Information processing method and device and electronic equipment

Abstract

The invention discloses an information processing method and device and electronic equipment, and the method comprises the steps: obtaining interaction data based on session communication with second equipment, the interaction data comprising first data transmitted from the second equipment to first equipment, and second data obtained based on an input part of the first equipment; analyzing the content of the interaction data; outputting third data to the second equipment in response to the condition that the content of the interaction data meets the output condition; wherein the third data is data generated by the target model based on the content of the first data.

Description

Technical Field

[0001] This application relates to the field of communications, and in particular, to an information processing method, apparatus, and electronic device. Background Art

[0002] During the process of using an electronic device for communication, whether it is audio communication or communication through text content, if it is necessary to query or obtain relevant information and output it, it can only be achieved through cumbersome operations, and the operation is inconvenient. Summary of the Invention

[0003] In view of this, this application provides an information processing method, apparatus, and electronic device, and the specific solutions are as follows:

[0004] An information processing method includes:

[0005] Based on the session communication with a second device, obtain interaction data, where the interaction data includes first data transmitted from the second device to the first device, and second data obtained based on the input component of the first device;

[0006] Analyze the content of the interaction data;

[0007] In response to the content of the interaction data satisfying the output condition, output third data to the second device;

[0008] Wherein, the third data is data generated by a target model based on the content of the first data.

[0009] Further, the session communication with the second device is: establishing session communication based on the communication identifier of the session party of the target application, and the interaction data is the data of the session party during the session communication;

[0010] The method further includes:

[0011] Based on the session communication with the second device, call a first intelligent program;

[0012] The first intelligent program is used to execute the obtaining of the interaction data, the analyzing of the content of the interaction data, and the outputting of the third data to the second device representing the communication identifier of the other party based on the target application in response to the content of the interaction data satisfying the output condition;

[0013] The first intelligent program is further used to call the target model to generate the third data.

[0014] Further, the content of the interaction data satisfying the output condition includes at least one of the following:

[0015] If the first keyword is included in the first data, it indicates that the content of the interaction data meets the output condition;

[0016] If the second keyword is included in the second data, it indicates that the content of the interaction data meets the output condition;

[0017] If the third keyword for the first keyword in the first data is not included in the second data, it indicates that the content of the interaction data meets the output condition.

[0018] Further, it further includes:

[0019] The target model generates third data based on the first data including the first keyword, and the third data is transmitted to the second device based on the session communication.

[0020] Further, in the case of outputting the third data to the second device, the method further includes:

[0021] If there is second data belonging to the same round of session as the first data, the second data is transmitted to the second device based on the session communication or not transmitted to the second device.

[0022] Further, the case where if the third keyword for the first keyword in the first data is not included in the second data, it indicates that the content of the interaction data meets the output condition includes:

[0023] If the third keyword for the first keyword in the first data is not included in the second data, and the interaction data expresses the end of a topic, it indicates that the content of the interaction data meets the output condition.

[0024] Further, the analyzing the content of the interaction data includes:

[0025] The first intelligent program analyzes the semantics of the content of the interaction data. If it is determined that the semantics of the content of the interaction data meet the authorization condition, the second intelligent program is called; wherein, the second intelligent program responds to each first data in the session communication with the second device;

[0026] The outputting the third data to the second device in response to the content of the interaction data meeting the output condition includes:

[0027] The second intelligent program calls the target model to generate third data for the current first data;

[0028] Transmit the third data to the second device through the session communication for the current first data;

[0029] Wherein, the first intelligent program is different from the second intelligent program.

[0030] Further, the method further includes:

[0031] Outputting the third data by the first device.

[0032] An information processing apparatus, comprising:

[0033] A first module, configured to obtain interaction data based on session communication with a second device, where the interaction data includes first data transmitted from the second device to the first device, and second data obtained based on an input component of the first device;

[0034] A second module, configured to analyze the content of the interaction data;

[0035] A third module, configured to output third data to the second device in response to the content of the interaction data satisfying an output condition;

[0036] Wherein the third data is data generated by a target model based on the content of the first data.

[0037] An electronic device, comprising: at least one communication component, at least one memory, and at least one processor, wherein:

[0038] The at least one communication component is configured to perform session communication with a second device;

[0039] The memory stores at least computer instructions and a target model;

[0040] The processor is configured to load the computer instructions to implement:

[0041] Analyzing the content of the interaction data, and outputting third data to the second device in response to the content of the interaction data satisfying an output condition;

[0042] The processor is further configured to load the target model to implement generating third data based on the content of the first data. Description of the Drawings

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0044] Figure 1 It is a flowchart of an information processing method disclosed in an embodiment of the present application;

[0045] Figure 2Flowchart of an information processing method disclosed in an embodiment of the present application;

[0046] Figure 3 Schematic diagram of a communication interface on a first device when a user 1 and a user 2 conduct session communication via short messages, disclosed in an embodiment of the present application;

[0047] Figure 4 Flowchart of an information processing method disclosed in an embodiment of the present application;

[0048] Figure 5 Flowchart of an information processing method disclosed in an embodiment of the present application;

[0049] Figure 6 Flowchart of an information processing device disclosed in an embodiment of the present application;

[0050] Figure 7 Schematic diagram of the structure of an electronic device disclosed in an embodiment of the present application. Detailed implementation manners

[0051] The following describes the embodiments of the present application in conjunction with the accompanying drawings in the embodiments of the present application. The terms used in the implementation part of the present application are only used to explain the specific embodiments of the present application, rather than aiming to limit the present application.

[0052] The following describes the embodiments of the present application in conjunction with the accompanying drawings. Those of ordinary skill in the art know that with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are equally applicable to similar technical problems.

[0053] The terms "first", "second", etc. in the specification, claims and the above-mentioned accompanying drawings of the present application are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances, which is only a way of distinguishing when describing objects with the same attributes in the embodiments of the present application. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion, so that a process, method, system, product or device including a series of units does not have to be limited to those units, but may include other units not clearly listed or inherent to these process, method, product or device.

[0054] The present application discloses an information processing method, and its flowchart is as Figure 1 shown, including:

[0055] Step S11: Obtain interaction data based on session communication with a second device, where the interaction data includes first data transmitted from the second device to the first device, and second data obtained based on an input component of the first device;

[0056] Step S12: Analyze the content of the interaction data;

[0057] Step S13: In response to the content of the interaction data satisfying the output condition, output third data to the second device, where the third data is data generated by the target model based on the content of the first data.

[0058] During the process of communication using an electronic device, whether it is audio communication or communication through text content, if relevant information needs to be queried or obtained and output, it requires cumbersome operations to achieve, which is inconvenient to operate.

[0059] Based on this, in this solution, when the first device and the second device conduct session communication, it is necessary to obtain the interaction data during the session communication and analyze it in order to generate third data, and be able to output the third data to the second device when the output condition is met, realizing the generation of relevant data based on the interaction data during the session communication and outputting it. This process can automatically generate and output relevant data without the user performing operations, simplifying the operation and improving the user experience.

[0060] The session communication between the first device and the second device can be: the first device and the second device conduct an audio session, such as a voice call, or it can be: the first device and the second device conduct a text-based session, such as typing and chatting.

[0061] During the session communication process between the first device and the second device, the first device transmits second data to the second device, and the second device transmits first data to the first device. The first data and the second data are determined as interaction data, that is, the interaction data includes the first data and the second data. If it is an audio session, the interaction data is the voices of both communication parties. If it is a text-based session, the interaction data is the chat text of both communication parties.

[0062] The information processing method disclosed in this embodiment can be applied to the first device or the second device. In this embodiment, it is described by taking the application to the first device as an example. The first device may include an intelligent program or system, and the intelligent program or system implements the information processing method disclosed in this embodiment. That is, as long as there is a session communication between the first device and the second device, the intelligent program or system will monitor the session communication until it is determined that the output condition is met, and then actively output the third data to the second device, ensuring the timely acquisition of the third data. At the same time, without manual operation by the user, the user experience is improved.

[0063] The intelligent program involved in this embodiment is an application of artificial intelligence technology, that is, an intelligent agent (Agent), which has the ability to direct the operation of the target model, including but not limited to calling the target model to execute related tasks, or the intelligent program itself includes the target model, and the target model is run when the intelligent program is run. The behavior of the intelligent program is determined by the target model in the intelligent program according to the current state and external input. Among them, the target model provides a decision-making basis through learning and training with a large amount of data. The intelligent agent can also call tools, plugins, and knowledge bases to provide reasoning, decision-making, and execution capabilities.

[0064] During the session communication between the first device and the second device, the first device can obtain the first data transmitted from the second device to the first device, and can also obtain the second data. The second data is directly obtained based on the input component of the first device, that is: when the user of the first device transmits the second data to the second device, first, the second data is input into the first device through the input component of the first device, and then the first device can transmit the second data to the second device through the network. When the user inputs the second data into the first device through the input component of the first device, the first device can obtain the second data.

[0065] After the first device obtains the interaction data, it needs to analyze the content of the interaction data to determine whether the content of the interaction data meets the output condition. Among them, whether the content of the interaction data meets the output condition, that is, whether the first device needs to output the third data to the second device. If it is determined that the output condition is met based on the content of the interaction data, the first device needs to output the third data to the second device; if it is determined that the output condition is not met based on the content of the interaction data, the first device does not need to output the third data to the second device.

[0066] Among them, the third data is the data generated by the first device by the target model based on the content of the first data. The third data can be generated and output when it is determined that the output condition is met; it can also be generated by the target model based on the content of the first data after obtaining the content of the interaction data, and is output only when it is determined that the content of the interaction data meets the output condition.

[0067] Taking query as an example, the generation of the third data here can be the original data obtained after the target model executes the query, for example: the order number, phone number, etc. queried; it can also be the data processed and generated by the target model based on the queried data, for example: the text or audio output after polishing the queried order number, phone number, etc. according to the current session style. For query-type tasks, the target model can retrieve locally from the first device or search from the cloud to obtain data related to the content of the first data.

[0068] Since the first data is the data transmitted from the second device to the first device, and the second data is obtained from the input component of the first device, that is, the second data is the data to be transmitted to the second device. When at least the data corresponding to obtaining a certain piece of information is included in the first data transmitted from the second device to the first device, it can be determined that the content of the interaction data meets the output condition. At this time, based on the relevant data of a certain piece of information included in the first data, the target model is used for retrieval to determine the third data generated by the target model based on the content of the first data, and this third data is the data corresponding to the certain piece of information.

[0069] In addition, when it is determined that the content of the interaction data meets the output condition, the third data is output to the second device. When the third data is output to the second device, the data type presented by the third data can be related to the type of the current session communication.

[0070] Specifically, if the current session communication between the first device and the second device is a voice call, the third data is converted into an audio data type, and the third data of the audio data type is output to the second device. After the second device obtains the third data of the audio data type, the third data is played on the second device so that the user of the second device can hear the played third data.

[0071] Among them, in order to make it not abrupt when the user of the second device listens to the played third data, when converting the third data into an audio data type, a target tone color and / or a target emotion can be set, that is, the third data is converted into an audio of an audio data type with a target tone color and / or a target emotion, so that the user of the second device can hear the third data with a target tone color and / or a target emotion, so as to ensure the communication experience of the user of the second device when communicating with the first device by voice.

[0072] Among them, the target tone color can be: a preset tone color, or: a simulated tone color obtained by simulating the tone color of the user of the first device; the target emotion can be: a preset emotion, or: determining the current emotion of the user of the first device, and obtaining a target emotion by simulating the current emotion of the user of the first device.

[0073] The information processing method disclosed in this embodiment obtains interaction data based on session communication with a second device. The interaction data includes first data transmitted from the second device to the first device and second data obtained based on an input component of the first device. Analyze the content of the interaction data; in response to the content of the interaction data meeting the output condition, output third data to the second device. The third data is data generated by a target model based on the content of the first data. In this solution, when the first device and the second device perform session communication, the content of the interaction data during the session communication can be analyzed, and when the condition is met, the data generated by the target model based on the content of the first data can be output, realizing the generation and output of the third data only based on the content of the interaction data, simplifying the operation process of outputting the third data during the session communication, improving the efficiency of the session communication, and improving the user experience.

[0074] This embodiment discloses an information processing method, and its flowchart is as Figure 2 shown, including:

[0075] Step S21: Based on session communication with a second device, call a first intelligent program, where the session communication with the second device is session communication established based on the communication identifier of the session party of the target application program;

[0076] Step S22: Obtain interaction data through the first intelligent program. The interaction data is the data of the session party during the session communication, including: first data transmitted from the second device to the first device and second data obtained based on an input component of the first device;

[0077] Step S23: Analyze the content of the interaction data through the first intelligent program to determine that the content of the interaction data meets the output condition;

[0078] Step S24: In response to the content of the interaction data meeting the output condition, output third data to the second device representing the communication identifier of the other party based on the target application program; where the third data is data generated by the first intelligent program calling a target model, and the target model generates the data based on the content of the first data.

[0079] The information processing method disclosed in this embodiment is applied to the first device. By monitoring the session communication between the first device and the second device by the first device, as long as it is determined that session communication is established between the first device and the second device, the first intelligent program is called, and the first intelligent program monitors the content of the interaction data during the session communication, so that when the output condition is met, that is, when relevant data needs to be output, the third data can be transmitted to the second device in a timely manner to ensure the communication efficiency between the first device and the second device.

[0080] Among them, the session communication between the first device and the second device can be: session communication established based on the communication identifier of the session party of the target application. The target application can be a call program. For example, a call between two devices can be established through the phone numbers in the phone book of the mobile phone. It can also be a voice program. For example, a voice call between the first device and the second device of user a can be established through the identifier of user a in the voice program. Or, it can be a text session program. For example, the session communication between the first device and the second device can be realized in the form of text messages, or the session communication between the first device and the second device can be realized in the form of WeChat short messages, etc.

[0081] After the first device and the second device establish session communication through the communication identifier of the session party of the target application, during the session communication process, the data output by the session side of the first device to the second device and the data output by the session side of the second device to the first device can both be determined as interaction data.

[0082] The first device monitors whether the first device has established session communication with other devices. As long as it is determined that the first device has established session communication with other devices, the first intelligent program is called, and the first intelligent program conducts monitoring and / or supplementation during the subsequent session communication process.

[0083] If the first device sends a short message to a certain communication identifier, it can be determined that session communication has been established between the first device and the second device corresponding to the communication identifier. At this time, the first intelligent program is called, and the first intelligent program monitors and analyzes the interaction data between the first device and the second device; or, if the first device receives a short message sent by the second device, it can be determined that session communication has been established between the first device and the second device. At this time, the first intelligent program is called.

[0084] If the first device sends a voice communication request to a certain communication identifier, or the first device receives a voice communication request sent by the second device, it can be determined that session communication has been established between the first device and the second device corresponding to the communication identifier. At this time, the first intelligent program is directly called. Or, when the first device sends a voice communication request to a certain communication identifier and it is determined that the voice communication request is responded to and the first device and the second device corresponding to the communication identifier can conduct voice communication, the first intelligent program is called to ensure that as long as the first intelligent program is called, there is interaction data that can be analyzed.

[0085] Among them, it should be noted that the first intelligent program can be called by the first device after the first device determines that a session communication is established between the first device and the second device, so that the first intelligent program can be started and execute the analysis of the interaction data in a timely manner after the session communication is established; or, it can also be: the first intelligent program monitors whether the first device establishes session communication with other devices. If it is determined that the first device establishes session communication with other devices, the first intelligent program is actively started, so that the first intelligent device can analyze the content of the interaction data during the session communication. If it is determined that the first device does not establish session communication with other devices, the first intelligent program is not started and will not be called.

[0086] After the first intelligent program is called, the first intelligent program analyzes the content of the interaction data during the session communication to determine whether it meets the output conditions. When the output conditions are met, the first intelligent program controls the target application program to output the third data to the second device representing the communication identifier of the other party. That is, when the first intelligent program determines that the content of the interaction data meets the output conditions, the first intelligent program calls the target model so that the target model can generate the third data based on the content of the first data. After the target model generates the third data, the first intelligent program can control the target model to directly transmit the third data to the target application program, and output the third data to the second device representing the communication identifier of the other party through the target application program; or, after the target model generates the third data, the first intelligent program obtains the third data from the target model and outputs the third data to the second device representing the communication identifier of the other party through the target application program.

[0087] In the information processing method disclosed in this embodiment, as long as it is determined that the first device and the second device establish session communication through the target application program, the first device will call the first intelligent program, and the first intelligent program will analyze the content of the interaction data during the session communication. When it is determined that the content of the interaction data meets the output conditions, the third data generated by the target model based on the content of the first data is output to the second device. In this solution, when it is determined that session communication is established, the first intelligent program is called, and the first intelligent program monitors the interaction data in the session communication, so that when data needs to be output, the third data can be generated and output to ensure the smooth progress of the session communication, avoid information not being transmitted through the session communication, ensure communication efficiency, and improve the user experience.

[0088] Furthermore, in the information processing method disclosed in this embodiment, determining that the content of the interaction data meets the output conditions may include at least one of the following:

[0089] If the first data includes the first keyword, it indicates that the content of the interaction data meets the output conditions;

[0090] If the second data includes a second keyword, it indicates that the content of the interaction data meets the output condition;

[0091] If the second data does not include a third keyword for the first keyword in the first data, it indicates that the content of the interaction data meets the output condition.

[0092] After determining that the first device and the second device establish session communication, analyze the content of the interaction data. As long as it is determined that the content of the interaction data meets any one of the above, it can be determined that the content of the interaction data meets the output condition. At this time, the third data is output to the second device so that the second device can obtain the third data to ensure that the user of the second device can obtain complete information.

[0093] Among them, if it is determined that the output condition is met based on the first data in the interaction data, specifically, it can be determined whether the first data includes a first keyword. When it is determined that the first data includes a first keyword, it is determined that the output condition is met.

[0094] The first data is the data transmitted from the second device to the first device, that is, the data output by the user of the second device. When the user of the second device wants to obtain certain information, it will be expressed in the data transmitted to the first device. Therefore, if the first data transmitted from the second device to the first device includes a first keyword, it can be determined that the output condition is met. At this time, the third data needs to be transmitted to the second device so that the user of the second device can obtain the corresponding information.

[0095] Multiple first keywords can be pre-stored. When analyzing the interaction data, if it is determined that a certain first keyword exists in the first data in the interaction data, it is determined that the output condition is met; or, the first keyword is not stored, but when analyzing the interaction data, based on the semantics of the second data in the interaction data, it is determined that certain information needs to be queried and output at present. Then, it can be determined that the output condition is met.

[0096] For example: User 1 uses the first device, User 2 uses the second device, and User 1 and User 2 have a voice call. At this time, session communication is established between the first device and the second device. If User 2 says "Do you have the phone number of someone" through the second device, this sentence is the first data. At this time, the system or the first intelligent program corresponding to the information processing method disclosed in this embodiment determines that the first data includes the keyword "phone number", which is a pre-stored keyword, and determines that the output condition is met. Or, the system or the first intelligent program analyzes the first data, determines that the phone number of someone needs to be queried at present, then determines "the phone number of someone" as the first keyword and determines that the current output condition is met.

[0097] For another example: User 2 says "Tell me your express delivery number" through the second device, and this sentence is the first data. At this time, the system or the first intelligent program determines that the first data summary includes the keyword "express delivery number", and this keyword is a keyword pre-stored in the device, then it is determined that the output condition is met. Or, the system or the first intelligent program analyzes the first data and determines that a query for an express delivery number is currently required, then determines "express delivery number" as the first keyword and determines that the current output condition is met.

[0098] In addition, when the first keyword is included in the first data, it is determined that the output condition is met. At this time, the third data needs to be output, and the third data is determined based on the first data. At this time, the semantics of the first data can be analyzed, or the data before the first data in the current session communication can be semantically analyzed to determine how the third data is determined. Specifically, based on the result of semantic analysis, it can be determined to query the third data from a specific application program, or query the third data from a specific location of the first device, or query the data related to the semantic analysis result from the network side as the third data, etc.

[0099] It should be noted that when the first keyword appears in the first data disclosed in this embodiment, it is determined that the output condition is met. It is necessary to ensure that when it is determined that the first keyword appears in the first data, the third data is output in the same round of conversation. The same round of conversation is in the form of question and answer, that is, the second device outputs the first data, and in the same round of conversation, the first device responds to the first data and outputs the third data to ensure the timeliness of the output third data and avoid the situation where the user of the second device is not sure what the third data corresponds to after a long time interval when the first device outputs the third data.

[0100] In addition, if it is determined that the output condition is met based on the second data in the interaction data, specifically, if the second keyword is included in the second data, and when it is determined that the second keyword is included in the second data, it is determined that the current output condition is met.

[0101] The second data is obtained based on the input component of the first device. That is, the user of the first device outputs the second data so as to transmit it to the second device, enabling the user of the second device to obtain the second data. The information processing method disclosed in this embodiment is applied to the first device. When the user of the first device outputs the second data, the input component of the first device can obtain the second data. If the second data is for the user of the second device to obtain certain information, the second data needs to include a second keyword at this time. The second keyword represents the information that the user of the second device needs to obtain. After the first device obtains the second data, it analyzes the second data. If it determines that the second data includes the second keyword, it can determine that currently the user of the second device needs to obtain certain information. Therefore, it can be determined that the current output condition is met. After transmitting the second data to the second device, the third data also needs to be transmitted to the second device. The third data is the information that the user of the second device needs to obtain.

[0102] At this time, multiple second keywords can be pre-stored. When analyzing the interaction data, if it is determined that there is a certain second keyword in the second data of the interaction data, it is determined that the output condition is met; or, instead of storing the second keyword, when analyzing the interaction data, based on the semantics of the second data in the interaction data, it is determined that currently certain information needs to be queried and output. At this time, it can be determined that the output condition is met.

[0103] For example: User 1 uses the first device and User 2 uses the second device. User 1 and User 2 have a voice call. At this time, a session communication is established between the first device and the second device. If User 1 says "Help provide the express delivery number", this sentence is the second data. At this time, the system or the first intelligent program determines that the second data includes the keyword "express delivery number", which is a pre-stored keyword, and determines that the output condition is met. Or, the system or the first intelligent program analyzes the second data, determines that currently the express delivery number needs to be queried, then determines "express delivery number" as the second keyword, and determines that the current output condition is met.

[0104] Another example: User 1 uses the first device and User 2 uses the second device. User 1 and User 2 have a voice call. At this time, a session communication is established between the first device and the second device. If User 1 says "Wait a moment, I'll look for it", this sentence is the second data. At this time, the system or the first intelligent program determines that the second data includes the keyword "I'll look for it", which is a pre-stored keyword, and determines that the output condition is met. Or, the system or the first intelligent program analyzes the second data, determines that currently the express delivery number needs to be queried, then determines "I'll look for it" as the second keyword, and determines that the current output condition is met.

[0105] In addition, when the second keyword is included in the second data, it is determined that the output condition is met. At this time, the third data needs to be output, and the third data is determined based on the first data. The first data is the data transmitted from the second device to the first device before the second data including the second keyword. At this time, the semantics of the first data can be analyzed, or the semantics of multiple first data before the second data in the current session communication can be analyzed to determine how the third data is determined. Specifically, based on the result of the semantic analysis, it can be determined to query the third data from a specific application, or query the third data from a specific location of the first device, or query the data related to the semantic analysis result from the network side as the third data, etc.

[0106] In this embodiment, if the second keyword appears in the second data, it is determined that the output condition is met. At this time, it is necessary to ensure that when it is determined that the second keyword appears in the second data, the third data is output in the same round of conversation. The same round of conversation is in the form of a question-and-answer, that is, the user of the first device outputs the second data. While the first device transmits the second data to the second device, the first device determines that the current output condition is met and, in response to the second data, outputs the third data. That is, after the first device outputs the second data, in the same round of conversation, the first device outputs the third data to ensure the timeliness of the output third data.

[0107] Further, when it is determined that the data condition is met based on the second data in the interaction data, it can also be: determining whether the second data includes a third keyword for the first keyword in the first data. If the second data does not include a third keyword for the first keyword in the first data, it is determined that the output condition is met.

[0108] During the session communication between the first device and the second device, if the first keyword appears in the first data in the interaction data of a certain round of conversation, it indicates that the user of the second device needs the user of the first device or the first device to provide some information. However, in the subsequent multiple rounds of conversation, that is, in the second data in the interaction data of multiple rounds of interaction, no third keyword for the first keyword in the first data appears, which means that in the subsequent multiple rounds of conversation, the user of the first device has not responded to the first data including the first keyword. At this time, in order to ensure that the user of the second device can obtain the information they need in a timely manner, the system or intelligent program can provide the relevant information, that is, generate the third data through the target model and output the third data to the second device. Therefore, when it is determined that the second data does not include a third keyword for the first keyword in the first data, it is determined that the current output condition is met.

[0109] In this embodiment, the system or intelligent program analyzes the interaction data during the session communication process, but does not actively output data. That is, when it is determined that the first keyword appears in the first data, the system or intelligent program does not directly output the third data for responding to the first data. Instead, it waits for the user of the first device to determine whether the user of the first device outputs the second data in response to the first data. If the user of the first device outputs the second data in response to the first data, there is no need for the system or intelligent program to output the third data. If it is determined that the user of the first device never outputs the second data in response to the first data, that is, the second data does not include the third keyword for the first keyword in the first data, at this time, the system or intelligent program will output the third data to respond to the first data, ensuring that the user of the second device can receive relevant information in a timely manner.

[0110] For example: User 1 uses the first device, and User 2 uses the second device. User 1 and User 2 conduct session communication through text messages. As Figure 3 shown, it is a schematic diagram of the communication interface on the first device when User 1 and User 2 conduct session communication through text messages. The text content on the left side of the communication interface is multiple first data transmitted by User 2 to the first device through the second device, and the text content on the right side of the communication interface is multiple second data output by User 1 obtained by the input component of the first device. The multiple second data are used to be transmitted to the second device. Among them, a certain first data output by User 2, such as: the first data 1 is "Help me check the phone number of Little A", and then User 2 continues to output other first data, such as: the first data 2 is "Have you been in touch with Little A recently", resulting in User 1 only responding to the first data 2 and not responding to the first data 1. Or, after User 1 obtains the first data 1, does not respond to it, but outputs other second data, such as: the second data 1 is "Little A has been very busy recently", etc., resulting in User 2 not receiving the phone number of Little A provided by User 1 in response to the first data 1. At this time, the system or intelligent program monitors this situation, and the system or intelligent program queries the phone number of Little A from the first device based on the first data 1 and generates the third data, and outputs the third data to the second device, such as: the third data is "The phone number of Little A is XXXX", to ensure that User 2 can timely learn the phone number of Little A in the case that User 1 does not respond to the first data 1 in a timely manner.

[0111] In this embodiment, since it is necessary to determine that the third keyword for the first keyword in the first data does not appear in the second data in the interaction data of multiple rounds of interaction, it is characterized that the current output condition is met. Then, the multiple rounds of interaction can be multiple rounds of interaction included in a topic, and the topic is the topic including the interaction where the first data is located, and the first data is the first data including the first keyword.

[0112] Specifically, if the second data does not include a third keyword for the first keyword of the first data, and the interaction data indicates the end of a topic, it is characterized that the current output condition is satisfied.

[0113] During the session communication between the first device and the second device, there may be multiple rounds of interaction. Different interactions may correspond to the same topic or different topics. A topic may include multiple rounds of interaction or only one round of interaction. Whether a topic ends or a new topic starts can be determined through the interaction data.

[0114] If it is determined that the first data includes the first keyword, and the second data in multiple rounds of interaction does not include the third keyword for the first keyword of the first data, that is, in multiple rounds of interaction, the user corresponding to the first device does not respond to the first data including the first keyword. At this time, continue to analyze the interaction data. If it is determined based on the interaction data that the topic corresponding to the first data including the first keyword has ended, it is characterized that the user of the first device and the user of the second device are about to start the next topic, or have already started the next topic. At this time, it can be determined that the current output condition is satisfied, that is, the system or intelligent program can respond to the first data including the first keyword.

[0115] To ensure that there is no omission of information in the ended topic, it is necessary to respond to the first data including the first keyword that the user of the first device did not respond to. At this time, the target model can generate a response to the first data including the first keyword, that is, generate the third data, and output the third data to the second device so that the user of the second device can know the response to the first data including the first keyword.

[0116] For example, the first data including the first keyword is "Help me query the express number of Xiaob". After multiple rounds of interaction, there is no response to this first data. After the topic corresponding to this multiple rounds of interaction ends, the third data for this first data can be generated and output to the second device, such as: "The express number of Xiaob you mentioned just now is XXXXX", or: "I am the intelligent assistant Xiaotian. Let me add that the express number of Xiaob you mentioned just now is XXXXX". That is, the supplementary third data can indicate that the current output third data is generated and output by the system or intelligent program, or it may not indicate that it is generated and output by the system or intelligent program.

[0117] This embodiment discloses an information processing method, and its flowchart is as Figure 4 shown, including:

[0118] Step S41: Obtain interaction data based on the session communication with the second device. The interaction data includes first data transmitted from the second device to the first device and second data obtained based on the input component of the first device.

[0119] Step S42: Analyze the content of the interaction data.

[0120] Step S43: In response to the content of the interaction data meeting the output condition, output third data to the second device through session communication. The third data is data generated by the target model based on the first data including the first keyword. Wherein, the content of the interaction data meeting the output condition includes at least one of the following: the first data includes the first keyword; the second data includes the second keyword; the second data does not include the third keyword for the first keyword in the first data.

[0121] During the session communication between the first device and the second device, the system or intelligent program analyzes the interaction data in this session communication process to determine whether the output condition is met, and when the output condition is met, generates and outputs the third data.

[0122] Among them, the generation of the third data is implemented by the target model, that is, when it is necessary to transmit third data other than the second data to be output by the user of the first device to the second device, the generation of the third data needs to be implemented by the target model.

[0123] The third data transmitted from the first device to the second device is usually to transmit the information that the user of the second device wants to know to the second device. The information that the user of the second device wants to know is determined by the first data transmitted from the second device to the first device. If the first data includes the first keyword, it can be determined that the user of the second device wants to know information related to the first keyword. Therefore, when the system or intelligent program determines that the current output condition is met, it transmits the first data including the first keyword to the target model. The target model queries relevant information based on the first data including the first keyword to generate the third data. After generating the third data, the system or intelligent program transmits the third data to the second device so that the user of the second device can obtain the information related to the first keyword, that is, the third data.

[0124] The target model can query based on the input first data and the first keyword in the first data, and use the queried information as the third data. Or, after the target model queries based on the first data and the first keyword and obtains the queried information, it can analyze and organize the queried information to obtain the third data.

[0125] Further, in this embodiment, after the first data and the first keyword in the first data are input into the target model, the target model can perform semantic analysis on the first data to obtain a semantic analysis result, and jointly determine what information needs to be queried by combining the first keyword with the semantic analysis result, so as to query relevant information;

[0126] Alternatively, when the first data and the first keyword in the first data are input into the target model, the interaction data before the first data including the first keyword can also be sent to the target model, so that the target model can accurately analyze what information needs to be queried currently, thereby ensuring the accuracy of the generated third data.

[0127] It should be noted that, in order to protect user privacy, in this embodiment, both the first device and the second device are authenticated devices. Then, in the session communication between the first device and the second device, the target model can query various information from the first device, and can also transmit the third data queried and generated by the target model to the second device, reducing the risk of information leakage in the first device.

[0128] In addition, during the session communication between the first device and the second device, analyze the content of the interaction data. If it is determined that the output condition is met, the target model needs to generate and output the third data based on the first data including the first keyword. Then, when it is determined that the output condition is met, it is necessary to determine the first data including the first keyword to determine whether the first data including the first keyword involves privacy issues. If it involves privacy issues, it will not respond to the satisfaction of the output condition, that is, even if the output condition is met, it will not control the target model to query and generate the third data based on the first data, nor will it transmit the third data to the second device, thereby effectively avoiding the risk of information leakage in the first device.

[0129] In the information processing method disclosed in this embodiment, the first device obtains interaction data based on the session communication with the second device. The interaction data includes the first data transmitted from the second device to the first device, and the second data obtained based on the input component of the first device; analyze the content of the interaction data to determine whether it meets the output condition, and when it is determined that the output condition is met, output the third data to the second device through the session communication. The third data is the data generated by the target model based on the first data including the first keyword. Among them, the content of the interaction data meeting the output condition includes at least one of the following: the first data includes the first keyword; the second data includes the second keyword; the second data does not include the third keyword for the first keyword in the first data. In this solution, when it is determined that the first data includes the first keyword, when the target model generates the third data, it needs to be generated based on the first data including the first keyword to ensure the accuracy of the third data generated by the target model.

[0130] Further, the information processing method disclosed in this embodiment may further include:

[0131] When outputting third data to a second device, if there is second data that belongs to the same round of session as the first data, the second data may or may not be transmitted to the second device based on session communication.

[0132] In the session communication between the first device and the second device, interaction data is obtained, the content of the interaction data is analyzed, if it is determined that the output condition is met, third data needs to be determined and output to the second device. If the third data is generated based on the first data including the first keyword, then the third data can be output as the same round of conversation as the first data including the first keyword. That is, in the Nth round of interaction data, the first data transmitted from the second device to the first device includes the first keyword. If the output condition is met at this time, the generated third data is also output in the Nth round of interaction data, so that the user of the second device can learn the third data in the Nth round of interaction. That is, as long as the first data including the first keyword transmitted by the second device is obtained, the first device directly feeds back the third data when feeding back, so as to ensure that the first data including the first keyword and the third data are in the same round of interaction.

[0133] In addition, since the third data is generated by the target model based on the content of the first data, it is only generated and output in response to the first data transmitted by the second device. However, the first data is transmitted from the second device to the first device, and the user of the first device can learn the first data. Then, when the user of the first device learns the first data, the user may have other data to transmit to the second device so that the user of the second device can receive the information that the user of the first device wants to transmit. The information that the user of the first device wants to transmit is determined as the second data. If the second data is the same as the third data, then when outputting the third data to the second device, there is no need to repeat outputting the second data; if the second data is different from the third data, while ensuring that the third data and the first data including the first keyword are in the same round of interaction, when outputting the third data, since the third data is used to respond to the first data, the second data that is not used to respond to the first data may no longer be output.

[0134] For example, the first data is "Do you know the express delivery number", the target model generates the third data based on this first data, and the third data is "The express delivery number is XXXXX". When the user of the first device receives the first data, they input the second data through the input component of the first device, and the second data is "What did I buy with this express delivery". In this case, the third data is generated in response to the first data, while the second data is not generated in response to the first data. To enable the user of the second device to timely obtain the information they want to know, the third data can be directly output, and the second data may not be transmitted to the second device. That is, the input component of the first device obtains the second data, but does not transmit it to the second device.

[0135] Alternatively, in the above example, after obtaining the first data, the target model can quickly generate the third data. During the process of generating and outputting the third data, the user of the first device has not yet found the express delivery number they want to know in the first data. At this time, since the third data has been output, the user of the first device will not output the second data anymore, and the third data is directly output by the system or intelligent program to respond to the first data.

[0136] Furthermore, after the user of the first device hears the other party say "Do you know the express delivery number", if they don't know and need to check, they may say "Ah... I don't know. Wait a moment, I'll check". Based on the target model, the third data is generated in this embodiment. At this time, instead of sending the answer "Ah... I don't know. Wait a moment, I'll check" to the user of the second device, the third data generated based on the target model can be directly used to replace the answer of the user of the first device.

[0137] In addition, during the session communication process between the first device and the second device, if the first data transmitted from the second device to the first device is obtained and the output condition is met, the target model generates the third data based on the first data and outputs the third data to the second device. When the user of the first device learns the first data, they may have other data they want to transmit to the second device so that the user of the second device can receive the information the user of the first device wants to transmit, that is, the second data. When the first device outputs the third data to the second device, the first device also obtains the second data input by the user of the first device through the input component of the first device, and the first device also outputs the second data to the second device, so that the second device can not only receive the third data for responding to the first data, but also receive the second data output by the user of the first device.

[0138] Continuing with the above example for illustration, for example: if the first data is "Do you know the express delivery number", the third data is "The express delivery number is XXXXX", and the second data is "What did you buy with this express delivery", then the first device outputs the third data and the second data to the second device, so that the user of the second device can, while learning the express delivery number it wants to know, also learn the question of the user of the first device.

[0139] This embodiment discloses an information processing method, and its flowchart is as Figure 5 shown, including:

[0140] Step S51: Based on the session communication with the second device, call the first intelligent program, where the session communication with the second device is to establish session communication based on the communication identifier of the session party of the target application program;

[0141] Step S52: Obtain interaction data through the first intelligent program. The interaction data is the data of the session party during the session communication, including: the first data transmitted from the second device to the first device, and the second data obtained based on the input component of the first device;

[0142] Step S53: Analyze the semantics of the content of the interaction data through the first intelligent program. If it is determined that the semantics of the content of the interaction data meet the authorization condition, call the second intelligent program, where the second intelligent program responds to each first data in the session communication with the second device;

[0143] Step S54: Call the target model through the second intelligent program to generate the third data for the current first data;

[0144] Step S55: Transmit the third data to the second device through the session communication for the current first data. The first intelligent program and the second intelligent program are different.

[0145] The first device conducts session communication with the second device. During the session communication process, there will be interaction data, that is, the first data transmitted from the second device to the first device, and the second data obtained based on the input component of the first device and needing to be transmitted to the second device. And when the output condition is met, the third data can also be generated by the target model and transmitted to the second device.

[0146] When it is determined that there is session communication between the first device and the second device, the intelligent program can be called, and the intelligent program performs the subsequent operation of whether to generate and output the third data. More specifically, in this embodiment, it can at least include the first intelligent program and the second intelligent program. The first intelligent program and the second intelligent program have different permissions and are used to perform different operations to ensure that the information processing method disclosed in this embodiment can be completed smoothly, quickly, and accurately during the execution process.

[0147] Specifically, when it is determined that there is session communication between the first device and the second device, the first intelligent program can be called first. The first intelligent program acquires and analyzes the interaction data during the session communication. When the first intelligent program determines that the content of the interaction data meets the output condition, it outputs the third data generated based on the target model to the second device, so that the second device can obtain the third data in response to the first data in a timely manner without manual query by the user, simplifying the operation process.

[0148] In addition, when the first intelligent program determines that the semantics of the content of the interaction data meet the authorization condition, it calls the second intelligent program.

[0149] Among them, meeting the authorization condition can be: the first data in the interaction data includes the fourth keyword, or the second data in the interaction data includes the fifth keyword.

[0150] For example, if the first data is "Help me analyze it with your AI assistant", since the first data is transmitted from the second device to the first device, after the first intelligent program of the first device obtains the first data and analyzes it, it can directly call the second intelligent program in the first device based on the first data, that is, the AI assistant.

[0151] Another example: if the second data is "Chat with my AI assistant", since the second data is input by the user of the first device obtained by the input device of the first device, after the first intelligent program of the first device obtains the second data and analyzes it, it can directly call the second intelligent program in the first device based on the second data, that is, the AI assistant, so that the second intelligent program can respond to each first data in the session communication.

[0152] Therefore, the first intelligent program can be called when there is session communication between the first device and other devices. After being called, it can analyze the interaction data in the session communication and output the third data to the second device when the output condition is met. After being called, the second intelligent program can respond to each first data transmitted by the second device in the session communication. That is, after the second intelligent program is called, the question-and-answer permission of the second intelligent program is higher than that of the first intelligent program which can only output data when the output condition is met, and the range it can query or retrieve is also larger than that of the first intelligent program.

[0153] After the second intelligent program is called, it can respond to each first data in the session communication. That is, as long as the second intelligent program is called, in the session communication between the first device and the second device, after the first device obtains the first data transmitted by the second device, the first device no longer outputs the second data to the second device, but only outputs the third data generated by the target model through the second intelligent program. At the same time, the first intelligent program also stops working, and the second intelligent program executes to obtain the interaction data, processes the interaction data, and outputs the third data and other processes.

[0154] After the second intelligent program is called, the second intelligent program transmits each obtained first data to the target model. The target model analyzes the first data, or analyzes the first data and the interaction data before the first data to generate the third data. Then, the second intelligent program transmits the third data to the second device through the current session communication; when the first data transmitted by the second device is obtained again, the second intelligent program continues to execute the above process to generate the third data and transmit the third data to the second device.

[0155] In addition, the first intelligent program is different from the second intelligent program. Specifically, the first intelligent program and the second intelligent program are different intelligent programs, or it can also be that the first intelligent program and the second intelligent program are the same intelligent program, but in different orange modes, so that the scope of question-and-answer permissions is different and the data retrieval scope is also different. Different intelligent programs are called in different scenarios.

[0156] In the information processing method disclosed in this embodiment, the first device and the second device perform session communication, call the first intelligent program, and the first intelligent program obtains and analyzes the interaction data in the session communication process. When the first intelligent program determines that the interaction data meets the authorization condition, it calls the second intelligent program. Then, the second intelligent program makes a corresponding reply to implement different intelligent programs in different scenarios and ensure the working efficiency of the intelligent program.

[0157] Furthermore, in the information processing method disclosed in this embodiment, it may further include:

[0158] Output the third data on the first device.

[0159] Since the third data is generated by the target model based on the content of the first data, when transmitting the third data to the second device, it is also necessary to output the third data on the first device, so as to ensure that when the third data in response to the first data is output to the second device for the user of the second device to receive, the user of the first device can also know the content of the third data transmitted from the first device to the second device, so as to ensure that when the third data needs to be supplemented or adjusted, the user of the first device can output supplementary information to the second device in a timely manner, so that the information obtained by the second device is complete and accurate information, so as to ensure the accuracy of the information output to the second device.

[0160] Further, when the first device outputs the third data, if feedback information from the user of the first device is obtained, the feedback information is analyzed. If it is determined that the feedback information indicates that the user of the first device did not hear clearly the content of the third data output by the first device, the first device can adjust the output mode of the third data output by the first device based on the feedback information. For example, the first device can change the output mode of the third data from outputting it in audio form to outputting it in text content, so as to avoid the situation where the user of the first device cannot hear clearly the audio of the third data due to problems such as a noisy environment; or, if the first device outputs the third data in audio form and outputs the third data through a receiver, the output mode of the third data output by the first device can be changed to: output the third data through the speaker of the first device; or, the volume when the first device outputs the third data can be increased; or, the first device can repeat outputting the third data in audio form, etc.

[0161] Or, when the first device outputs the third data, if feedback information from the user of the first device is obtained, the feedback information is analyzed. If it is determined that the feedback information indicates that the user of the first device cannot see clearly the content of the third data output by the first device, the first device can adjust the output mode of the third data output by the first device based on the feedback information. For example, the first device can change the output mode of the third data from outputting it in text form to outputting it in audio form, so as to avoid the situation where the user of the first device cannot see clearly the audio of the third data due to problems such as blocked vision, that is, the third data displayed in text form on the first device is broadcast through an automatic voice broadcast.

[0162] The first device outputs the third data. In addition, the first device also outputs the first data. When the first device outputs the third data and / or the first data, the data output mode of its output of the third data and / or the first data can be adjusted.

[0163] Specifically, obtain the target sensing parameter, and adjust the output manner of the third data and / or the first data of the first device based on the target sensing parameter; or determine the posture of the first device, and adjust the output manner of the third data and / or the first data of the first device based on the posture of the first device.

[0164] For the third data, when output locally on the first device, it can be presented in text form so that the user of the first device can receive the accurate text content of the third data. Of course, it can also be output in audio form to ensure that the user of the first device can receive the information of the third data in a timely manner.

[0165] The target sensing parameter can be the distance parameter detected by the distance sensor on the first device, or the distance parameter obtained by analyzing the image information collected by the image acquisition sensor on the first device. When the distance parameter is lower than a certain threshold, it indicates that the distance between the first device and the user of the first device is relatively close. At this time, if the data is presented in text form, the font size in the text can be adjusted; if the data is presented in audio form, the volume of the audio output can be adjusted. If the distance parameter indicates that the distance between the first device and the user of the first device is relatively far, the volume when outputting the third data and / or the first data can be increased. If the distance parameter indicates that the distance between the first device and the user of the first device is relatively close, the volume when outputting the third data and / or the first data can be decreased; the audio output can also be adjusted to be output through the speaker or the receiver. If the distance parameter indicates that the target area (such as the ear) of the first device and the user of the first device is relatively close, the first device can be adjusted to output the third data and / or the first data through the receiver. If the distance parameter indicates that the target area (such as the ear) of the first device and the user of the first device is relatively far, the first device can be adjusted to output the third data and / or the first data through the speaker, so as to ensure the output effect when the third data and / or the first data is output locally on the first device and ensure that the user of the first device can clearly hear the data output by the first device.

[0166] This embodiment discloses an information processing device, and its structural schematic diagram is as Figure 6 shown, including:

[0167] The first module 61, the second module 62 and the third module 63.

[0168] Among them, the first module 61 is used to obtain interaction data based on the session communication with the second device. The interaction data includes the first data transmitted from the second device to the first device, and the second data obtained based on the input component of the first device;

[0169] The second module 62 is used to analyze the content of the interaction data;

[0170] The third module 63 is configured to output third data to the second device in response to the content of the interaction data satisfying the output condition;

[0171] wherein the third data is data generated by the target model based on the content of the first data.

[0172] Furthermore, the session communication with the second device is: establishing session communication based on the communication identifier of the session party of the target application, and the interaction data is the data of the session party during the session communication;

[0173] The information processing device disclosed in this embodiment may further include:

[0174] A fourth module, configured to call a first intelligent program based on the session communication with the second device;

[0175] The first intelligent program is configured to call the first module, the second module and the third module to execute obtaining the interaction data, analyzing the content of the interaction data, and in response to the content of the interaction data satisfying the output condition, outputting third data to the second device representing the communication identifier of the other party based on the target application; the first intelligent program is further configured to call the target model to generate the third data.

[0176] Furthermore, the content of the interaction data satisfying the output condition includes at least one of the following:

[0177] If the first data includes a first keyword, it indicates that the content of the interaction data satisfies the output condition; if the second data includes a second keyword, it indicates that the content of the interaction data satisfies the output condition; if the second data does not include a third keyword for the first keyword in the first data, it indicates that the content of the interaction data satisfies the output condition.

[0178] Furthermore:

[0179] The target model generates the third data based on the first data including the first keyword, and the third data is transmitted to the second device based on the session communication.

[0180] Furthermore, the information processing device disclosed in this embodiment may further include:

[0181] A fifth module, in the case of outputting the third data to the second device, if there is second data belonging to the same round of session as the first data, the fifth module is configured to transmit the second data to the second device based on the session communication or not transmit it to the second device.

[0182] Furthermore, if the second data does not include a third keyword for the first keyword in the first data, indicating that the content of the interaction data satisfies the output condition, includes:

[0183] If the third keyword for the first keyword in the first data is not included in the second data, and the interaction data indicates the end of a topic, it is characterized that the content of the interaction data meets the output condition.

[0184] Further, the second module is configured to:

[0185] The first intelligent program analyzes the semantics of the content of the interaction data. If it is determined that the semantics of the content of the interaction data meet the authorization condition, the second intelligent program is called; wherein, the second intelligent program responds to each first data in the session communication with the second device.

[0186] The third module is configured to:

[0187] The second intelligent program calls the target model for the current first data to generate the third data; transmits the third data to the second device through session communication for the current first data; wherein, the first intelligent program is different from the second intelligent program.

[0188] Further, the information processing device disclosed in this embodiment may further include:

[0189] The sixth module is used to output the third data on the first device.

[0190] The information processing device disclosed in this embodiment is implemented based on the information processing method disclosed in the above embodiment, and will not be elaborated here.

[0191] The information processing device disclosed in this embodiment obtains interaction data based on the session communication with the second device. The interaction data includes the first data transmitted from the second device to the first device and the second data obtained based on the input component of the first device; analyzes the content of the interaction data; and outputs the third data to the second device in response to the content of the interaction data meeting the output condition. The third data is the data generated by the target model based on the content of the first data. In this solution, when the first device and the second device perform session communication, the content of the interaction data in the session communication process can be analyzed, and when the conditions are met, the data generated by the target model based on the content of the first data is output, realizing the generation and output of the third data only based on the content of the interaction data, simplifying the operation process of outputting the third data in the session communication process, improving the efficiency of the session communication, and improving the user experience.

[0192] This embodiment discloses an electronic device, and its structural schematic diagram is as Figure 7 shown, including:

[0193] At least one communication component 71, at least one memory 72 and at least one processor 73.

[0194] Wherein, at least one communication component 71 is used to perform session communication with the second device;

[0195] The memory 72 stores at least computer instructions and a target model;

[0196] The processor 73 is configured to load computer instructions to implement: analyzing the content of the interaction data, and outputting third data to the second device in response to the content of the interaction data satisfying an output condition;

[0197] The processor is further configured to load the target model to generate third data based on the content of the first data.

[0198] The electronic device disclosed in this embodiment is implemented based on the information processing method disclosed in the above embodiment, and will not be elaborated here.

[0199] The electronic device disclosed in this embodiment obtains interaction data based on session communication with a second device. The interaction data includes first data transmitted from the second device to the first device and second data obtained based on an input component of the first device; analyzes the content of the interaction data; and outputs third data to the second device in response to the content of the interaction data satisfying an output condition. The third data is data generated by the target model based on the content of the first data. In this solution, during the session communication between the first device and the second device, the content of the interaction data in the session communication process can be analyzed, and when the condition is met, the data generated by the target model based on the content of the first data is output, realizing the generation and output of the third data only based on the content of the interaction data, simplifying the operation process of outputting the third data in the session communication process, improving the efficiency of the session communication, and improving the user experience.

[0200] In addition, it should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the drawings of the device embodiments provided in this application, the connection relationship between the modules indicates that they have a communication connection, which can be specifically implemented as one or more communication buses or signal lines.

[0201] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus necessary general hardware. Of course, it can also be implemented by dedicated hardware including application-specific integrated circuits, dedicated CPUs, dedicated memories, dedicated components, etc. Generally, functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structures for implementing the same function can also be diverse, such as analog circuits, digital circuits, or dedicated circuits. However, for the present application, software program implementation is a better embodiment in more cases. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a readable storage medium, such as a floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk, or optical disc of a computer, and includes several instructions for causing a computer device (which can be a personal computer, training device, or network device, etc.) to execute the methods described in various embodiments of the present application.

[0202] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product.

[0203] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a dedicated computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, training device, or data center to another website, computer, training device, or data center in a wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that a computer can store, or a data storage device such as a training device or data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)).

Claims

1. An information processing method, comprising: Obtaining interaction data based on session communication with a second device, where the interaction data includes first data transmitted from the second device to the first device and second data obtained based on an input component of the first device; Analyzing the content of the interaction data; Outputting third data to the second device in response to the content of the interaction data satisfying an output condition; wherein the third data is data generated by a target model based on the content of the first data.

2. The method according to claim 1, wherein the session communication with the second device is: establishing session communication based on a communication identifier of a session party of a target application, and the interaction data is data of the session party during the session communication; The method further comprises: Invoking a first intelligent program based on session communication with the second device; The first intelligent program is used to execute obtaining the interaction data, analyzing the content of the interaction data, and in response to the content of the interaction data satisfying the output condition, outputting the third data to the second device representing the communication identifier of the other party based on the target application; The first intelligent program is further used to invoke the target model to generate the third data.

3. The method according to claim 1 or 2, wherein the content of the interaction data satisfying the output condition includes at least one of the following: If the first data includes a first keyword, it indicates that the content of the interaction data satisfies the output condition; If the second data includes a second keyword, it indicates that the content of the interaction data satisfies the output condition; If the second data does not include a third keyword for the first keyword in the first data, it indicates that the content of the interaction data satisfies the output condition.

4. The method according to claim 3, further comprising: The target model generates third data based on the first data including the first keyword, and the third data is transmitted to the second device based on the session communication.

5. The method according to claim 4, when outputting the third data to the second device, the method further comprises: If there is second data belonging to the same round of session as the first data, the second data is transmitted to the second device or not transmitted to the second device based on the session communication.

6. The method according to claim 3, wherein the case that if the second data does not include a third keyword for the first keyword in the first data, it indicates that the content of the interaction data satisfies the output condition includes: If the second data does not include a third keyword for the first keyword in the first data and the interaction data expresses the end of a topic, it indicates that the content of the interaction data satisfies the output condition.

7. The method according to claim 2, wherein analyzing the content of the interaction data includes: The first intelligent program analyzes the semantics of the content of the interaction data, and if it is determined that the semantics of the content of the interaction data satisfies an authorization condition, it invokes a second intelligent program; wherein the second intelligent program responds to each first data in the session communication with the second device; Outputting third data to the second device in response to the content of the interaction data meeting the output condition includes: The second intelligent program calls a target model for the current first data to generate third data; Transmitting the third data to the second device through the session communication for the current first data; Wherein, the first intelligent program is different from the second intelligent program.

8. The method according to claim 1, the method further includes: Outputting the third data on the first device.

9. An information processing device, comprising: A first module, configured to obtain interaction data based on a session communication with a second device, the interaction data including first data transmitted from the second device to the first device and second data obtained based on an input component of the first device; A second module, configured to analyze the content of the interaction data; A third module, configured to output third data to the second device in response to the content of the interaction data meeting the output condition; Wherein, the third data is data generated by a target model based on the content of the first data.

10. An electronic device, comprising: At least one communication component, at least one memory, and at least one processor, wherein: The at least one communication component is used for session communication with the second device; The memory stores at least computer instructions and a target model; The processor is configured to load the computer instructions to implement: Analyzing the content of the interaction data and outputting third data to the second device in response to the content of the interaction data meeting the output condition; The processor is further configured to load the target model to implement generating third data based on the content of the first data.

Images