Model processing method and device, equipment and storage medium

Abstract

The invention provides a model processing method and device, equipment and a storage medium. The method comprises: a terminal device sending a first message, the first message comprising: input information, and type information and / or task information, to request a network device to determine N first questions to input a first model, and further to receive a second message from the network device, the second message comprising M first questions determined based on a first prompt template and the input information, wherein N is a positive integer, the N first problems are part or all of the M first problems, and the prompt service is realized in the wireless network. Furthermore, the first prompt template is determined based on the type information and / or the task information, so that intelligent acquisition of the prompt template is realized, the use convenience of the model is improved, and the reasoning effect of the model is ensured.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a method, device, equipment and storage medium for model processing. Background Art

[0002] It is a common consensus that the 6th generation mobile networks (6G) will move towards the era of intelligent and inclusive communication. Large models, such as a large language model (LLM), are expected to become the foundation technology for intelligent and inclusive communication. It is expected that large models will be deployed in wireless networks in the future to achieve deep coupling of communication with perception, computing, and control.

[0003] Prompt is an important medium for users to interact with large models. Appropriate prompt templates will facilitate accurate description of problems, thereby improving the reasoning effect of large models. At present, prompt templates need to be downloaded and selected by users from the cloud, resulting in low convenience in using large models. In addition, the selection of prompt templates relies on user experience, which cannot guarantee the applicability of prompt templates and thus cannot ensure that problems described based on prompts can improve the reasoning effect of large models. Therefore, how to accurately determine prompt templates in wireless networks and then describe problems based on prompt templates to improve the convenience of model use and model reasoning effect is a problem that needs to be solved urgently. Summary of the invention

[0004] The embodiments of the present application provide a model processing method, device, equipment and storage medium, in order to accurately determine the prompt template in a wireless network, and then describe the problem based on the prompt template to improve the convenience of model use and the model reasoning effect.

[0005] In the first aspect, the present application provides a method for model processing. The execution subject of the method may be a terminal device or a component in the terminal device, such as a chip, a chip system or other functional module capable of calling and executing a program. For ease of understanding, the following exemplary description is given with the terminal device as the execution subject.

[0006] In an example of the first aspect, the method includes: a terminal device sends a first message, the first message includes: input information, and type information and / or task information, to request a network device to determine N first questions input into a first model, and then receive a second message from the network device, the second message includes M first questions determined based on a first prompt template and input information, wherein N is a positive integer, and the N first questions are part or all of the M first questions, and a prompt service is implemented in a wireless network. Furthermore, the first prompt template is determined based on type information and / or task information, which implements intelligent acquisition of prompt templates, improves the convenience of model use, and ensures the reasoning effect of the model.

[0007] In one possible implementation, the terminal device may send a third message to the first device, where the third message is used to request the first device to perform model reasoning based on N of the M first problems using the first model, thereby improving the convenience of using the model in the wireless network.

[0008] For the purpose of ensuring the accuracy of the prompt template matched, or ensuring the rationality of the first question, or reducing the complexity of model processing, etc., the first question may be screened to determine N first questions from the M first questions, such as for the purpose of ensuring the accuracy of the prompt template matched, or ensuring the rationality of the first question, or reducing the complexity of model processing, etc. Exemplarily, the terminal device sends a fourth message, the fourth message is used to request the second device to screen the M first questions through the first model, and receives a fifth message, the fifth message is used to indicate N first questions among the M first questions.

[0009] In a possible implementation, the N first questions are the first N first questions arranged in descending order of rationality scores after the first model scores the M first questions for rationality, so as to ensure the rationality of the first questions.

[0010] In a possible implementation, when the M first questions do not meet the preset conditions, in order to ensure that the first questions are suitable for input into the first model to perform model reasoning to meet the user's model reasoning requirements, further optimization can be performed to obtain questions that meet the preset conditions (such as the second question). Exemplarily, the terminal device sends a sixth message to the network device, the sixth message includes a first indication information, the first indication information is used to indicate that the M first questions do not meet the preset conditions, and receives a seventh message, the seventh message includes a second question, the second question is generated based on a second prompt template and input information, and the second prompt template is obtained by aggregating the M first prompt templates corresponding to the M first questions. The accuracy of the question generated by the second prompt template obtained after aggregating multiple first prompt templates is higher than the accuracy of the question generated using only one first prompt template, that is, a more accurate reasoning result can be obtained after inputting the first model.

[0011] Optionally, the sixth message may further include: input information, and type information and / or task information.

[0012] In one possible implementation, the second question includes a first vector and a second vector, the first vector is obtained based on input information, and the second vector is obtained based on vectors mapped by M first prompt templates. The second question is presented in the form of a vector to improve the accuracy of the question, that is, to improve the reasoning effect after the question is input into the model.

[0013] In a possible implementation, the terminal device sends an eighth message, where the eighth message is used to request the first device to perform model reasoning based on the second problem through the first model to improve the reasoning effect of the first model on the input information.

[0014] In another example of the first aspect, the method includes: a terminal device sends a first message, the first message is used to request a network device to determine a third question input into a first model, the first message includes: input information and type information, and receives a second message from the network device, the second message includes a third question, the third question is determined based on a vector generated by a prompt generation unit and the input information, the prompt generation unit corresponds to the type information, and provides a solution for realizing intelligent generation of soft prompts in wireless networks.

[0015] In one possible implementation, the third question includes a third vector and a fourth vector. The third vector is obtained according to the input information, and the fourth vector is generated by the prompt generation unit based on the input information. The third question is presented in the form of a vector to improve the accuracy of the question, that is, to improve the reasoning effect after the question is input into the model.

[0016] Based on the two examples of the first aspect above, optionally, the first message is carried in a non-access layer NAS message or a user plane message.

[0017] Based on the two examples of the first aspect above, optionally, the second message is carried in a NAS message.

[0018] Based on the two examples of the first aspect mentioned above, optionally, the terminal device receives a ninth message, which is used to indicate supported task information and / or supported large models, so as to synchronize network capability information about model processing between the network device and the terminal device.

[0019] In the second aspect, the present application provides a method for model processing, the execution subject of which may be a network device or a component in a network device, such as a chip, a chip system, or other functional module capable of calling and executing a program. Optionally, a functional module providing a prompt service may be deployed in the network device, or may be replaced with a functional module providing a prompt service. For ease of understanding, the following exemplary description is given with the network device as the execution subject.

[0020] In an example of the second aspect, the method includes: a network device receives a first message, the first message is used to request determination of N first questions input into a first model, N is a positive integer, the first message includes: input information, and type information and / or task information; the network device sends a second message, the second message includes M first questions, the N first questions are part or all of the M first questions, the first question is determined based on a first prompt template and the input information, and the first prompt template is determined based on the type information and / or task information.

[0021] In one possible implementation, the network device matches M first prompt templates in the template library according to the type information and / or task information, and determines the first question corresponding to the first prompt according to each first prompt template in the M first prompt templates and the input information.

[0022] In a possible implementation, the network device receives a fourth message, where the fourth message is used to request to screen the M first questions through the first model, and sends a fifth message, where the fifth message is used to indicate N first questions among the M first questions.

[0023] In a possible implementation, it also includes: the network device receives a sixth message, the sixth message includes first indication information, the first indication information is used to indicate that the M first questions do not meet the preset conditions, and sends a seventh message, the seventh message includes a second question, the second question is generated based on a second prompt template and input information, and the second prompt template is aggregated based on the M first prompt templates corresponding to the M first questions.

[0024] In a possible implementation manner, the sixth message further includes: input information, and type information and / or task information.

[0025] In a possible implementation, the method further includes: the network device aggregates M first prompt templates to obtain a second prompt template, and obtains a second question according to the second prompt template and input information.

[0026] In a possible implementation, the second question includes a first vector and a second vector, the first vector is obtained according to input information, and the second vector is obtained according to vectors mapped by M first prompt templates.

[0027] In another example of the second aspect, the method includes: a network device receives a first message, the first message is used to request determination of a third question input into the first model, the first message includes: input information and type information, and sends a second message, the second message includes a third question, the third question is determined based on a vector generated by a prompt generation unit and the input information, and the prompt generation unit corresponds to the type information.

[0028] In a possible implementation, the method further includes: the network device obtains a prompt generation unit corresponding to the type information, generates a vector according to the input information through the prompt generation unit, and then determines the third question according to the vector and the input information.

[0029] In a possible implementation, the third question includes a third vector and a fourth vector, the third vector is obtained according to the input information, and the fourth vector is generated by the prompt generation unit based on the input information.

[0030] Based on the foregoing two examples of the second aspect, optionally, the first message is carried in a non-access layer NAS message or a user plane message.

[0031] Based on the foregoing two examples of the second aspect, optionally, the second message is carried in a NAS message.

[0032] In a third aspect, the present application provides a method for model processing. The execution subject of the method may be a policy control function (PCF), such as a PCF module, or a device or network element deployed with a PCF. For ease of understanding, the following exemplary description is given with PCF as the execution subject.

[0033] The method includes: the PCF sends a ninth message, the ninth message is used to indicate supported task information and / or supported large models, so as to synchronize network capability information related to model processing.

[0034] Optionally, the PCF may obtain the task information and / or the large model supported by the network from the network device (such as a functional module providing prompt service in the network device).

[0035] In a fourth aspect, an embodiment of the present application provides a communication device, which includes a processing module and a transceiver module.

[0036] In an example of the fourth aspect, a processing module is used to determine a first message, wherein the first message is used to request a network device to determine N first questions input into a first model, where N is a positive integer, and the first message includes: input information, and type information and / or task information; a transceiver module is used to send the first message; the transceiver module is also used to receive a second message from the network device, wherein the second message includes M first questions, the N first questions are part or all of the M first questions, and the first questions are determined based on a first prompt template and the input information, and the first prompt template is determined based on the type information and / or the task information.

[0037] In a possible implementation, the transceiver module is further used to: send a third message, where the third message is used to request the first device to perform model reasoning based on N first questions among the M first questions through the first model.

[0038] In one possible implementation, the transceiver module is also used to: send a fourth message, which is used to request the second device to filter the M first questions through the first model; and receive a fifth message, which is used to indicate N first questions among the M first questions.

[0039] In one possible implementation, the transceiver module is also used to: send a sixth message, the sixth message including first indication information, the first indication information being used to indicate that the M first questions do not meet a preset condition; receive a seventh message, the seventh message including a second question, the second question being generated based on a second prompt template and the input information, the second prompt template being aggregated based on the M first prompt templates corresponding to the M first questions respectively.

[0040] In a possible implementation manner, the sixth message further includes: the input information, and the type information and / or the task information.

[0041] In a possible implementation, the second question includes a first vector and a second vector, the first vector is obtained according to the input information, and the second vector is obtained according to the vectors mapped by the M first prompt templates.

[0042] In a possible implementation, the transceiver module is further used to: send an eighth message, where the eighth message is used to request the first device to perform model reasoning based on the second problem through the first model.

[0043] In another example of the fourth aspect, the processing module is used to determine a first message, which is used to request the network device to determine a third question input into the first model, and the first message includes: input information, and type information; the transceiver module is used to send the first message; the transceiver module is also used to receive a second message from the network device, and the second message includes a third question, which is determined based on a vector generated by a prompt generation unit and the input information, and the prompt generation unit corresponds to the type information.

[0044] In a possible implementation, the third question includes a third vector and a fourth vector, the third vector is obtained according to the input information, and the fourth vector is generated by the prompt generation unit based on the input information.

[0045] Based on another example of the fourth aspect above, optionally, the first message is carried in a NAS message or a user plane message.

[0046] Based on another example of the fourth aspect above, optionally, the second message is carried in a NAS message.

[0047] In a possible implementation, the transceiver module is further used to receive a ninth message, where the ninth message is used to indicate supported task information and / or supported large models.

[0048] In a fifth aspect, an embodiment of the present application provides a communication device, including: a processing module and a transceiver module.

[0049] In an example of the fifth aspect, the transceiver module is used to receive a first message, the first message is used to request to determine N first questions input into a first model, N is a positive integer, and the first message includes: input information, and type information and / or task information; the processing module is used to determine M first questions, the N first questions are part or all of the M first questions, the first questions are determined based on a first prompt template and the input information, and the first prompt template is determined based on the type information and / or the task information; the transceiver module is also used to send a second message, the second message includes M first questions.

[0050] In one possible implementation, the processing module is specifically used to: match M first prompt templates in the template library according to the type information and / or the task information; and determine the first question corresponding to the first prompt according to each first prompt template in the M first prompt templates and the input information.

[0051] In a possible implementation, the transceiver module is also used to: receive a fourth message, the fourth message is used to request to filter the M first questions through the first model; send a fifth message, the fifth message is used to indicate N first questions among the M first questions.

[0052] In one possible implementation, the transceiver module is also used to: receive a sixth message, the sixth message including first indication information, the first indication information being used to indicate that the M first questions do not meet a preset condition; send a seventh message, the seventh message including a second question, the second question being generated based on a second prompt template and the input information, the second prompt template being aggregated based on the M first prompt templates corresponding to the M first questions respectively.

[0053] In a possible implementation manner, the sixth message further includes: the input information, and the type information and / or the task information.

[0054] In a possible implementation, the processing module is further used to: aggregate the M first prompt templates to obtain a second prompt template; and obtain the second question according to the second prompt template and the input information.

[0055] In a possible implementation, the second question includes a first vector and a second vector, the first vector is obtained according to the input information, and the second vector is obtained according to the vectors mapped by the M first prompt templates.

[0056] In another example of the fifth aspect, the transceiver module is used to receive a first message, the first message is used to request determination of a third question input into the first model, the first message including: input information and type information; the processing module is used to determine the third question, the third question is determined based on a vector generated by a prompt generation unit and the input information, the prompt generation unit corresponds to the type information; the transceiver module is also used to send a second message, the second message including the third question.

[0057] In a possible implementation, the processing module is specifically used to: obtain a prompt generation unit corresponding to the type information; generate a vector according to the input information through the prompt generation unit; and determine the third question according to the vector and the input information.

[0058] In a possible implementation, the third question includes a third vector and a fourth vector, the third vector is obtained according to the input information, and the fourth vector is generated by the prompt generation unit based on the input information.

[0059] In the two examples of the fifth aspect above, optionally, the first message is carried in a NAS message or a user plane message.

[0060] In the two examples of the fifth aspect above, optionally, the second message is carried in a NAS message.

[0061] In a sixth aspect, the present application provides a model processing device, including: a processing module, used to determine a ninth message, the ninth message is used to indicate supported task information and / or supported large models; a transceiver module, used to send the ninth message.

[0062] In a seventh aspect, an embodiment of the present application provides a communication device, comprising: a processor, configured to execute a method as described in the first aspect, the second aspect, the third aspect, or any possible implementation method by running a computer program or through a logic circuit.

[0063] In a possible implementation manner, the communication device further includes: a memory, wherein the memory is used to store the computer program.

[0064] In a possible implementation manner, the communication device further includes: a communication interface, where the communication interface is used to input and / or output signals.

[0065] In an eighth aspect, an embodiment of the present application provides a chip, comprising: a processor, configured to call and execute computer instructions from a memory, so that a device equipped with the chip executes a method in the first aspect, the second aspect, the third aspect, or any possible implementation method.

[0066] In a ninth aspect, an embodiment of the present application provides a communication system, comprising: a communication device for executing the method in the first aspect or each possible implementation, and a communication device for executing the method in the second aspect or each possible implementation.

[0067] In the tenth aspect, an embodiment of the present application provides a computer-readable storage medium for storing computer program instructions, and the computer program enables a computer to execute a method as in the first aspect, the second aspect, the third aspect, or each possible implementation.

[0068] In an eleventh aspect, an embodiment of the present application provides a computer program, which enables a computer to execute a method as described in the first aspect, the second aspect, the third aspect, or any possible implementation manner.

[0069] In a twelfth aspect, an embodiment of the present application provides a computer program product, comprising computer program instructions, which enable a computer to execute a method as in the first aspect, the second aspect, the third aspect, or any possible implementation manner.

[0070] The beneficial effects of the contents of the above-mentioned second to twelfth aspects and each possible implementation method can be referred to the beneficial effects brought about by the above-mentioned first aspect and each possible implementation method of the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 One possible, non-limiting system schematic is shown.

[0072] Figure 2 A schematic flowchart of a prompt service provided in an embodiment of the present application.

[0073] Figure 3 A schematic diagram of an interactive process of a model processing method provided in an embodiment of the present application.

[0074] Figure 4 A schematic diagram of an interactive process of a model processing method provided in an embodiment of the present application.

[0075] Figure 5 A schematic diagram of an interactive process of a model processing method provided in an embodiment of the present application.

[0076] Figure 6 A schematic diagram of an interactive process of a model processing method provided in an embodiment of the present application.

[0077] Figure 7 A schematic diagram of an interactive process of model processing provided in an embodiment of the present application.

[0078] Figure 8A schematic diagram of an interactive process of model processing provided in an embodiment of the present application.

[0079] Fig. 9 A schematic diagram of an interactive process of model processing provided in an embodiment of the present application.

[0080] Fig.10 A schematic diagram of an interactive process for synchronizing capability information related to model processing provided in an embodiment of the present application.

[0081] Fig.11 It is a schematic block diagram of a communication device provided in an embodiment of the present application.

[0082] Fig.12 It is another schematic block diagram of the communication device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0083] The technical solution in this application will be described below in conjunction with the accompanying drawings.

[0084] Figure 1 A possible, non-limiting system schematic is shown. Figure 1 As shown, the communication system 10 includes a radio access network (RAN) 100 and a core network (CN) 200. The RAN 100 includes at least one RAN node (e.g. Figure 1 110a and 110b, collectively referred to as 110) and at least one terminal (such as Figure 1 RAN 100 may also include other RAN nodes, such as wireless relay equipment and / or wireless backhaul equipment ( Figure 1 The terminal 120 is connected to the RAN node 110 in a wireless manner. The RAN node 110 is connected to the core network 200 in a wireless or wired manner. The core network device in the core network 200 and the RAN node 110 in the RAN 100 may be different physical devices, or may be the same physical device that integrates the core network logical function and the radio access network logical function.

[0085] RAN 100 may be a cellular system related to the third generation partnership project (3GPP), for example, a 4G, 5G, or 6G mobile communication system. RAN 100 may also be an open access network (open RAN, O-RAN or ORAN), a cloud radio access network (cloud radio access network, CRAN), or a wireless fidelity (wireless fidelity, WiFi) system. RAN 100 may also be a communication system that integrates two or more of the above systems.

[0086] The RAN node 110, which may also be sometimes referred to as an access network device, a RAN entity or an access node, constitutes a part of the communication system to help the terminal achieve wireless access. The multiple RAN nodes 110 in the communication system 10 may be nodes of the same type or nodes of different types. In some scenarios, the roles of the RAN node 110 and the terminal 120 are relative, for example, Figure 1 The network element 120i may be a helicopter or a drone, which may be configured as a mobile base station. For the terminals 120j that access the RAN 100 through the network element 120i, the network element 120i is a base station; but for the base station 110a, the network element 120i is a terminal. The RAN node 110 and the terminal 120 are sometimes referred to as communication devices, for example Figure 1 The network elements 110a and 110b can be understood as communication devices with base station functions, and the network elements 120a-120j can be understood as communication devices with terminal functions.

[0087] In one possible scenario, a RAN node may be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next generation NodeB (gNB), a next generation base station in a sixth generation (6G) mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system. A RAN node may be a macro base station (e.g. Figure 1 110a in), micro base stations or indoor stations (such as Figure 1110b in the description), a relay node or a donor node, or a wireless controller in a CRAN scenario. Optionally, the RAN node may also be a server, a wearable device, a vehicle or an on-board device, etc. For example, the access network device in the vehicle to everything (V2X) technology may be a road side unit (RSU). All or part of the functions of the RAN node in the present application may also be implemented by software functions running on hardware, or by virtualization functions instantiated on a platform (such as a cloud platform). The RAN node in the present application may also be a logical node, a logical module or software that can implement all or part of the functions of the RAN node.

[0088] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, and different RAN nodes respectively implement part of the functions of the base station. For example, the RAN node can be a centralized unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU). The CU and DU can be set separately, or can also be included in the same network element, such as a baseband unit (BBU). The RU can be included in a radio frequency device or a radio frequency unit, such as a remote radio unit (RRU), an active antenna unit (AAU) or a remote radio head (RRH).

[0089] A terminal may also be called terminal equipment, user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device.

[0090] The terminal device may be a device that provides voice / data connectivity to users, such as a handheld device or vehicle-mounted device with wireless connection function. At present, some examples of terminals can be: mobile phones, tablet computers (pads), computers with wireless transceiver functions (such as laptops, PDAs, etc.), drones, customer-premises equipment (CPE), smart point of sale (POS) machines, mobile Internet devices (MID), virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self driving, wireless terminals in remote medical, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), etc. assistant, PDA), handheld devices with wireless communication function, computing devices or other processing devices connected to a wireless modem, vehicle-mounted devices, wearable devices, terminal devices in 5G networks or terminal devices in systems evolved after 5G, etc.

[0091] To facilitate understanding of the embodiments of the present application, the terms involved are first described exemplarily.

[0092] A large model, such as a large language model (LLM), can refer to a machine learning model with a large parameter scale (e.g., more than 10 million), which can be applied to natural language processing, computer vision, speech recognition, etc. This application only uses the application scenario of a large model as an example, but does not limit the type and scale of the model applied by prompt.

[0093] Prompt engineering is the core technology for efficient operation of large models. Prompt can provide clear, concise and targeted prompts to optimize the output effect of the model. In prompt engineering, the questions input by the user can be converted into new questions based on the prompt template to facilitate the model to understand the questions and optimize the output of the model. The questions input by the user can also be called the description of the problem, the input of the problem, or the input information (such as input). Compared with the new questions formed based on the model, the questions input by the user can also be called the original question, the original question description, the original input, the original question input, etc.

[0094] For example, in a sentiment classification task, the question input by the user is "I like this movie", and the prompt template is "[X]. All in all, it is a [Z] movie". The "[X]" in the prompt template is the replacement position of the question input by the user, and "[Z]" is the position of the word to be predicted by the model. The new question obtained based on the prompt template conversion is "I like this movie. All in all, it is a [Z] movie". Based on the new question, the network model can predict the word at the [Z] position, such as "interesting" or "touching". Furthermore, based on the new question, the network model can predict the sentiment classification of the word at the [Z] position, such as a 0.9 probability for positive sentiment and a 0.1 probability for negative sentiment.

[0095] See also Figure 2 As shown, currently, the cloud stores a prompt template library. Users download various prompt templates in the prompt template library from the cloud, and select a suitable prompt template from the downloaded prompt templates based on experience. The user's question is converted based on the selected prompt template to obtain a new question. The new question is input into the big model on the cloud. The big model performs model reasoning on the input question, and the user then downloads the reasoning result from the cloud. In this case, the user needs to manually download and select the prompt template, which makes the model less convenient to use and cannot guarantee the model reasoning effect.

[0096] At present, in order to realize the deep coupling of communication, perception, calculation, control, etc. of the large model in the wireless network, the large model can be deployed in the wireless network. The large model can be deployed independently or in a distributed manner, and this application does not limit this. For example, when the large model is deployed independently, it can be deployed in the core network 200 or the access network 100; for another example, when the large model is deployed in a distributed manner, it can be distributedly deployed in the core network 200 and the access network 100, or distributedly deployed in the core network 200 and the cloud (such as a cloud server). At present, there is a lack of effective technical solutions for how to obtain prompt templates in wireless networks. Therefore, the technical problem to be solved by this application is to realize the intelligent acquisition of prompt templates through information (including signaling and / or data) transmission and processing between devices in a wireless network, so as to improve the convenience of model use and ensure the model reasoning effect.

[0097] Prompts can include hard prompts and soft prompts. Hard prompts are templates based on fixed prompt words, which form new questions by adding fixed prompt words to the input sentence. For example, in the example of the sentiment classification task mentioned above, the prompt template is the template of the hard prompt; soft prompts replace the fixed prompt word template with a learnable vector. In other words, the prompt words in the template of the hard prompt are readable, and the prompt words in the template of the soft prompt are vectorized, such as the soft prompt is a continuous vector recognizable by the model. Studies have shown that using an implicit, trained, and best soft prompt instead of a hard prompt can achieve better results. For example, when the same large model processes the same task, the Bert-Base model uses a hard prompt template score of 43.3 and a soft prompt template score of 48.3; the Bert-Large model uses a hard prompt score of 39.4 and a soft prompt score of 50.6. However, in wireless networks, there is currently a lack of effective technical solutions for how to achieve the generation of soft prompts, which is another technical problem that this application hopes to solve.

[0098] The model processing method provided in the embodiment of the present application will be described below with reference to the accompanying drawings.

[0099] It should be understood that the following is only for the convenience of understanding and explanation, and the method provided in the embodiment of the present application is described by taking the interaction between the terminal device and the network device as an example. The terminal device may be, for example, Figure 1 The terminal 120 in the network device may be, for example, Figure 1 The RAN node 110 in the core network, or the device in the core network 200.

[0100] It should also be understood that this should not constitute any limitation on the execution subject of the method provided in the present application. As long as the method provided in the embodiment of the present application can be executed by running a program having the code of the method provided in the embodiment of the present application, it can be used as the execution subject of the method provided in the embodiment of the present application. For example, the above-mentioned terminal device can also be replaced by a component in the terminal device, such as a chip, a chip system or other functional module that can call and execute a program; the above-mentioned network device can also be replaced by a component in the network device, such as a chip, a chip system or other functional module that can call and execute a program.

[0101] In some embodiments, the network device may be deployed with a functional module of the prompt service to provide auxiliary services for the large model. The functional module of the prompt service may be, for example, a prompt logic function (PLF) module, which may be a hardware module, a software module, or a module combining hardware and software. The interaction between the terminal device and the network device may be implemented based on the interaction between the terminal device and the functional module of the prompt service. PLF is only an exemplary name for the functional module of the prompt service, and this application does not limit this.

[0102] Optionally, the PLF module can be deployed in the core network (such as Figure 1 The core network 200 in Figure 1 RAN100 in the figure), when the PLF module is deployed in the RAN, it can be deployed in the CU, and this application does not limit this.

[0103] Optionally, the present application does not limit the number of PLF modules deployed in a wireless network. When multiple PLF modules are deployed, each PLF module may correspond to at least one model, each PLF module may be used to perform at least one task, and each PLF module may be used to reason about at least one category of problems.

[0104] Figure 3 A schematic diagram of an interactive flow of a model processing method provided in an embodiment of the present application. Figure 3 , the method 300 includes part or all of the following processes.

[0105] S310, the terminal device sends a first message to the network device, the first message is used to request the network device to determine N first questions input into the first model, N is a positive integer, the first message includes: input information, and type information and / or task information. Correspondingly, the network device receives the first message sent by the terminal device.

[0106] S320, the network device sends a second message to the terminal device, the second message includes M first questions, the N first questions are part or all of the M first questions, the first questions are determined based on the first prompt template and input information, the first prompt template is determined based on type information and / or task information. Correspondingly, the terminal device receives the second message from the network device.

[0107] It should be noted that the N first questions may be inputs of the first model. When the terminal device requests the network device to determine the first question to be input into the first model, the number of the first questions may not be indicated. The first question may be a new question converted by the prompt model in the above example.

[0108] As mentioned above, the input information (input) may include questions input by the user, such as questions input by the user through a terminal device.

[0109] Type information (type) may refer to the type requirements of user questions (such as input), such as classification problems, regression problems, etc. For example, in a sentiment classification model, it may include text classification problems (text classification, textCLS); text-span classification problems (text-span CLS), where text-span CLS refers to asking about sentiment tendencies for one of the subjects when a sentence includes sentiment tendencies under several different topics; text-pair natural language inference problems (text-pair CLS); sequence tagging problems (tagging); text generation problems (Text Generation), etc. It should be understood that the type information included in the first message may include one or more of the above examples.

[0110] Task information (task) may refer to the category of tasks that the model needs to perform, such as sentiment classification tasks, topic classification tasks, code generation tasks, image generation tasks, text generation tasks, etc. Taking the sentiment classification model as an example, the task information may include sentiment classification tasks (sentiment), in which the model can infer whether the text is positive (or active) or negative (or passive); topic classification tasks (topics), in which the model can infer that the text is a related topic; intention recognition tasks (intention), in which the model can infer the user's intention and prepare a reply based on the intention; aspect sentiment tasks (aspect sentiment); natural language inference (NLI) tasks, in which the model infers whether there is a causal relationship between the input sentences; named entity recognition tasks (named entity recognition, NER); summarization tasks (summarization); text translation tasks (translation), etc. The task information included in the first message may include one or more of the above examples.

[0111] It should be understood that each type of information may correspond to one or more task information, and similarly, each task information may correspond to one or more type information, which is not limited in this application. Each type of information and a task under the type may correspond to one or more prompt templates.

[0112] The type information and the task information may be input by the user through the terminal device, or the type information and the task information may be identified by the terminal device. For example, the terminal device may determine the type information and / or the task information based on the question input by the user.

[0113] In order to realize intelligent determination of prompt templates, in an embodiment of the present application, the first prompt template used to determine the first question can be determined based on the type information and / or task information in the first message. Exemplarily, the network device can determine the corresponding M first prompt templates based on the type information and / or task information in the first message, and then determine the first question according to each prompt template in the M first prompt templates and input information, and then obtain M first questions corresponding to the M first prompt templates.

[0114] In some embodiments, a plurality of prompt templates may be stored in a wireless network, and the plurality of prompt templates may be stored in the form of a template library. Optionally, the template library may be deployed in a core network. The prompt template library may include a first correspondence, and the first correspondence includes a correspondence between type information, task information, and prompt templates. As shown in Table 1 below, in the template library, when the type information is "text classification problem" and the task information is "emotion classification task", the prompt template is "[X] It is a [Z] movie"; when the type information is "text fragment classification problem" and the task information is "emotional task", the prompt template is "[X] How is the service? [Z]", and so on.

[0115] Table 1

[0116]

[0117]

[0118] The first question may be determined by the network device based on the input information and the first prompt template. Referring to Table 1, when the input information is "I like this movie.", the type information is "text classification problem", and the task information is "emotion classification task", the network device matches the M first prompt templates obtained in the template library according to the type information and the task information, including "[X] It is a [Z] movie". Then the first question may be "I like this movie. It is a [Z] movie". After the first question is input into the first model for model inference, the result obtained may include "very good, excellent...".

[0119] In some embodiments, the first prompt template may also be determined based on information of the first model, such as an identifier (ID) of the first model, execution parameters of the first model, a type of the first model, etc. Optionally, the first message may include information of the first model. The information of the model may have a corresponding relationship with the prompt template, and the corresponding relationship may be preset or preconfigured, and then the network device may determine the first prompt template corresponding to the first model in the corresponding relationship according to the information of the first model.

[0120] The first model may be any model deployed in the wireless network, for example, the large model mentioned above, which is not limited in this application. One or more models may be deployed in the wireless network, and the first model may be a model that meets the task requirements. The first model may be determined by the terminal device indication, or the first model may be determined based on the task information and / or type information.

[0121] Therefore, in this embodiment, the terminal device sends a first message to the network device, the first message includes input information, type information and / or task information, to request the network device to determine N first questions input into the first model, and then receives a second message sent by the network device, the second message includes M first questions determined based on the first prompt template and the input information, and a prompt service is implemented in the wireless network. Furthermore, the first prompt template is determined based on the type information and / or task information, which realizes the intelligent acquisition of the prompt template, improves the convenience of model use, and ensures the reasoning effect of the model.

[0122] Figure 4 A schematic diagram of an interactive flow of a model processing method provided in an embodiment of the present application. Figure 4 As shown, the method 400 may include part or all of the following processes.

[0123] exist Figure 4 In the method 400 shown, S410 and S420 are respectively Figure 3 S310 and S320 in the illustrated embodiment are the same or similar and will not be described in detail for the sake of brevity.

[0124] In some embodiments, the number M of first questions included in the second message sent by the network device may be equal to the number N of first questions that need to be input into the first model, or in other words, the M first questions included in the second message sent by the network device are all used as inputs to the first model.

[0125] In other embodiments, the first questions may be screened to determine N first questions from M first questions for various possible dimensional considerations, such as to ensure the accuracy of matching the prompt template, or to ensure the rationality of the first questions, or to reduce the complexity of model processing.

[0126] It should be noted that the present application does not limit the screening method of the terminal device to determine N first questions from M first questions. Optionally, if only for the consideration of reducing the complexity of model processing, the terminal device can randomly determine N first questions from M first questions.

[0127] As an example, the first question can be filtered by Figure 4 As shown, including:

[0128] S430, the terminal device may send a fourth message to the second device, and the fourth message may be used to request the second device to screen the M first questions using the first model. Correspondingly, the network device receives the fourth message from the terminal device.

[0129] S440, the second device sends a fifth message to the terminal device, where the fifth message is used to indicate N first questions among the M first questions.

[0130] Exemplarily, the network device may prioritize the M first questions using the first model in response to the request of the fourth message, and select the top N first questions in descending order of priority.

[0131] The first model can prioritize the M first questions by scoring the M first questions. For example, the M first questions are scored based on the rationality of the first questions, and the priorities are sorted in descending order of the scores, that is, the priorities are sorted in descending order of rationality. It should be noted that the present application does not limit the basis for the first model to score the first questions. For example, the first model can score the first questions according to the frequency of occurrence of the first questions.

[0132] The first model is deployed in the second device, and when the first model is distributedly deployed, the second device may be deployed with part of the first model. The second device may be a core network device, or an access network device, or a cloud device (such as a cloud server).

[0133] See also Figure 4 As shown, in S450, the terminal device may send a third message to the first device, and the third message is used to request the first device to perform model reasoning based on N first questions among the M first questions through the first model. The N first questions may be obtained after question screening, or the N first questions may be M first questions (M=N).

[0134] The first model is deployed in the first device. When the first model is deployed in a distributed manner, the first device may be deployed with part of the first model. The first device may be a core network device, an access network device, or a cloud device (such as a cloud server). The first device and the second device may be the same device or different devices. When the first device and the second device are different devices, the first model is deployed in a distributed manner on the first device and the second device.

[0135] In some embodiments, the M first questions included in the second message may not all meet the preset conditions. The preset conditions may be different for different types of questions. For example, for a text generation task, the quality of the answer output by the first model for the first question can be judged from the perspective of diversity and / or accuracy. When the quality of the answer meets the threshold, it is determined that the first question meets the preset conditions. Diversity refers to designing multiple different questions, and whether the answers answered by the large model are the same; accuracy refers to whether the answer generated by the first model is fluent, whether it contains harmful content, etc.

[0136] Combine the following Figure 5S530 and S540 in the flowchart exemplify how to obtain new questions to be input into the first model when the M first questions do not meet the preset conditions. Figure 5 The S510 and S520 in Figure 3 S310 and S320 are the same or similar, and will not be described in detail for brevity. Figure 3 The example shown is implemented based on the example shown, but the present application is not limited to this. Figure 4 The example shown is used as the basis for implementation. For example, when executing Figure 4 After S440 in Figure 5 In S530 and S540, when S530 is executed after S440, the first indication information can be used to indicate that N first questions among the M first questions do not meet the preset condition.

[0137] See also Figure 5 In S530, the terminal device sends a sixth message to the network device, where the sixth message includes first indication information, and the first indication information is used to indicate that the M first questions do not meet the preset conditions.

[0138] Optionally, the sixth message may further include: input information, and type information and / or task information. The input information included in the sixth message may be the same as the input information included in the first message, the type information included in the sixth message may be the same as the type information included in the first message, and the task information included in the sixth message may be the same as the task information included in the first message. However, in some scenarios, in order to successfully obtain the first question that meets the preset conditions, at least one of the input information, type information, and input information included in the first message may be adjusted to increase the possibility of successfully obtaining the first question.

[0139] In response to the request of the sixth message, the network device can aggregate the first prompt templates corresponding to the M first questions to obtain a second prompt template, and then obtain the second question based on the second prompt template, so that the second question meets the preset condition. As mentioned above, the first prompt template corresponding to the first question refers to the first prompt template used when generating (or converting) the first question.

[0140] Further, in S540, the network device may send a seventh message to the terminal device, the seventh message including the second question. Optionally, in S550, the terminal device may send an eighth message to the first device based on the received second question, the eighth message being used to request the first device to perform model reasoning based on the second question through the first model.

[0141] Exemplarily, the second question may include a first vector and a second vector, wherein the first vector is obtained according to input information, and the second vector is calculated according to vectors mapped by M first prompt templates. The second vector may be a second prompt template obtained by the network device based on aggregation of the M first prompt templates, that is, the aggregated second prompt template may be a softprompt.

[0142] It should be understood that, based on experimental data, aggregating multiple prompt templates (such as the first prompt template) can achieve better results than using only one prompt template (such as the first prompt template). Input questions converted based on different prompt templates (such as the first prompt template) into the first model respectively, and then perform reasoning respectively to obtain reasoning results. Next, select appropriate rules to aggregate multiple prompt templates (such as the first prompt template). For example, global average, weighted average, or voting, distillation, etc. can be used to obtain the aggregated prompt template (such as the second prompt template). As the number of aggregated prompt templates (such as the first prompt template) increases, the accuracy of the question will also increase. The advantages of using multiple prompt templates (such as the first prompt template) for aggregation are reflected in: a) leveraging the advantages of different prompt templates to achieve complementarity; b) more stable performance in downstream tasks.

[0143] Exemplarily, the network device aggregating the second prompt template based on the M first prompt templates may include: the network device embeds each of the M first prompt templates into a low-dimensional vector through a first model.

[0144] For example, the input information is "I like deep learning", and the three first prompt templates are: "From now on, you are a translator", "I hope you can play the role of English translation, spelling proofreading and rhetoric improvement", "Now I let you act as a translator, your goal is to translate any language into English, and the translation must be natural and authentic". The embedding vectors obtained for the three first prompt templates are:

[0145] [-0.73510434 2.41941113-0.75119304 1.22246059 -0.49535954 0.17048515] [0.1686593 0.66778136 0.65839084 1.76373291 0.62441869 1.28184983]

[0147] [-1.22016658 0.26831831 0.40529441-0.7297467-0.77142339 0.70344466]

[0148] The network device averages multiple vectors to obtain the second vector, such as:

[0149] [-0.59553721 1.1185036 0.10416407 0.75214893-0.21412141 0.71859322]

[0150] The network device embeds the input information "I like deep learning" through the first model to obtain the first vector. For example:

[0151] [0.45298121 0.33040098 0.20693714 -1.48242658 -0.14846323 0.00864623]

[0152] After combining the second vector with the first vector, the second problem is formed. For example:

[0153] [[-0.59553721 1.1185036 0.10416407 0.75214893-0.21412141 0.71859322]

[0154] [0.45298121 0.33040098 0.20693714 -1.48242658 -0.14846323 0.00864623]]

[0155] When the first vector and the second vector are combined to form the second problem, the order of the first vector and the second vector is not limited.

[0156] See also Figure 6 As shown, step 600 may include S610 and S620.

[0157] S610, the terminal device sends a first message to the network device, the first message is used to request the network device to determine a third question input into the first model, the first message includes: input information, and type information. Correspondingly, the network device receives the first message from the terminal device.

[0158] S620, the terminal device receives a second message from the network device, the second message includes a third question, the third question is determined based on a vector generated by a prompt generation unit and the input information, and the prompt generation unit corresponds to the type information.

[0159] Similar to the first question in the aforementioned embodiment, the third question may be an input to the first model.

[0160] The network device may generate a third question based on the prompt generating unit in response to the first message.

[0161] Exemplarily, the network device may convert the input information through a prompt generation unit to obtain a corresponding vector, which may be called a softprompt. The prompt generation unit may be determined by the network device based on the type information. Exemplarily, the network device may determine the prompt generation unit corresponding to the type information in a preset corresponding relationship based on the type information included in the first message, and the corresponding relationship includes a corresponding relationship between the prompt generation unit and the type information.

[0162] Exemplarily, the third question may include a third vector and a fourth vector, the third vector being obtained according to the input information, and the fourth vector being the vector generated by the prompt generation unit based on the input information. Optionally, the prompt generation unit may be referred to as a prompt generator or a prompt generation model.

[0163] For example, the input information is "I like deep learning", and the fourth vector (ie, softprompt) generated by the prompt generation unit according to the input information can be:

[0164] The network device maps the input information into a third vector, such as embedding the input information "I like deep learning" through the first model to obtain the third vector. For example, it can be:

[0165] After combining the fourth vector with the third vector, we get the third problem. For example:

[0166] [[0.59553721 1.1185036 0.10416407 0.75214893-0.21412141 0.71859322]

[0167] [0.45298121 0.43050098 0.20693714 -1.48242658 -0.14846323 0.00864623]]

[0168] When the third vector and the fourth vector are combined to form the third problem, the order between the third vector and the fourth vector is not limited in the present application.

[0169] Optionally, in an embodiment of the present application, the first message may further include task information, or the type information in the first message may be replaced with task information.

[0170] Based on this, in this embodiment, the terminal device sends a first message to the network device, the first message includes input information and type information, to request the network device to determine the third question of the input first model, and then receives a second message sent by the network device, the second message includes the third question, and the third question is determined based on the vector generated by the prompt generation unit and the input information, and the prompt generation unit corresponds to the type information. A solution is provided for realizing intelligent generation of soft prompts in wireless networks.

[0171] Next, take the network device implemented as PLF or PLF module as an example, combined with Figures 7 to 9 An exemplary description is given of deploying a PLF in a wireless network.

[0172] Figure 7 A schematic diagram of an interactive process of model processing provided in an embodiment of the present application. Among them, PLF can be a device or network element deployed with PLF, TCF can be a device or network element deployed with TCF, and the first model can be a device or network element deployed with the first model (such as the first device and / or the second device mentioned above). Figure 7 As shown, the model processing method may include some or all of the following steps:

[0173] S701, the terminal device sends a task request to the TCF, and the task request can be used to request to establish a task session (taskID) with the PLF. The task request can be carried in a task-non-access stratum (T-NAS) message. Optionally, the task request can include at least one of task information, problem category, task identifier (such as task ID), and task execution parameters, wherein the task execution parameters can include at least one of input information and information of the first model.

[0174] S702, the TCF matches the PLF based on the task request, such as matching the corresponding PLF based on at least one of the input information, task information, problem category, task identifier (such as task ID), and information of the first model in the task request, and notifying the PLF.

[0175] S703, the PLF sends a request response to the terminal device, where the request response is used to confirm the request to establish the task session, thereby establishing a task session between the terminal device and the PLF.

[0176] S704, the terminal device sends a first message to the PLF. Optionally, the first message may be sent in the form of a task data packet.

[0177] S705: The PLF obtains M first prompt templates based on the type information and / or task information in the first message.

[0178] S706: The PLF obtains M first questions based on each first prompt template in the M first prompt templates and the input information.

[0179] S707, the PLF sends M first questions to the terminal device. The M first questions may be carried by a task data packet.

[0180] S708: The terminal device determines to use M first questions as questions to be input into the first model, or determines N first questions from the M first questions as questions to be input into the first model.

[0181] S709: The terminal device sends the determined M first questions or N first questions to the first model.

[0182] S710: The first model performs model reasoning based on the input first question to obtain a reasoning result.

[0183] S711, the first model sends the inference result to the terminal device.

[0184] Among them, S704 to S710 have been explained in the above examples and will not be repeated for the sake of brevity.

[0185] Figure 8 A schematic diagram of an interactive process of model processing provided in an embodiment of the present application. Among them, the access and mobility management function (AMF) can be a device or network element deployed with AMF, and the PLF and the first model can refer to Figure 7 The description in the examples. Figure 8 In the illustrated embodiment, the terminal device may forward information to the PLF proxy through the AMF to implement information transmission between the terminal device and the PLF. The model processing method may include some or all of the following steps:

[0186] S801, the terminal device sends a first message to the AMF. The first message can be carried in a NAS message.

[0187] S802, AMF sends a first message to PLF to implement proxy forwarding of the first message.

[0188] S803: The PLF obtains M first prompt templates by matching based on the type information and / or task information in the first message.

[0189] S804: PLF obtains M first questions based on each first prompt template in the M first prompt templates and the input information.

[0190] S805, the PLF sends M first questions to the terminal device. The M first questions are carried in NAS information.

[0191] S806: The terminal device determines to use M first questions as questions to be input into the first model, or determines N first questions from the M first questions as questions to be input into the first model.

[0192] S807: The terminal device sends the determined M first questions or N first questions to the first model.

[0193] S808: The first model performs model reasoning based on the input first question to obtain a reasoning result.

[0194] S809: The first model sends the inference result to the terminal device.

[0195] Some steps are similar to those in the previous examples and will not be described again for brevity.

[0196] Fig. 9 A schematic diagram of an interactive process of model processing provided in an embodiment of the present application. Fig. 9 In the embodiment shown, the first message is carried in a user plane message. The user plane function (UPF) may be a device or network element with a UPF deployed. The PLF and the first model may refer to Figure 7 The description in the examples. Fig. 9 In the illustrated embodiment, the terminal device may transfer information to the PLF proxy through the UPF to implement information transmission between the terminal device and the PLF. The model processing method may include some or all of the following steps:

[0197] S901, the terminal device sends a first message to the UPF. The first message can be carried in a user plane message.

[0198] S902, UPF sends a first message to PLF to implement proxy forwarding of the first message.

[0199] S903: The PLF obtains M first prompt templates by matching based on the type information and / or task information in the first message.

[0200] S904: PLF obtains M first questions based on each first prompt template in the M first prompt templates and the input information.

[0201] S905, the PLF sends M first questions to the terminal device. The M first questions are carried in NAS information.

[0202] S906: The terminal device determines to use M first questions as questions to be input into the first model, or determines N first questions from the M first questions as questions to be input into the first model.

[0203] S907, the terminal device sends the determined M first questions or N first questions to the first model.

[0204] S908: The first model performs model reasoning based on the input first question to obtain a reasoning result.

[0205] S909: The first model sends the inference result to the terminal device.

[0206] Some steps are similar to those in the previous examples and will not be described again for brevity.

[0207] In some embodiments, the network device can synchronize the network's model processing capability information to the terminal device, for example, the network device can synchronize supported task information and / or supported models (including large models) to the terminal device, so that the terminal device can implement any of the above embodiments based on the network's model processing capability, such as the task information included in the first message sent by the terminal device to the network device should belong to the task type supported by the network. See below Fig.10 shown.

[0208] Fig.10 A schematic diagram of an interactive process for synchronizing capability information of model processing provided in an embodiment of the present application. Among them, PCF can be a device or network element with PCF deployed, and PLF can participate in Figure 7 In combination with the description in the embodiment Fig.10 As shown, the method may include the following steps:

[0209] S1001, PCF may obtain network supported task information and / or supported models (including large models) from PLF. Exemplarily, PCF sends a query message to PLF, the query message is used to query the network supported task information and / or supported models (including large models), PLF may send a query response to PCF, the query response includes supported task information and / or supported models (including large models); alternatively, PCF may read network supported task information and / or supported models (including large models) from PLF. Optionally, the number of supported task information may be one or more, and the supported task information may form a list (such as a task type list); similarly, the number of supported models may be one or more, and the supported models may form a list (such as a model list).

[0210] S1002, the PCF sends a ninth message to the terminal device, where the ninth message is used to indicate supported task information and / or supported models (including large models). Optionally, the ninth message can be carried in a broadcast message, that is, the PCF can send the ninth message in a broadcast manner. Accordingly, the terminal device receives the ninth message from the PCF.

[0211] Fig.11 1 is a schematic block diagram of a communication device provided in an embodiment of the present application. The communication device 1100 may be a terminal or a network device, or may be a device in a terminal device or a network device, or may be a device that can be used in conjunction with a terminal device or a network device. Fig.11 As shown, the device 1100 may include: a transceiver module 1110 and a processing module 1120 .

[0212] Optionally, the communication device 1100 may correspond to the terminal device in the above method embodiment.

[0213] If executed Figure 3 In any of the method embodiments shown, the processing module 1120 can be used to determine a first message, wherein the first message is used to request the network device to determine N first questions input into the first model, where N is a positive integer, and the first message includes: input information, and type information and / or task information; the transceiver module 1110 can be used to send the first message; the transceiver module 1110 is also used to receive a second message from the network device, wherein the second message includes M first questions, the N first questions are part or all of the M first questions, and the first questions are determined based on a first prompt template and the input information, and the first prompt template is determined based on the type information and / or the task information.

[0214] If executed Figure 6 In any of the method embodiments shown, the processing module 1120 can be used to determine a first message, wherein the first message is used to request the network device to determine a third question input into the first model, and the first message includes: input information, and type information; the transceiver module 1110 can be used to send the first message; the transceiver module 1110 is also used to receive a second message from the network device, wherein the second message includes a third question, and the third question is determined based on a vector generated by a prompt generation unit and the input information, and the prompt generation unit corresponds to the type information.

[0215] It should be understood that the specific process executed by each module has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0216] Optionally, the communication device 1100 may correspond to the network device in the above method embodiment.

[0217] If executed Figure 3 In any of the method embodiments shown, the transceiver module 1110 can be used to receive a first message, wherein the first message is used to request determination of N first questions input into a first model, where N is a positive integer, and the first message includes: input information, and type information and / or task information; the processing module 1120 can be used to determine M first questions, where the N first questions are part or all of the M first questions, and the first questions are determined based on a first prompt template and the input information, and the first prompt template is determined based on the type information and / or the task information; the transceiver module 1110 is also used to send a second message, wherein the second message includes the M first questions.

[0218] If executed Figure 6 In any of the method embodiments shown, the transceiver module 1110 can be used to receive a first message, wherein the first message is used to request determination of a third question input into the first model, and the first message includes: input information and type information; the processing module 1120 can be used to determine a third question, wherein the third question is determined based on a vector generated by a prompt generation unit and the input information, and the prompt generation unit corresponds to the type information; the transceiver module 1110 is also used to send a second message, and the second message includes the third question.

[0219] It should be understood that the specific process executed by each module has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0220] The transceiver module 1110 in the communication device 1100 may be implemented by a transceiver, for example, corresponding to Fig.12 The transceiver 1220 in the communication device 1200 shown in FIG. 1 , the processing module 1120 in the communication device 1100 may be implemented by at least one processor, for example, corresponding to Fig.12 The processor 1210 in the communication device 1200 shown in FIG.

[0221] When the communication device 1100 is a chip or a chip system configured in a communication device (such as a terminal device or a network device), the transceiver module 1110 in the communication device 1100 can be implemented through an input / output interface, circuit, etc., and the processing module 1120 in the communication device 1100 can be implemented through a processor, microprocessor or integrated circuit integrated on the chip or chip system.

[0222] Fig.12 is another schematic block diagram of a communication device provided in an embodiment of the present application. Fig.12 As shown, the communication device 1200 may include: a processor 1210. The processor 1210 may be used to execute the method executed by the first communication device or the second communication device in the above method embodiment.

[0223] In some possible implementations, the communication device 1200 may include a transceiver 1220. The transceiver 1220 may communicate with the processor 1210 through an internal connection path. The processor 1210 may control the transceiver 1220 to send and / or receive signals.

[0224] In some possible implementations, the communication device 1200 may include a memory 1230. The memory 1230 may communicate with the processor 1210 through an internal connection path. The memory 1230 and the processor 1210 may be integrated together or separately arranged. The memory 1230 may also be a memory outside the device. The memory 1230 is used to store instructions, and the processor 1210 is used to execute the instructions stored in the memory 1230 to execute the method in the above method embodiment.

[0225] It should be understood that the communication device 1200 may correspond to the terminal device or network device in the above method embodiment, and may be used to execute the various steps and / or processes performed by the first communication device or the second communication device in the above method embodiment. Optionally, the memory 1230 may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. The memory 1230 may be a separate device or may be integrated in the processor 1210. The processor 1210 may be used to execute instructions stored in the memory 1230, and when the processor 1210 executes instructions stored in the memory, the processor 1210 is used to execute the various steps and / or processes of the above method embodiment corresponding to the terminal device or network device.

[0226] Optionally, the communication device 1200 is the terminal device in the previous embodiment.

[0227] Optionally, the communication device 1200 is the network device in the previous embodiment.

[0228] Among them, the transceiver 1220 may include a transmitter and a receiver. The transceiver 1220 may further include an antenna, and the number of antennas may be one or more. The processor 1210 and the memory 1230 and the transceiver 1220 may be devices integrated on different chips. For example, the processor 1210 and the memory 1230 may be integrated in a baseband chip, and the transceiver 1220 may be integrated in a radio frequency chip. The processor 1210 and the memory 1230 and the transceiver 1220 may also be devices integrated on the same chip. This application does not limit this.

[0229] Optionally, the communication device 1200 is a component configured in a terminal device, such as a chip, a chip system, etc.

[0230] Optionally, the communication device 1200 is a component configured in a network device, such as a chip, a chip system, etc.

[0231] The transceiver 1220 may also be a communication interface, such as an input / output interface, a circuit, etc. The transceiver 1220, the processor 1210, and the memory 1230 may be integrated into the same chip, such as a baseband chip.

[0232] The present application also provides a processing device, including at least one processor, wherein the at least one processor runs a computer program or a logic circuit so that the processing device executes the method executed by the first communication device or the second communication device in the above method embodiment. The above processing device may also include a memory, which is used to store the above computer program.

[0233] The embodiment of the present application also provides a processing device, including a processor and an input / output interface. The input / output interface is coupled to the processor. The input / output interface is used to input and / or output information. The information includes at least one of an instruction and data. The processor is used to execute a computer program so that the processing device executes the method executed by the terminal device or the network device in the above method embodiment.

[0234] The present application also provides a processing device, including a processor and a memory. The memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the processing device executes the method executed by the terminal device or network device in the above method embodiment.

[0235] It should be understood that the above-mentioned processing device can be one or more chips. For example, the processing device can be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on chip (SoC), a central processor unit (CPU), a network processor (NP), a digital signal processor (DSP), a microcontroller unit (MCU), a programmable logic device (PLD) or other integrated chips.

[0236] In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software. The steps of the method disclosed in conjunction with the embodiment of the present application can be directly embodied as a hardware processor for execution, or a combination of hardware and software modules in a processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in conjunction with its hardware. To avoid repetition, it is not described in detail here.

[0237] It should be noted that the processor in the embodiment of the present application can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method embodiment can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to perform, or the hardware and software modules in the decoding processor can be combined and performed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0238] It can be understood that the memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0239] According to the method provided in the embodiment of the present application, the present application also provides a computer program product, which includes: a computer program or a set of instructions, when the computer program or a set of instructions is run on a computer, the computer executes the method executed by the terminal device or network device in the above method embodiment.

[0240] According to the method provided in the embodiment of the present application, the present application also provides a computer-readable storage medium, which stores a program. When the program runs on a computer, the computer executes the method executed by the terminal device or network device in the above method embodiment.

[0241] According to the method provided in the embodiment of the present application, the present application also provides a communication system, which may include the aforementioned terminal device or network device.

[0242] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0243] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0244] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for model processing, characterized in that: Applied to terminal equipment, including: Sending a first message, where the first message is used to request the network device to determine N first questions input into a first model, where N is a positive integer, and the first message includes input information, and type information and / or task information; Receive a second message from the network device, the second message including M first questions, the N first questions being part or all of the M first questions, the first questions being determined based on a first prompt template and the input information, and the first prompt template being determined based on the type information and / or the task information.

2. The method according to claim 1, characterized in that: Also includes: A third message is sent, where the third message is used to request the first device to perform model reasoning based on the N first questions among the M first questions through the first model.

3. The method according to claim 1 or 2, characterized in that: Also includes: Sending a fourth message, where the fourth message is used to request the second device to screen the M first questions through the first model; A fifth message is received, where the fifth message is used to indicate the N first questions among the M first questions.

4. The method according to any one of claims 1 to 3, characterized in that: Also includes: Sending a sixth message, where the sixth message includes first indication information, where the first indication information is used to indicate that the M first questions do not meet a preset condition; A seventh message is received, where the seventh message includes a second question, where the second question is generated based on a second prompt template and the input information, where the second prompt template is aggregated based on M first prompt templates corresponding to the M first questions.

5. The method according to claim 4, characterized in that The sixth message also includes the input information, and the type information and / or the task information.

6. The method according to claim 4 or 5, characterized in that: The second question includes a first vector and a second vector, wherein the first vector is obtained according to the input information, and the second vector is obtained according to the vectors mapped by the M first prompt templates.

7. The method according to any one of claims 4 to 6, characterized in that: Also includes: An eighth message is sent, where the eighth message is used to request the first device to perform model reasoning based on the second problem through the first model.

8. A method for model processing, characterized in that: Applied to terminal equipment, including: Sending a first message, the first message is used to request the network device to determine a third question input into the first model, the first message comprising: input information, and type information; A second message is received from the network device, the second message comprising a third question, the third question is determined based on a vector generated by a prompt generation unit and the input information, the prompt generation unit corresponding to the type information.

9. The method according to claim 8, characterized in that The third question includes a third vector and a fourth vector, the third vector is obtained according to the input information, and the fourth vector is generated by the prompt generation unit based on the input information.

10. The method according to any one of claims 1 to 9, characterized in that: The first message is carried in a non-access layer NAS message or a user plane message.

11. The method according to any one of claims 1 to 10, characterized in that: The second message is carried in a NAS message.

12. The method according to any one of claims 1 to 11, characterized in that: Also includes: A ninth message is received, where the ninth message is used to indicate supported task information and / or supported large models.

13. A method for model processing, characterized in that: Applied to network equipment, including: Receive a first message, the first message is used to request to determine N first questions input into a first model, N is a positive integer, the first message includes: input information, and type information and / or task information; Send a second message, the second message including M first questions, the N first questions being part or all of the M first questions, the first questions being determined based on a first prompt template and the input information, and the first prompt template being determined based on the type information and / or the task information.

14. The method according to claim 13, characterized in that Also includes: According to the type information and / or the task information, M first prompt templates are obtained by matching in a template library; According to each first prompt template in the M first prompt templates and the input information, a first question corresponding to the first prompt is determined.

15. The method according to claim 13 or 14, characterized in that receiving a fourth message, wherein the fourth message is used to request to screen the M first questions through the first model; A fifth message is sent, where the fifth message is used to indicate N first questions among the M first questions.

16. The method according to any one of claims 13 to 15, characterized in that Also includes: receiving a sixth message, the sixth message including first indication information, the first indication information being used to indicate that the M first questions do not meet a preset condition; A seventh message is sent, where the seventh message includes a second question, where the second question is generated based on a second prompt template and the input information, where the second prompt template is aggregated based on M first prompt templates corresponding to the M first questions.

17. The method according to claim 16, characterized in that The sixth message further includes: the input information, and the type information and / or the task information.

18. The method according to claim 16 or 17, characterized in that Also includes: Aggregating the M first prompt templates to obtain a second prompt template; The second question is obtained according to the second prompt template and the input information.

19. The method according to any one of claims 16 to 18, characterized in that The second question includes a first vector and a second vector, wherein the first vector is obtained according to the input information, and the second vector is obtained according to the vectors mapped by the M first prompt templates.

20. A method for model processing, characterized in that: Applied to network equipment, including: receiving a first message, the first message being used to request determination of a third question input into the first model, the first message comprising: input information and type information; A second message is sent, wherein the second message includes a third question, wherein the third question is determined based on a vector generated by a prompt generation unit and the input information, and the prompt generation unit corresponds to the type information.

21. The method according to claim 20, characterized in that Also includes: Obtain a prompt generation unit corresponding to the type information; Generate a vector according to the input information by the prompt generating unit; The third question is determined according to the vector and the input information.

22. The method according to claim 20 or 21, characterized in that The third question includes a third vector and a fourth vector, the third vector is obtained according to the input information, and the fourth vector is generated by the prompt generation unit based on the input information.

23. The method according to any one of claims 13 to 22, characterized in that The first message is carried in a non-access layer NAS message or a user plane message.

24. The method according to any one of claims 13 to 23, characterized in that The second message is carried in a NAS message.

25. A communication device, characterized in that: The method comprises a module for executing the method as claimed in any one of claims 1 to 12, or comprises a module for executing the method as claimed in any one of claims 13 to 24.

26. A communication device, characterized in that: include: A processor, wherein the processor is configured to execute the method according to any one of claims 1 to 24 by running a computer program or by a logic circuit.

27. The device according to claim 26, characterized in that Also included is a memory for storing the computer program.

28. The device according to claim 26 or 27, characterized in that Also included is a communication interface for inputting and / or outputting signals.

29. A communication system, characterized in that: include: A communication device for executing the method according to any one of claims 1 to 12, and a communication device for executing the method according to any one of claims 13 to 24.

30. A computer-readable storage medium, characterized in that: Used to store computer program instructions, the computer program causing a computer to execute the method according to any one of claims 1 to 24.

31. A computer program product, characterized in that The method comprises computer program instructions which cause a computer to execute the method as claimed in any one of claims 1 to 24.

Images