Information processing method and apparatus, device, and storage medium

Abstract

The embodiments of the present disclosure relate to an information processing method and apparatus, a device, and a storage medium. The method proposed herein comprises: acquiring message data, which comprises a plurality of historical messages associated with a target object; on the basis of temporal information of the plurality of historical messages, organizing the message data into a plurality of message segments; providing the plurality of message segments to a target model to generate annotation information for the plurality of message segments, wherein the annotation information indicates whether the plurality of message segments is associated with the same topic; and on the basis of the annotation information, aggregating a first group of message segments associated with a first topic into a first conversation. In this way, on the basis of the plurality of historical messages associated with the target object, the embodiments of the present disclosure can generate annotation information associated with a certain topic, thereby reducing the number of requests and improving the accuracy of conversation segmentation.

Description

Information processing methods, apparatus, equipment and storage media Technical Field

[0001] The exemplary embodiments disclosed herein generally relate to the field of computers, and more particularly to methods, apparatus, devices and computer-readable storage media for information processing. Background Technology

[0002] With the development of computer and internet technologies, more and more users are using electronic devices to send and receive messages, thus enabling conversations. To utilize historical conversation information on these devices to obtain the information people need, it is necessary to segment the conversation information. Therefore, the accuracy of conversation segmentation has become a key concern.

[0003] Summary of the Invention

[0004] In a first aspect of this disclosure, an information processing method is provided. The method includes: acquiring message data, the message data including multiple historical messages associated with a target object; organizing the message data into multiple message segments based on time information of the multiple historical messages; providing the multiple message segments to a target model to generate annotation information for the multiple message segments, the annotation information indicating whether the multiple message segments are associated with the same topic; and aggregating a first group of message segments associated with a first topic into a first session based on the annotation information.

[0005] In a second aspect of this disclosure, an apparatus for information processing is provided. The apparatus includes: an acquisition module configured to acquire message data, the message data including multiple historical messages associated with a target object; an organization module configured to organize the message data into multiple message segments based on time information of the multiple historical messages; a providing module configured to provide the multiple message segments to a target model to generate annotation information for the multiple message segments, the annotation information indicating whether the multiple message segments are associated with the same topic; and an aggregation module configured to aggregate a first group of message segments associated with a first topic into a first session based on the annotation information.

[0006] In a third aspect of this disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform the method of the first aspect.

[0007] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program that can be executed by a processor to implement the method of the first aspect.

[0008] In a fifth aspect of this disclosure, a computer program product is provided. The computer program product includes computer-executable instructions that, when executed by a processor, implement the method according to a first aspect of this disclosure.

[0009] It should be understood that the content described in this content section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0010] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0011] Figure 1 shows a schematic diagram of an example environment in which embodiments of the present disclosure may be implemented;

[0012] Figure 2 shows a flowchart of an example information processing procedure according to some embodiments of the present disclosure;

[0013] Figures 3A and 3B illustrate schematic diagrams of example information processing procedures according to some embodiments of the present disclosure;

[0014] Figure 4 shows a schematic structural block diagram of an example information processing apparatus according to some embodiments of the present disclosure; and

[0015] Figure 5 shows a block diagram of an electronic device capable of implementing several embodiments of the present disclosure. Detailed Implementation

[0016] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0017] It should be noted that the headings of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and embodiments of any type may be included under any section / subsection. Furthermore, embodiments described in any section / subsection may be combined in any way with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0018] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below. The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0019] The embodiments of this disclosure may involve user data, data acquisition, and / or use. All of these aspects comply with applicable laws, regulations, and relevant provisions. In the embodiments of this disclosure, all data collection, acquisition, processing, manipulation, forwarding, and use are conducted with the user's knowledge and confirmation. Accordingly, in implementing the embodiments of this disclosure, the type, scope of use, and usage scenarios of any data or information that may be involved should be communicated to the user and their authorization obtained in accordance with relevant laws and regulations through appropriate means. The specific methods of notification and / or authorization may vary depending on the actual situation and application scenario, and the scope of this disclosure is not limited in this respect.

[0020] In this specification and the embodiments, any processing of personal information will be carried out only under the premise of legality (such as obtaining the consent of the personal information subject, or being necessary for the performance of a contract), and will only be carried out within the scope stipulated or agreed upon. A user's refusal to process personal information other than that necessary for basic functions will not affect the user's use of basic functions.

[0021] Traditional methods of directly severing sessions at silent intervals may result in false positives; when user intervals approach a threshold, some continuous operations are split into multiple sessions; and coherent single intents cannot be recognized. Therefore, this method of session segmentation suffers from inaccurate segmentation.

[0022] Embodiments of this disclosure propose an information processing scheme. According to this scheme, message data can be acquired, including multiple historical messages associated with a target object; based on the time information of the multiple historical messages, the message data is organized into multiple message segments; multiple message segments are provided to a target model to generate annotation information for the multiple message segments, the annotation information indicating whether the multiple message segments are associated with the same topic; and based on the annotation information, a first group of message segments associated with a first topic is aggregated into a first session.

[0023] In this way, embodiments of this disclosure can generate annotation information associated with a certain topic based on multiple historical messages associated with the target object, thereby reducing the number of requests and improving the accuracy of session segmentation.

[0024] The following section provides a detailed description of various example implementations of this scheme, with reference to the accompanying drawings.

[0025] Example Environment

[0026] Figure 1 illustrates a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. As shown in Figure 1, the example environment 100 may include an electronic device 110.

[0027] In this example environment 100, electronic device 110 can run an application 120 that supports user interface interaction. Application 120 can be any suitable type of application for user interface interaction, examples of which may include, but are not limited to, browser applications, interactive applications, or other suitable applications. User 140 can interact with application 120 via electronic device 110 and / or its attached devices.

[0028] In environment 100 of Figure 1, if application 120 is active, electronic device 110 can use application 120 to present interface 150 for supporting interface interaction.

[0029] In some embodiments, electronic device 110 communicates with server 130 to provide services to application 120. Electronic device 110 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, electronic device 110 can also support any type of user-facing interface (such as "wearable" circuitry).

[0030] Server 130 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. Server 130 may include, for example, computing systems / servers such as mainframes, edge computing nodes, computing devices in a cloud environment, etc. Server 130 can provide backend services for applications 120 that support content presentation in electronic devices 110.

[0031] A communication connection can be established between server 130 and electronic device 110. This communication connection can be established via wired or wireless means. The communication connection may include, but is not limited to, Bluetooth, mobile network, Universal Serial Bus, and Wi-Fi connections; the embodiments of this disclosure are not limited in this respect. In the embodiments of this disclosure, server 130 and electronic device 110 can achieve signaling interaction through the communication connection between them.

[0032] It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.

[0033] Example process

[0034] Figure 2 shows a flowchart of an example information processing procedure 200 according to some embodiments of the present disclosure. Procedure 200 can be implemented at electronic device 110, server 130 or other suitable electronic device. Procedure 200 is described below with reference to Figure 1.

[0035] As shown in the figure, in box 210, electronic device 110 acquires message data, which includes multiple historical messages associated with the target object.

[0036] In some embodiments, such message data may also include multiple response messages from the target object to multiple historical messages.

[0037] In some embodiments, such multiple historical messages may be, for example, multi-turn conversation messages associated with a target object in a dialogue scenario. Furthermore, such multiple historical messages may also be operation messages from the target object to the application, such as clicks, long presses, and shares by the target object. It is understood that the above are merely examples of message data types, and this disclosure is not intended to limit the type of message data acquired.

[0038] For ease of description, the following will use a dialogue scenario between a user and a bot as an example.

[0039] Referring to Figure 3A, such data messages can include multiple historical messages associated with the target object and corresponding multiple response messages. As an example, the user's question message is "How is the weather today?", and the corresponding response message from the robot program is "The weather is sunny today."

[0040] In box 220, electronic device 110 organizes message data into multiple message segments based on the time information of multiple historical messages.

[0041] In some embodiments, the electronic device 110 organizes message data into multiple message segments based on the time information of multiple historical messages and according to a preset time window (e.g., 1 minute, 30 minutes). In some embodiments, each message segment may include at least one historical message and a corresponding reply message. For ease of description, the following description uses the example of each message segment including one historical message and a corresponding reply message.

[0042] In box 230, electronic device 110 provides multiple message segments to the target model to generate annotation information for the multiple message segments, the annotation information indicating whether the multiple message segments are related to the same topic.

[0043] In some embodiments, the target model may include a language model that may be pre-trained based on a supervised fine-tuning training process to generate annotation information for multiple message segments.

[0044] In some embodiments, if the target model has a large window, the electronic device 110 may also provide the target model with descriptive information corresponding to multiple message segments. Continuing to refer to FIG3A, such descriptive information may be the identity information of the target object (e.g., user, robot program) and / or the time interval corresponding to the corresponding message segment.

[0045] Referring again to Figure 3A, the electronic device 110 provides four message segments to the language model. Each message segment can have a corresponding round number, the identity information of the target object, the time interval corresponding to the previous message segment, historical messages, and the corresponding reply message.

[0046] In this way, the electronic device 110 can output more accurate annotation information based on more descriptive information, thereby improving the accuracy of session segmentation.

[0047] In some embodiments, the electronic device 110 may provide guidance to the language model to instruct the language model to segment the multiple message segments based on the topics of the multiple message segments.

[0048] Furthermore, the electronic device 110 acquires all annotation information generated by the language model for multiple message segments. The electronic device 110 can output the annotation information as a string or an array to indicate whether the multiple message segments are related to the same topic.

[0049] Referring again to Figure 3A, the electronic device 110 identifies the topic matching of the first message segment and the second message segment based on the language model and prompts. For example, the first message segment and the second message segment can be labeled as 1, and the third message segment and the fourth message segment can be labeled as 0. The electronic device 110 outputs the corresponding array [1,1,0,0] based on the labeling information.

[0050] As another example, if the annotation information output by the language model corresponds to the array form [1,1,0,1], it means that the first message segment, the second message segment, and the fourth message segment are topic matched.

[0051] Referring to Figure 3B, the electronic device 110 can also utilize a target model to process multiple message segments to generate confidence information. As an example, such confidence information indicates the confidence level of multiple message segments matching the same topic. Such a target model could be, for example, a transformer model. Due to the limited input window size of these models, the electronic device 110 can process the acquired message data, for example, omitting acquired bot response messages, time intervals, identity information, while retaining round numbers and historical messages. In some examples, excessively long historical messages can be truncated to match the model's input window size.

[0052] Furthermore, the electronic device 110 obtains a confidence threshold. Based on the relationship between the confidence levels and the confidence thresholds corresponding to the multiple message segments, the electronic device 110 generates annotation information for the multiple message segments.

[0053] Referring to Figure 3B, it can be seen that the confidence level of the first message segment is 0.7, the second message segment is 0.6, the third message segment is 0.2, and the fourth message segment is 0.1. Assuming a confidence threshold of 0.5, if the confidence levels of the first and second message segments are both greater than this threshold of 0.5, it indicates that the first and second message segments match in terms of topic, and both are labeled as 1. The third and fourth message segments are labeled as 0. The electronic device 110 outputs the corresponding array [1,1,0,0] based on this labeling information.

[0054] In box 240, electronic device 110 aggregates the first group of messages associated with the first topic into a first session based on the annotation information.

[0055] In some embodiments, the annotation information includes a set of tag sequences associated with multiple message segments, such tag sequences may be presented, for example, as an array. Furthermore, each tag sequence corresponds to a specific topic, and each tag sequence includes multiple tags corresponding to the multiple message segments, each tag indicating whether the corresponding message segment matches the corresponding topic.

[0056] In some embodiments, such a set of tag sequences includes a first tag sequence corresponding to a first topic. For example, such a first tag sequence is [1,1,0,0]. Based on this first tag sequence, the electronic device 110 determines a first set of message segments associated with the first topic from multiple message segments, namely a first message segment and a second message segment, and aggregates multiple messages included in the first message segment and the second message segment into a first session.

[0057] In some embodiments, such a set of tag sequences further includes a second tag sequence corresponding to the second topic. Based on the second tag sequence, the electronic device 110 determines a second set of message segments associated with the second topic from multiple message segments, and the electronic device 110 aggregates the second set of message segments associated with the second topic into a second session.

[0058] As an example, if the second tag sequence determined by the four message segments based on the second topic is [1,1,0,1], then the electronic device 110 can determine the first message segment, the second message segment and the fourth message segment related to the second topic from the four message segments, and aggregate the multiple messages included therein into a second session.

[0059] Understandably, multiple message segments can be based on different topics and have their own corresponding tag sequences. Electronic device 110 aggregates the message segments into different sessions based on the corresponding tag sequences.

[0060] In this way, embodiments of this disclosure can generate annotation information associated with a certain topic based on multiple historical messages associated with the target object, thereby reducing the number of requests and improving the accuracy of session segmentation.

[0061] Example devices and equipment

[0062] Embodiments of this disclosure also provide corresponding apparatus for implementing the methods or processes described above. FIG4 shows a schematic structural block diagram of an example information processing apparatus 400 according to certain embodiments of this disclosure. Apparatus 400 may be implemented as or included in electronic device 110. The various modules / components in apparatus 400 may be implemented by hardware, software, firmware, or any combination thereof.

[0063] As shown in Figure 4, the device 400 includes an acquisition module 410 configured to acquire message data, the message data including multiple historical messages associated with a target object; an organization module 420 configured to organize the message data into multiple message segments based on the time information of the multiple historical messages; a providing module 430 configured to provide multiple message segments to the target model to generate annotation information for the multiple message segments, the annotation information indicating whether the multiple message segments are associated with the same topic; and an aggregation module 440 configured to aggregate a first group of message segments associated with a first topic into a first session based on the annotation information.

[0064] In some embodiments, the apparatus 400 further includes a first providing module configured to provide the target model with descriptive information corresponding to multiple message segments to generate annotation information for the multiple message segments. The descriptive information includes at least one of the following: the identity information of the target object; and the time interval corresponding to the corresponding message segment.

[0065] In some embodiments, the message data also includes multiple response messages from the target object to multiple historical messages, with each message segment including at least one historical message and a corresponding response message.

[0066] In some embodiments, the organization module 420 is further configured to organize message data into multiple message segments based on time information and according to a preset time window.

[0067] In some embodiments, the target model includes a language model, and the providing module 430 is further configured to provide guidance to the language model, the guidance being used to instruct the target model to divide multiple message segments based on the topics of multiple message segments; and to obtain annotation information generated by the language model for the multiple message segments.

[0068] In some embodiments, the providing module 430 is further configured to process multiple message segments using a target model to generate confidence information indicating the confidence level of the multiple message segments matching the same topic; and to generate annotation information for the multiple message segments based on the confidence information.

[0069] In some embodiments, the annotation information includes a set of tag sequences associated with multiple message segments, each tag sequence corresponding to a corresponding topic, and each tag sequence includes multiple tags corresponding to multiple message segments, each tag indicating whether the corresponding message segment matches the corresponding topic.

[0070] In some embodiments, a set of tag sequences includes a first tag sequence corresponding to a first topic, and the apparatus 400 further includes a first determining module configured to determine a first set of message segments associated with the first topic from a plurality of message segments based on the first tag sequence.

[0071] In some embodiments, a set of tag sequences includes a second tag sequence corresponding to a second topic, and the apparatus 400 further includes a second determining module configured to determine a second set of message segments associated with the second topic from a plurality of message segments based on the second tag sequence; and to aggregate the second set of message segments associated with the second topic into a second session.

[0072] The modules included in device 400 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units can be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to machine-executable instructions, some or all of the modules in device 400 can be implemented at least partially by one or more hardware logic components. By way of example, and not limitation, exemplary types of hardware logic components that can be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0073] Figure 5 shows a block diagram of an electronic device 500 in which one or more embodiments of the present disclosure may be implemented. It should be understood that the electronic device 500 shown in Figure 5 is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. The electronic device 500 shown in Figure 5 can be used to implement the electronic device 110 of Figure 1.

[0074] As shown in Figure 5, the electronic device 500 is in the form of a general-purpose electronic device. Components of the electronic device 500 may include, but are not limited to, one or more processors or processing units 510, memory 520, storage devices 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. The processing unit 510 may be a physical or virtual processor and is capable of performing various processes according to programs stored in the memory 520. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of the electronic device 500.

[0075] Electronic device 500 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 520 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 530 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 500.

[0076] Electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 5, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks may be provided. In these cases, each drive may be connected to a bus (not shown) via one or more data media interfaces. Memory 520 may include computer program product 525 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0077] Communication unit 540 enables communication with other electronic devices via a communication medium. Additionally, the functionality of components of electronic device 500 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, electronic device 500 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0078] Input device 550 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 560 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 500 can also communicate with one or more external devices (not shown) via communication unit 540 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 500, or with any device that enables electronic device 500 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0079] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0080] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0081] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0082] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0083] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0084] Various implementations of this disclosure have been described above. The foregoing description is exemplary and not exhaustive, nor is it limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. An information processing method, comprising: Obtain message data, which includes multiple historical messages associated with the target object; Based on the time information of the aforementioned historical messages, the message data is organized into multiple message segments; The target model is provided with the multiple message segments to generate annotation information for the multiple message segments, the annotation information indicating whether the multiple message segments are associated with the same topic; as well as Based on the annotation information, the first group of messages associated with the first topic are segmented and aggregated into the first session.

2. The method according to claim 1, further comprising: The target model is provided with descriptive information corresponding to the plurality of message segments to generate the annotation information for the plurality of message segments. The descriptive information includes at least one of the following: the identity information of the target object; and the time interval corresponding to the corresponding message segment.

3. The method according to claim 1, wherein the message data further includes multiple response messages from the target object to the multiple historical messages, and each message segment includes at least one historical message and a corresponding response message.

4. The method according to claim 1, wherein organizing the message data into multiple message segments based on the time information of the plurality of historical messages includes: Based on the time information and according to the preset time window, the message data is organized into the multiple message segments.

5. The method according to claim 1, wherein the target model includes a language model, and providing the target model with the plurality of message segments to generate annotation information for the plurality of message segments includes: Provide guidance to the language model, the guidance being used to instruct the target model to divide the multiple message segments based on the topics of the multiple message segments; as well as Obtain the annotations generated by the language model for the multiple message segments. information.

6. The method according to claim 1, wherein providing the plurality of message segments to the target model to generate annotation information for the plurality of message segments comprises: The target model is used to process the multiple message segments to generate confidence information, which indicates the confidence level of the multiple message segments matching the same topic; as well as Based on the confidence information, the annotation information for the multiple message segments is generated.

7. The method of claim 1, wherein the annotation information includes a set of tag sequences associated with the plurality of message segments, each tag sequence corresponding to a corresponding topic, and each tag sequence includes a plurality of tags corresponding to the plurality of message segments, each tag indicating whether the corresponding message segment matches the corresponding topic.

8. The method of claim 7, wherein the set of tag sequences includes a first tag sequence corresponding to the first topic, and the method further includes: Based on the first tag sequence, the first group of message segments associated with the first topic is determined from the plurality of message segments.

9. The method of claim 7, wherein the set of tag sequences includes a second tag sequence corresponding to a second topic, and the method further includes: Based on the second tag sequence, a second group of message segments associated with the second topic is determined from the plurality of message segments; as well as The second group of messages associated with the second topic are segmented and aggregated into a second session.

10. An information processing apparatus, comprising: The acquisition module is configured to acquire message data, which includes multiple historical messages associated with the target object; The organization module is configured to organize the message data into multiple message segments based on the time information of the multiple historical messages; A providing module is configured to provide the multiple message segments to a target model to generate annotation information for the multiple message segments, the annotation information indicating whether the multiple message segments are associated with the same topic; as well as The aggregation module is configured to aggregate a first group of messages associated with a first topic into a first session based on the annotation information.

11. An electronic device, comprising: At least one processing unit; as well as At least one memory, coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, which, when executed by the at least one processing unit, cause the electronic device to perform the method according to any one of claims 1 to 9.

12. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method according to any one of claims 1 to 9.

13. A computer program product comprising computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 9.

Images