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

Abstract

The invention discloses an information processing method and device, terminal equipment and a computer readable storage medium, and the method comprises the steps: obtaining instruction information and a target semantic abstract, the target semantic abstract being obtained by carrying out semantic abstract generation on target information flow data; based on the instruction information and the target semantic abstract, constructing prompt data; and inputting the prompt data into the intelligent reply model to obtain a reply result corresponding to the instruction information. By the adoption of the method, the information flow data can be processed, the semantic abstract is generated, the intelligent reply model is made to reply the instruction information in combination with the semantic abstract, the intelligent reply model can better understand the instruction information, and the reply accuracy of the intelligent reply model is remarkably improved.

Description

Technical Field

[0001] This application relates to the field of information processing technology, specifically to an information processing method, apparatus, terminal equipment, and computer-readable storage medium. Background Technology

[0002] In everyday use cases, users typically already receive important information related to their work tasks, especially in informal communication environments such as random discussions in hallways, impromptu phone calls, or quick conversations during tea breaks. In these scenarios, users often fail to provide complete context, offering only fragmented information, or omitting core elements due to a lack of structured expression habits. They may even deliberately simplify descriptions without recognizing the importance of the information, leading to gaps in information expression during secondary interactions with artificial intelligence (AI) models.

[0003] This incomplete information transmission makes it difficult for AI models to build a complete semantic understanding framework through a single round of dialogue, ultimately leading to responses that deviate from the user's actual needs or results that significantly deviate from the expected goals, severely impacting the efficiency of human-machine collaboration. Summary of the Invention

[0004] This application provides an information processing method, apparatus, terminal device, and computer-readable storage medium that can process information stream data to generate semantic summaries, enabling intelligent response models to respond to instruction information in conjunction with the semantic summaries. This allows the intelligent response models to better understand the instruction information and significantly improves the accuracy of their responses.

[0005] The technical solution adopted by this invention to solve the problem is as follows: On the one hand, this application provides an information processing method, including: Obtain instruction information and target semantic summary, wherein the target semantic summary is generated by semantic summarizing the target information stream data; Based on instruction information and target semantic summary, construct prompt data; Input the prompt data into the intelligent response model to obtain the response result corresponding to the instruction information.

[0006] In some embodiments of this application, the target semantic summary is generated in the following manner: Extracting event elements from target information stream data; Generate a target semantic summary based on event elements.

[0007] In some embodiments of this application, instruction information and target semantic digest are obtained, including: Obtain the input data of the first user to input the intelligent response model, and generate instruction information based on the input data; The semantic digest associated with the instruction information in the semantic digest cache data is determined as the target semantic digest, or the latest semantic digest in the semantic digest cache data is determined as the target semantic digest.

[0008] In some embodiments of this application, instruction information and target semantic digest are obtained, including: Obtain the target semantic summary; Extract task information from the target semantic summary and use the task information as instruction information.

[0009] In some embodiments of this application, the target information flow data is obtained in the following ways: In response to the operation of the second user, audio stream data is recorded; The speech stream data is converted into corresponding text to obtain candidate information stream data; Based on the candidate information stream data, the target information stream data is determined.

[0010] In some embodiments of this application, target information flow data is determined based on candidate information flow data, including: Determine whether the candidate information stream data meets the predetermined conditions; If the candidate information stream data meets the predetermined conditions, the candidate information stream data will be identified as the target information stream data; If the candidate information stream data does not meet the predetermined conditions, the step of recording the voice stream data continues to be performed in response to the operation of the second user.

[0011] In some embodiments of this application, determining whether candidate information stream data meets predetermined conditions includes: Obtain the recording time period corresponding to the candidate information stream data, and determine that the candidate information stream data meets the predetermined conditions if the recording time period is within the predetermined time period range; Alternatively, obtain the recording location corresponding to the candidate information stream data, and if the recording location is within the predetermined location range, determine that the candidate information stream data meets the predetermined conditions; Alternatively, detect whether there are predetermined sensitive words in the candidate information stream data. If there are no predetermined sensitive words in the candidate information stream data, determine that the candidate information stream data meets the predetermined conditions.

[0012] Secondly, embodiments of the present invention also provide an information processing apparatus, comprising: The acquisition module is used to acquire instruction information and target semantic summary, wherein the target semantic summary is generated by semantic summarizing the target information stream data; The building module is used to construct prompt data based on instruction information and target semantic summary; The response module is used to input the prompt data into the intelligent response model and obtain the response result corresponding to the instruction information.

[0013] Thirdly, this application also provides a terminal device, which includes: One or more processors; Memory; and One or more applications, wherein the applications are stored in memory and configured to be executed by a processor to implement the information processing method of any of the first aspects.

[0014] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to perform the steps of the information processing method of any of the first aspects.

[0015] The beneficial effects of this invention are as follows: By acquiring instruction information and a target semantic summary obtained by semantically summarizing the target information stream data, and constructing prompt data based on the instruction information and the target semantic summary, the prompt data is input into the intelligent response model to obtain the response result corresponding to the instruction information. The information stream data can be processed to generate a semantic summary, enabling the intelligent response model to respond to the instruction information in conjunction with the semantic summary. This allows the intelligent response model to better understand the instruction information and significantly improves the accuracy of the intelligent response model's response. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of a scenario for the information processing system provided in an embodiment of the present invention; Figure 2 This is a flowchart illustrating one embodiment of the information processing method provided in this invention. Figure 3 This is a schematic diagram of an information processing scenario provided in an embodiment of the present invention; Figure 4 This is a schematic block diagram of the information processing device provided in the embodiments of the present invention; Figure 5 This is a schematic diagram of the structure of one embodiment of the terminal device provided in this invention. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] In the description of this application, the terms "first," "second," "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first," "second," "third," etc., may explicitly or implicitly include one or more of the stated features.

[0020] In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0021] It should be noted that since the method in this application embodiment is executed in a terminal device, the processing objects of each terminal device exist in the form of data or information, such as time, which is essentially time information. It can be understood that if size, quantity, position, etc. are mentioned in subsequent embodiments, they are all corresponding data that exist so that the terminal device can process them. Specific details will not be elaborated here.

[0022] This application provides an information processing method, apparatus, terminal device, and computer-readable storage medium, which will be described in detail below.

[0023] Please see Figure 1 , Figure 1 This is a schematic diagram of a scenario for an information processing system provided in an embodiment of this application. The information processing system may include a terminal device 100, which integrates an information processing unit, such as... Figure 1 Terminal devices in the process.

[0024] In this embodiment, the terminal device 100 is mainly used to acquire instruction information and target semantic summary. The target semantic summary is generated by semantic summarizing the target information stream data. Based on the instruction information and the target semantic summary, prompt data is constructed. The prompt data is input into the intelligent reply model to obtain the reply result corresponding to the instruction information. The information stream data can be processed to generate a semantic summary, so that the intelligent reply model can reply to the instruction information in combination with the semantic summary. This enables the intelligent reply model to better understand the instruction information and significantly improve the accuracy of the intelligent reply model's reply.

[0025] In this embodiment, the terminal device 100 can be an independent server, a server network, or a server cluster. For example, the terminal device 100 described in this embodiment includes, but is not limited to, a computer, a network host, a single network server, a set of multiple network servers, or a cloud server composed of multiple servers. The cloud server is composed of a large number of computers or network servers based on cloud computing.

[0026] It is understood that the terminal device 100 used in the embodiments of this application can be a device that includes both receiving and transmitting hardware, that is, a device having receiving and transmitting hardware capable of performing bidirectional communication on a bidirectional communication link. Such a device may include: cellular or other communication devices having a single-line display, a multi-line display, or a cellular or other communication device without a multi-line display. Specifically, the terminal device 100 may be a desktop terminal or a mobile terminal, and the terminal device 100 may also be one of a mobile phone, tablet computer, laptop computer, etc.

[0027] Those skilled in the art will understand that Figure 1 The application environment shown is merely one application scenario of the solution in this application and does not constitute a limitation on the application scenario of the solution in this application. Other application environments may include those that are more specific to this application. Figure 1 The number of more or fewer terminal devices shown, for example Figure 1 Only one terminal device is shown in the diagram. It is understood that the information processing system may also include one or more other services, which are not specified here.

[0028] In addition, such as Figure 1 As shown, the information processing system may also include a memory 200 for storing data, such as text data, such as target semantic summaries, input data, response results, etc., and voice data, such as voice stream data, etc.

[0029] It should be noted that, Figure 1The schematic diagram of the information processing system shown is merely an example. The information processing system and scenario described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of information processing systems and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0030] First, this application provides an information processing method. The execution subject of the information processing method is an information processing device, which is applied to a terminal device. The information processing method includes: acquiring instruction information and target semantic summary, wherein the target semantic summary is obtained by generating a semantic summary of target information stream data; constructing prompt data based on instruction information and target semantic summary; and inputting the prompt data into an intelligent response model to obtain a response result corresponding to the instruction information.

[0031] like Figure 2 The diagram shown is a flowchart of an embodiment of the information processing method in this application. The information processing method may include the following steps S201 to S203, as detailed below: Step S201: Obtain instruction information and target semantic summary, wherein the target semantic summary is generated by semantic summarizing the target information stream data.

[0032] In one specific embodiment, the instruction information can be a specific request or command issued to the AI ​​model, such as asking a question or requesting the execution of a task. There are many ways to obtain instruction information, such as obtaining instruction information by acquiring user input text, or obtaining instruction information from other applications or components through an interface; this embodiment does not limit this. The target information stream data can be the raw voice or text information stream generated by the user during communication or meetings with others, or it can be natural communication content in informal scenarios. The target semantic summary is a summary containing key information extracted after semantic understanding of the target information stream data, specifically including task description, task time, execution object, task requirements, etc.

[0033] This step can collect instruction information and target semantic summaries. Target semantic summaries are key semantic contents extracted from the user's communication with others. By acquiring instruction information, the AI ​​model can understand the user's direct needs; while by acquiring target semantic summaries, the AI ​​model can acquire background information that the user has received but has not explicitly expressed to the AI ​​model when communicating with others.

[0034] By combining instruction information and target semantic summaries, AI models can more comprehensively understand the user's true intentions and contextual background, thereby improving the accuracy and relevance of responses and solving the problems of missing information expression and lost context when interacting with AI models.

[0035] Step S202: Construct prompt data based on instruction information and target semantic summary.

[0036] In one specific embodiment, within the AI ​​model, prompt data is input information used to guide the model in generating specific responses. It is structured input consistent with the AI ​​model and can be generated based on a pre-defined prompt template: the instruction information and target semantic summary are filled into the prompt template to obtain the prompt data. The prompt data in this step combines direct instructions with semantic summaries extracted from informal communication to provide richer contextual information.

[0037] Step S203: Input the prompt data into the intelligent response model to obtain the response result corresponding to the instruction information.

[0038] In one specific embodiment, the intelligent response model can be an automatic recovery system based on artificial intelligence technology, capable of generating corresponding response content based on the input prompt data. The intelligent response model can be a large language model or a self-developed AI model, possessing powerful natural language understanding and generation capabilities.

[0039] By inputting the prompt data into the AI ​​model, the AI ​​model can generate more accurate, relevant, and personalized responses, improving the response quality of the AI ​​assistant, enhancing the user's interaction experience and satisfaction with the AI, and solving the problems of missing information expression and lost context when users interact with the AI ​​model.

[0040] In one specific implementation, the target semantic summary is generated as follows: extracting event elements from the target information flow data; and generating the target semantic summary based on the event elements.

[0041] In this embodiment, deep semantic analysis and understanding can be performed on the raw voice or text information stream data generated by users during communication or meetings with others, extracting elements of events mentioned in the communication, such as task dates, task keywords, event summaries, and task requirements. These event elements can describe the time mentioned in the communication from multiple perspectives and reflect the core content and user needs of the communication. After extracting the event elements, they can be combined using a fixed format to generate a target semantic summary.

[0042] Semantic summarization enables AI models to quickly locate key information in communication content, avoiding the burden of processing a large amount of irrelevant or redundant information, thereby improving information processing efficiency and providing users with a more personalized, accurate and efficient interactive experience.

[0043] In one specific implementation, obtaining instruction information and target semantic summary includes: obtaining input data of the first user input intelligent response model, generating instruction information based on the input data; determining the semantic summary associated with the instruction information in the semantic summary cache data as the target semantic summary, or determining the latest semantic summary in the semantic summary cache data as the target semantic summary.

[0044] In this embodiment, the first user can be a user interacting with the AI ​​model. The input data consists of various forms of information provided by the user to the AI ​​model. This can be text content, such as a text description of a problem entered by the user; it can also be voice data, which is converted and processed into analyzable voice feature information or directly converted into text information; or it can be image data, such as an image uploaded by the user containing a specific scene or object, from which key information can be extracted using image recognition technology. By acquiring the user's input data, a foundation is provided for generating subsequent instruction information, enabling the instruction information to reflect the user's specific needs or intentions, so that the AI ​​model can perform targeted subsequent processing.

[0045] Semantic summary cache data is a collection of processed and refined semantic information pre-stored in the system cache. The purpose of caching is to quickly access and reuse data, reducing the time spent on repetitive calculations and data processing. The association can be based on semantic similarity, logical relevance, or fulfillment of a pre-defined matching rule between the instruction information and the semantic summary. For example, if the instruction information mentions a specific topic, and a semantic summary in the semantic summary cache also revolves around that topic, then there is a association between the two. This embodiment can quickly locate the semantic summary most relevant to the current instruction information within the existing semantic summary cache data and use it as the target semantic summary.

[0046] The latest semantic summary refers to the most recently generated or updated semantic summary in the semantic summary cache, arranged chronologically. Besides determining a suitable target semantic summary by associating it with instruction information, the latest semantic summary can also be selected as the target semantic summary. The latest semantic summary often reflects the characteristics and trends of recently processed information, which can, to some extent, meet users' real-time needs, enabling AI models to provide services based on the latest information, thus improving user experience and the practicality of AI models.

[0047] In one specific implementation, obtaining instruction information and target semantic summary includes: obtaining target semantic summary; extracting task information from target semantic summary; and using task information as instruction information.

[0048] In this embodiment, the automation and intelligence of AI model task processing can be further improved. It can automatically obtain target semantic summary, extract task information from the target semantic summary, and use the task information as instruction information to be replied to later, and give the corresponding reply.

[0049] The target semantic summary can be a recently acquired semantic summary. Task information can be a combination of elements in the target semantic summary that clearly point to specific action instructions, and can include structured fields such as executable task types (e.g., preparing a report), operation objects (e.g., new product PPT), and delivery standards.

[0050] Through this embodiment, the AI ​​model can capture unexpressed user needs, automatically extract task information from the target semantic summary, and provide a response based on subsequent steps, further improving user work efficiency.

[0051] In one specific implementation, the target information stream data is obtained as follows: in response to the operation of the second user, voice stream data is recorded; the voice stream data is converted into corresponding text to obtain candidate information stream data; and the target information stream data is determined based on the candidate information stream data.

[0052] The executing entity in this embodiment can be a device that implements the above-described information processing method, such as a server or computer, or a portable listening device that supports recording functionality, such as headphones or a smartphone. The second user can be a user operating the recording device; they can be the same user as the first user or a different user. Furthermore, to ensure data security, appropriate access permissions can be set for the first user and the second user.

[0053] Users can collect raw audio signals in real time using portable listening devices in informal or formal settings, including ambient noise and multiple speakers' voices, to obtain speech stream data. Then, automatic speech recognition technology can be used to convert the speech stream data into corresponding text, yielding candidate information stream data. This candidate information stream data can be directly identified as the target information stream data and uploaded to the cloud for processing, executing the methods described in steps S201 to S203.

[0054] Among them, portable listening devices can be equipped with light prompts to indicate that the user is recording. They can also have noise reduction and voice recognition capabilities, which can identify and record human voices from the recorded sound and upload the recorded audio stream data directly to the cloud for text conversion. Alternatively, they can directly convert the audio stream data to text to obtain the corresponding text data, and then upload the text data to the cloud for further processing.

[0055] In one specific implementation, determining the target information stream data based on the candidate information stream data includes: determining whether the candidate information stream data meets predetermined conditions; if the candidate information stream data meets the predetermined conditions, determining the candidate information stream data as the target information stream data; if the candidate information stream data does not meet the predetermined conditions, continuing to execute the operation in response to the second user and recording the voice stream data.

[0056] In this embodiment, after obtaining candidate information stream data, the portable listening device can further process the candidate information stream data. Only if the candidate information stream data meets predetermined conditions will it be identified as target information stream data and uploaded to the cloud. If the candidate information stream data does not meet the predetermined conditions, it will be saved locally and not uploaded to the cloud.

[0057] The pre-set conditions can be privacy conditions. Only when the recording content meets the privacy conditions and can be uploaded to the cloud will subsequent processing be carried out. If the recording content does not meet the privacy conditions and uploading to the cloud may lead to information leakage, the candidate information stream data will not be used as the target information stream data and will not be uploaded to the cloud. The portable listening device will wait for the user to start recording again and record voice data again without further processing the candidate information stream data recorded this time.

[0058] In one specific implementation, determining whether candidate information stream data meets predetermined conditions includes: obtaining the recording time period corresponding to the candidate information stream data, and determining that the candidate information stream data meets predetermined conditions if the recording time period is within a predetermined time period range; or, obtaining the recording location corresponding to the candidate information stream data, and determining that the candidate information stream data meets predetermined conditions if the recording location is within a predetermined location range; or, detecting whether there are predetermined sensitive words in the candidate information stream data, and determining that the candidate information stream data meets predetermined conditions if there are no predetermined sensitive words in the candidate information stream data.

[0059] In this optional embodiment, the predetermined condition may be at least one of the following: recording time condition, recording location condition, or recording sensitive word condition.

[0060] The recording period refers to the time frame during which voice data is recorded. A pre-defined time range is one or more pre-set time periods used to specify when eligible voice data should be recorded. This step can filter voice data based on time criteria to determine whether it needs processing. For example, a company might only want voice data captured during working hours to be further processed, avoiding the processing of irrelevant data from outside working hours. By setting a pre-defined time range, voice data that does not meet the time criteria can be automatically filtered out, thereby reducing the amount of data processed subsequently, improving processing efficiency, and ensuring that only work-related voice content is processed.

[0061] Recording location refers to the geographical location where the voice data is recorded. A predetermined location range is one or more pre-defined geographical locations used to limit the geographical locations where eligible voice data should be recorded. This step filters voice data based on geographical location to determine whether it needs processing. For example, a company may only want to process voice data captured within the office area to exclude irrelevant data from other locations (such as employees' homes). By setting predetermined location ranges, it is possible to ensure that only voice data relevant to specific geographical locations is processed, thereby improving the targeting and effectiveness of data processing, helping to protect employee privacy, and ensuring that the information received by the AI ​​model is closely related to its work environment.

[0062] Sensitive words refer to words that may involve privacy, confidentiality, or information unsuitable for public processing. This step protects the privacy and compliance of businesses and users by detecting and excluding voice data containing sensitive words. For example, businesses may not want to process voice data containing confidential project names, personally identifiable information, or inappropriate remarks. The sensitive word detection mechanism automatically filters out potentially risky content before data processing, thereby protecting the privacy and security of businesses and users and avoiding unnecessary legal risks and reputational damage.

[0063] In one specific implementation, such as Figure 3As shown, firstly, when users engage in informal communication with others, such as hallway discussions, impromptu phone calls, or tea break conversations, they can activate the listening enhancement module on a portable listening device to enable instant listening. A "click to start listening + light prompt" mechanism ensures the clarity of user operation and protects privacy. Noise reduction and voice recognition technologies are used to collect clear speech content, record the audio, and obtain the raw audio stream. Subsequently, the collected audio content, i.e., the raw audio stream, is sent to the semantic summarization engine. The semantic summarization engine first uses automatic speech recognition technology to transcribe the speech into text, then extracts key task semantics, keywords, event elements, and other structured information from the text based on a large language model, generating a structured semantic summary containing fields such as scene time, keywords, event summary, task candidates, and trust scores. Next, the context injection module packages the structured semantic summary output by the semantic summarization engine into context cache data, and uses silent injection (combining user commands with the latest semantic summary to generate context data), semantic association (combining user commands with related semantic summaries to generate context data), or explicit prompts (i.e., autonomous prompts) to generate context data. The system communicates with the enterprise AI model through various means, including obtaining instructions through the latest semantic summaries and combining them with the latest semantic summaries to generate contextual data, obtaining response results, and displaying them to the user. Contextual information is automatically injected into the AI ​​model's context system. Finally, after receiving user instructions, the enterprise AI model first checks whether there is valid context available and incorporates the contextual information into the Prompt construction process to improve response matching accuracy. It also supports personalized learning and long-term memory reconstruction, thereby achieving accurate understanding and high-quality response to the user's real needs. Throughout the process, all processing is ensured to comply with strict security and privacy standards, including user-initiated activation, privacy prompts, enterprise-level privacy policy configuration, and automatic filtering of local sensitive words.

[0064] To better implement the information processing method in the embodiments of this application, based on the information processing method, the embodiments of this application also provide an information processing device, such as... Figure 4 As shown, the information processing device 400 includes: The acquisition module 410 is used to acquire instruction information and target semantic summary, wherein the target semantic summary is generated by semantic summarizing the target information stream data; Module 420 is used to construct prompt data based on instruction information and target semantic summary; The response module 430 is used to input the prompt data into the intelligent response model and obtain the response result corresponding to the instruction information.

[0065] In this embodiment, instruction information and target semantic summary are obtained, wherein the target semantic summary is generated by semantic summarizing the target information stream data; based on the instruction information and target semantic summary, prompt data is constructed; the prompt data is input into the intelligent response model to obtain the response result corresponding to the instruction information. The information stream data can be processed to generate a semantic summary, enabling the intelligent response model to respond to the instruction information in conjunction with the semantic summary. This allows the intelligent response model to better understand the instruction information and significantly improve the accuracy of the intelligent response model's response.

[0066] In some embodiments of this application, the target semantic summary is generated in the following manner: Extracting event elements from target information stream data; Generate a target semantic summary based on event elements.

[0067] In some embodiments of this application, the acquisition module 410 acquires instruction information and target semantic summary, including: Obtain the input data of the first user to input the intelligent response model, and generate instruction information based on the input data; The semantic digest associated with the instruction information in the semantic digest cache data is determined as the target semantic digest, or the latest semantic digest in the semantic digest cache data is determined as the target semantic digest.

[0068] In some embodiments of this application, the acquisition module 410 acquires instruction information and target semantic summary, including: Obtain the target semantic summary; Extract task information from the target semantic summary and use the task information as instruction information.

[0069] In some embodiments of this application, the target information stream data is obtained in the following manner: In response to the operation of the second user, audio stream data is recorded; The speech stream data is converted into corresponding text to obtain candidate information stream data; Based on the candidate information stream data, the target information stream data is determined.

[0070] In some embodiments of this application, determining target information stream data based on candidate information stream data includes: Determine whether the candidate information stream data meets the predetermined conditions; If the candidate information stream data meets the predetermined conditions, the candidate information stream data will be identified as the target information stream data; If the candidate information stream data does not meet the predetermined conditions, the step of recording the voice stream data continues to be performed in response to the operation of the second user.

[0071] In some embodiments of this application, determining whether candidate information stream data meets predetermined conditions includes: Obtain the recording time period corresponding to the candidate information stream data, and determine that the candidate information stream data meets the predetermined conditions if the recording time period is within the predetermined time period range; Alternatively, obtain the recording location corresponding to the candidate information stream data, and if the recording location is within the predetermined location range, determine that the candidate information stream data meets the predetermined conditions; Alternatively, detect whether there are predetermined sensitive words in the candidate information stream data. If there are no predetermined sensitive words in the candidate information stream data, determine that the candidate information stream data meets the predetermined conditions.

[0072] This application embodiment also provides a terminal device that integrates any of the information processing devices provided in this application embodiment. The terminal device includes: One or more processors; Memory; and One or more applications, wherein the applications are stored in memory and configured to be executed by a processor of the steps in any of the embodiments of the information processing method described above.

[0073] This application also provides a terminal device that integrates any of the information processing devices provided in this application. For example... Figure 5 As shown, it illustrates a structural schematic diagram of the terminal device involved in the embodiments of this application. Specifically: The terminal device may include components such as a processor 501 with one or more processing cores, a memory 502 with one or more computer-readable storage media, a power supply 503, and an input unit 504. Those skilled in the art will understand that... Figure 5 The terminal device structure shown does not constitute a limitation on the terminal device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein: The processor 501 is the control center of the terminal device. It connects various parts of the terminal device via various interfaces and lines, and performs various functions and processes data by running or executing software programs and / or modules stored in the memory 502, and by calling data stored in the memory 502, thereby providing overall monitoring of the terminal device. Optionally, the processor 501 may include one or more processing cores; preferably, the processor 501 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 501.

[0074] The memory 502 can be used to store software programs and modules. The processor 501 executes various functional applications and data processing by running the software programs and modules stored in the memory 502. The memory 502 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 502 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 502 may also include a memory controller to provide the processor 501 with access to the memory 502.

[0075] The terminal device also includes a power supply 503 that supplies power to the various components. Preferably, the power supply 503 can be logically connected to the processor 501 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 503 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0076] The terminal device may also include an input unit 504, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0077] Although not shown, the terminal device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 501 in the terminal device loads the executable files corresponding to the processes of one or more applications into the memory 502 according to the following instructions, and the processor 501 runs the applications stored in the memory 502 to realize various functions, as follows: Obtain instruction information and target semantic summary, wherein the target semantic summary is generated by semantic summarizing the target information stream data; Based on instruction information and target semantic summary, construct prompt data; Input the prompt data into the intelligent response model to obtain the response result corresponding to the instruction information.

[0078] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0079] Therefore, embodiments of this application provide a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk, etc. A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in any of the information processing methods provided in embodiments of this application. For example, the computer program loaded by the processor can execute the following steps: Obtain instruction information and target semantic summary, wherein the target semantic summary is generated by semantic summarizing the target information stream data; Based on instruction information and target semantic summary, construct prompt data; Input the prompt data into the intelligent response model to obtain the response result corresponding to the instruction information.

[0080] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the detailed descriptions of other embodiments above, which will not be repeated here.

[0081] In practice, each of the above units or structures can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units or structures, please refer to the previous method embodiments, which will not be repeated here.

[0082] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0083] The above provides a detailed description of an information processing method, apparatus, terminal device, and computer-readable storage medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. An information processing method, characterized in that, Applied to servers, including: Obtain instruction information and target semantic summary, wherein the target semantic summary is generated by semantic summarizing the target information stream data; Based on the instruction information and the target semantic summary, prompt data is constructed; The prompt data is input into the intelligent response model to obtain the response result corresponding to the instruction information.

2. The information processing method according to claim 1, characterized in that, The target semantic summary is generated in the following manner: Extract event elements from the target information stream data; Based on the event elements, the target semantic summary is generated.

3. The information processing method according to claim 1, characterized in that, The acquisition of instruction information and target semantic summary includes: Obtain input data from the first user to input the intelligent response model, and generate the instruction information based on the input data; The semantic summary associated with the instruction information in the semantic summary cache data is determined as the target semantic summary, or the latest semantic summary in the semantic summary cache data is determined as the target semantic summary.

4. The information processing method according to claim 1, characterized in that, The acquisition of instruction information and target semantic summary includes: Obtain the target semantic summary; Task information is extracted from the target semantic summary, and the task information is used as the instruction information.

5. The information processing method according to claim 1, characterized in that, The target information stream data is obtained in the following manner: In response to the operation of the second user, audio stream data is recorded; The speech stream data is converted into corresponding text to obtain candidate information stream data; Based on the candidate information stream data, the target information stream data is determined.

6. The information processing method according to claim 5, characterized in that, The step of determining the target information stream data based on the candidate information stream data includes: Determine whether the candidate information stream data meets the predetermined conditions; If the information flow data meets predetermined conditions, the candidate information flow data is determined as the target information flow data; If the information stream data does not meet the predetermined conditions, the step of recording the voice stream data in response to the operation of the second user continues.

7. The information processing method according to claim 6, characterized in that, Determining whether the candidate information stream data meets predetermined conditions includes: Obtain the recording time period corresponding to the candidate information stream data, and if the recording time period is within a predetermined time period range, determine that the candidate information stream data meets the predetermined conditions; Alternatively, obtain the recording position corresponding to the candidate information stream data, and if the recording position is within a predetermined position range, determine that the candidate information stream data meets the predetermined conditions; Alternatively, detect whether there are predetermined sensitive words in the candidate information stream data. If there are no predetermined sensitive words in the candidate information stream data, determine that the candidate information stream data meets the predetermined conditions.

8. An information processing device, characterized in that, include: The acquisition module is used to acquire instruction information and target semantic summary, wherein the target semantic summary is obtained by generating a semantic summary of the target information stream data; The construction module is used to construct prompt data based on the instruction information and the target semantic summary; The response module is used to input the prompt data into the intelligent response model to obtain the response result corresponding to the instruction information.

9. A terminal device, characterized in that, The terminal device includes: one or more processors, a memory, and one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the information processing method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores a computer program, which is loaded by a processor to execute the steps of the information processing method according to any one of claims 1 to 7.

Images