention result data; In response to determining that the user intention result data has second modification request data, acquiring second subscription modification information corresponding to the second modification request data; and updating the user subscription modification information based on the current user subscription modification information and the second subscription modification information; and The execution of the user subscription modification information judgment is looped until it is determined that no modification request data exists in the user intention result data.

4. The content subscription method according to claim 3, wherein: The first modification request data includes at least one of supplement request data and replacement request data, and the second modification request data includes at least one of supplement request data and replacement request data.

5. The content subscription method according to claim 1, wherein: The intent recognition model is trained through the following steps: Obtain the intent word slot library and model training samples; Processing the model training samples to obtain training sample data, wherein the training sample data includes model role data, subscription information sample data, scenario definition data, and sample intent data corresponding to the subscription information sample data; and The intent recognition model is trained based on the intent word slot library and the training sample data.

6. The content subscription method according to claim 5, wherein: The model training samples include prompt corpus training samples and predefined training samples.

7. The content subscription method according to claim 5 or 6, wherein: The training of the intent recognition model based on the intent word slot library and the training sample data includes: Determine whether at least one intent word slot in the intent word slot library exists in the subscription information sample data; In response to determining that the subscription information sample data does not contain at least one intent word slot in the intent word slot library, sending subscription information modification request data corresponding to the subscription information sample data, otherwise, Acquire the sample intent result data corresponding to at least one intent word slot in the intent word slot library; and The dialogue ability scoring model is used to calculate the correlation between the user sample intention result data and the sample intention data, wherein the training of the intention recognition model is terminated when the correlation meets a set threshold.

8. The content subscription method according to claim 7, wherein: The obtaining of the sample intent result data corresponding to at least one intent word slot in the intent word slot library comprises: Determining whether there is a first intent word slot value corresponding to the at least one intent word slot in the subscription information sample data; In response to determining that a first intent word slot value corresponding to the at least one intent word slot does not exist in the subscription information sample data, based on a logical relationship between the subscription information sample data and the first intent word slot value, sending subscription information modification request data corresponding to the first intent word slot value; In response to determining that a first intention word slot value corresponding to the at least one intention word slot exists in the training sample data, obtaining an intention word slot sequence corresponding to the first intention word slot in the intention word slot library; and Sample intent result data is obtained based on the intent word slot sequence.

9. The content subscription method according to claim 7, wherein: The dialogue ability scoring model is trained based on a large model and a relevance scoring corpus.

10. The content subscription method according to claim 6, wherein: The logical relationship between the user conversation sample data and the first intention word slot value of the at least first intention word slot includes at least one of a replacement intention word slot value and a supplementary intention word slot value.

11. The content subscription method according to claim 1, wherein: The method further comprises: After obtaining the subscription content corresponding to the user intention result data in the information source, a generative artificial intelligence model is used to obtain a content overview corresponding to the subscription content.

12. A content subscription device, comprising: An initial user intention data acquisition module, used to obtain initial user intention data based on initial user subscription information using an intention recognition model; A user intention result data acquisition module, used to obtain user intention result data based on the initial user intention data; An information source acquisition module, used to determine the information source corresponding to the user intention result data; as well as The subscription content acquisition module is used to acquire the subscription content corresponding to the user intention result data in the information source.

13. The content subscription device according to claim 12, wherein: The user intention result data acquisition module further includes: A first submodule is configured to, in response to determining that first modification request data exists in the initial user intention data, obtain first subscription modification information corresponding to the first modification request data; and The second submodule is used to obtain first user intention update data based on the initial user subscription information and the first subscription modification information, and set the first user intention update data as the user intention result data.

14. The content subscription device according to claim 13, wherein: The second submodule further comprises: A module for setting the first subscription modification information as user subscription modification information; A module for executing a user subscription information modification judgment, wherein the module for executing a user subscription information modification judgment further comprises: A submodule for obtaining second user intention update data based on the initial user subscription information and the current user subscription modification information by using the intention recognition model, and setting the second user intention update data as the user intention result data; A submodule for acquiring second subscription modification information corresponding to the second modification request data in response to determining that the user intention result data has second modification request data; and A submodule for updating the user subscription modification information based on the current user subscription modification information and the second subscription modification information; and A module for looping the execution of user subscription modification information judgment until it is determined that the user intention result data does not contain modification request data.

15. The content subscription device according to claim 14, wherein: The first modification request data includes at least one of supplement request data and replacement request data, and the second modification request data includes at least one of supplement request data and replacement request data.

16. The content subscription device according to claim 12, wherein: The intent recognition model includes: A training sample acquisition unit is used to acquire the intent word slot library and model training samples; a sample intention data acquisition unit, configured to process the model training sample to obtain training sample data, wherein the training sample data includes model role data, subscription information sample data, scenario definition data, and sample intention data corresponding to the subscription information sample data; and A model training unit is used to train the intent recognition model based on the intent word slot library and the training sample data.

17. The content subscription device according to claim 16, wherein: The model training samples include prompt corpus training samples and predefined training samples.

18. The content subscription device according to claim 16 or 17, wherein: The model training unit further comprises: A first subunit is used to determine whether at least one intention word slot in the intention word slot library exists in the subscription information sample data; A second subunit is configured to, in response to determining that at least one intent word slot in the intent word slot library does not exist in the subscription information sample data, send subscription information modification request data corresponding to the subscription information sample data, otherwise, obtain the sample intent result data corresponding to at least one intent word slot in the intent word slot library; and The third subunit is used to calculate the correlation between the user sample intention result data and the sample intention data by using the dialogue ability scoring model, wherein the training of the intention recognition model is terminated when the correlation meets the set threshold.

19. The content subscription device according to claim 18, wherein: The second subunit further comprises: A unit for determining whether there is a first intent word slot value corresponding to the at least one intent word slot in the subscription information sample data; A unit for sending subscription information modification request data corresponding to the first intent word slot value based on a logical relationship between the subscription information sample data and the first intent word slot value in response to determining that the first intent word slot value corresponding to the at least one intent word slot does not exist in the subscription information sample data; In response to determining that a first intention word slot value corresponding to the at least one intention word slot exists in the training sample data, a unit of an intention word slot sequence corresponding to the first intention word slot in the intention word slot library is obtained; and A unit for obtaining sample intent result data based on the intent word slot sequence.

20. The content subscription device according to claim 18, wherein: The dialogue ability scoring model is trained based on a large model and a relevance scoring corpus.

21. The content subscription device according to claim 17, wherein: The logical relationship between the user conversation sample data and the first intention word slot value of the at least first intention word slot includes at least one of a replacement intention word slot value and a supplementary intention word slot value.

22. The content subscription device according to claim 12, wherein: The content subscription device also includes a content overview generation module, which is used to obtain a content overview corresponding to the subscription content corresponding to the user intention result data in the information source by using a generative artificial intelligence model.

23. An electronic device, comprising: at least one processor; as well as a memory communicatively coupled to the at least one processor; in The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 11.

24. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-11.

25. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images