Information processing method, electronic device and information processing system

Abstract

The present application provides an information processing method, an electronic device and an information processing system, the method comprising: receiving first input information of a user in an intelligent dialogue system; determining a target robot based on the first input information; establishing interaction between the user and the target robot in the intelligent dialogue system; wherein the intelligent dialogue system can generate response information based on the input information to realize multiple rounds of interaction with the user, and the present application improves the accuracy of the intelligent dialogue system in solving problems for users.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and more particularly to an information processing method, electronic equipment and an information processing system. Background Art

[0002] Currently, task-based chatbots can be applied to intelligent dialogue systems to answer questions raised by users. Specifically, users can interact with randomly assigned robots for multiple rounds to solve their problems.

[0003] However, due to the limited problem-solving capabilities of robots, the accuracy of problem-solving by intelligent dialogue systems is low. Summary of the invention

[0004] In view of this, the present invention provides an information processing method, an electronic device and an information processing system to solve the above technical problems.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An information processing method, comprising:

[0007] Receiving first input information from a user in the intelligent dialogue system;

[0008] Determine a target robot based on the first input information;

[0009] An interaction between the user and the target robot is established in the intelligent dialogue system; wherein the intelligent dialogue system can generate response information based on input information to realize multiple rounds of interaction with the user.

[0010] Preferably, determining the target robot based on the first input information includes:

[0011] Sending the first input information to multiple robots;

[0012] receiving a plurality of first response information fed back by the plurality of robots, wherein the first response information carries a matching degree parameter in response to the first input information;

[0013] A robot whose matching degree parameter carried in the first response information meets a first preset condition is determined as a target robot.

[0014] Preferably, determining the target robot based on the first input information includes:

[0015] Sending the first input information to multiple robots;

[0016] Receiving a plurality of first response information fed back by the plurality of robots;

[0017] Matching the plurality of first response information with the preset dimensional features respectively to determine a matching degree parameter;

[0018] The robot whose matching parameter for sending the first response information meets the first preset condition is selected as the target robot.

[0019] Preferably, sending the first input information to a plurality of robots comprises:

[0020] determining a robot type based on the first input information;

[0021] The first input information is sent to a plurality of robots of the robot type.

[0022] Preferably, the target robot includes at least two target robots, and the method further includes:

[0023] Outputting first response information of the at least two target robots, where the first response information is information in response to the first input information;

[0024] Obtaining the second input information of the user;

[0025] determining a first target robot among the at least two target robots based on the second input information;

[0026] The interaction between the user and the first target robot is maintained, and the interaction between the user and other target robots except the first target robot is cancelled.

[0027] An electronic device, comprising:

[0028] A first interface, used to receive first input information from a user in the intelligent dialogue system;

[0029] A processor is used to determine a target robot based on the first input information, and establish interaction between the user and the target robot in the intelligent dialogue system; wherein the intelligent dialogue system can generate response information based on the input information to realize multiple rounds of interaction with the user.

[0030] Preferably, it also includes:

[0031] Second interface;

[0032] The processor determines a target robot based on the first input information, including:

[0033] Sending the first input information to multiple robots through the second interface;

[0034] receiving, through the second interface, a plurality of first response information fed back by the plurality of robots, wherein the first response information carries a matching degree parameter in response to the input information;

[0035] A robot whose matching degree parameter carried in the first response information meets a first preset condition is determined as a target robot.

[0036] Preferably, it also includes:

[0037] Second interface;

[0038] The processor determines a target robot based on the first input information, including:

[0039] Sending the first input information to multiple robots through the second interface;

[0040] Receiving a plurality of first response information fed back by the plurality of robots through the second interface;

[0041] Matching the plurality of first response information with the preset dimensional features respectively to determine a matching degree parameter;

[0042] The robot whose matching parameter for sending the first response information meets the first preset condition is selected as the target robot.

[0043] Preferably, the processor sends the first input information to a plurality of robots through the second interface, including:

[0044] determining a robot type based on the first input information;

[0045] The first input information is sent to a plurality of robots of the robot type through the second interface.

[0046] An information processing system, comprising:

[0047] Multiple robots;

[0048] An electronic device for communicating with the plurality of robots, the electronic device comprising:

[0049] A first interface, used to receive first input information from a user in the intelligent dialogue system;

[0050] A processor is used to determine a target robot based on the first input information, and establish interaction between the user and the target robot in the intelligent dialogue system; wherein the intelligent dialogue system can generate response information based on the input information to realize multiple rounds of interaction with the user.

[0051] It can be seen from the above technical solution that the present application provides an information processing method, which receives the first input information of the user in the intelligent dialogue system, determines the target robot based on the first input information, and establishes interaction between the user and the target robot in the intelligent dialogue system, wherein the intelligent dialogue system can generate response information based on the input information to realize multiple rounds of interaction with the user; it can be seen that the present application can match the target robot for interacting with the user based on the user's first input information, that is, the target robot is assigned to the user in a targeted manner, thereby improving the accuracy of the intelligent dialogue system in solving problems for the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0053] Figure 1 A flowchart of an information processing method provided for the first method embodiment of the present application;

[0054] Figure 2 A flowchart of an information processing method provided for the second method embodiment of the present application;

[0055] Figure 3 A flowchart of an information processing method provided for the third method embodiment of the present application;

[0056] Figure 4 A flowchart of an information processing method provided for the fourth method embodiment of the present application;

[0057] Figure 5 A schematic diagram of the structure of an electronic device provided for the first device embodiment of the present application;

[0058] Figure 6 A structural diagram of an information processing system provided for the sixth device embodiment of the present application. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] The first method embodiment of the present application provides an information processing method, such as Figure 1 As shown, the method may include the following steps:

[0061] Step 101: receiving first input information from a user in an intelligent dialogue system;

[0062] An information processing method provided by the present application can be executed by an electronic device, which can specifically be a server. The electronic device can be applied to an intelligent dialogue system, and the intelligent dialogue system can generate response information based on input information to achieve multiple rounds of interaction with the user. Specifically, the multiple rounds of interaction with the user can be completed by a target robot determined subsequently.

[0063] Step 102: determining a target robot based on the first input information;

[0064] The electronic device can communicate with multiple robots, thereby determining the target robot from the multiple robots based on the first input information. Specifically, the electronic device can provide an open interface to the multiple robots, thereby communicating with the multiple robots.

[0065] It should be noted that the robot in this application can be a task-based chat robot.

[0066] Step 103: Establishing interaction between the user and the target robot in the intelligent dialogue system.

[0067] Specifically, a direct interaction between the user and the target robot can be established, that is, the interaction between the user and the target robot can be performed without using an electronic device. Alternatively, an indirect interaction between the user and the target robot can be established, that is, the interaction between the user and the target robot is still performed through an electronic device.

[0068] When the user establishes interaction with the target robot, the user can have multiple rounds of interaction with the target robot in the intelligent dialogue system, that is, the target robot can generate response information based on the user's input information to achieve multiple rounds of interaction with the user. The multiple rounds of interaction can refer to the user inputting information once, the target robot feeding back information once, the user inputting information again, and the target robot feeding back information again. For example, the user's input information is: What should I do if my mobile phone is often turned off? The target robot generates response information based on the input information: What is the model of your mobile phone? The user inputs again based on the target robot's response information: The model of my mobile phone is xxxx. The target robot continues to generate response information based on the input information: What is the current battery level of your mobile phone? The user enters information again... The target robot generates response information again... The problem of frequent shutdown of the user's mobile phone is solved through multiple rounds of interaction.

[0069] It should be noted that the above-mentioned multiple rounds of interactions can be carried out in one conversation window, and communication can be carried out through text or voice.

[0070] In summary, in this embodiment, by receiving the first input information of the user in the intelligent dialogue system, the target robot is determined based on the first input information, and the interaction between the user and the target robot is established in the intelligent dialogue system, wherein the intelligent dialogue system can generate response information based on the input information to realize multiple rounds of interaction with the user; it can be seen that in the present application, the target robot for interacting with the user can be matched based on the user's first input information, that is, the target robot is assigned to the user in a targeted manner, thereby improving the accuracy of the intelligent dialogue system in solving problems for the user.

[0071] The second method embodiment of the present application provides an information processing method, which mainly describes an implementation method of determining a target robot based on first input information, such as Figure 2 As shown, the method comprises the following steps:

[0072] Step 201: receiving first input information from a user in an intelligent dialogue system;

[0073] Step 202: Sending the first input information to multiple robots;

[0074] The electronic device can communicate with multiple robots, thereby sending the first input information to the multiple robots. Specifically, the electronic device can provide an open interface, and the robot can register on the electronic device through the open interface, so that the electronic device can communicate with the registered multiple robots.

[0075] In this embodiment, optionally, in order to prevent the user's privacy information from being leaked, before sending the first input information to multiple robots, it can be detected whether the first input information contains sensitive information. If it is determined that it contains sensitive information, the first input information is desensitized, that is, the sensitive information in the first input information is replaced with general information corresponding to the sensitive information, and the desensitized first input information is sent to multiple robots.

[0076] Sensitive information may include various private information such as user personal information, device information used, etc. For example, if the first input information contains "Zhang San", since Zhang San is user personal information, "Zhang San" can be replaced with general information "XXX".

[0077] In this embodiment, optionally, in order to ensure that multiple robots can improve the recognition rate of the first input information after receiving the desensitized first input information, the electronic device can also mark the common information in the desensitized first input information as a sensitive information type and then send it to multiple robots.

[0078] For example, after replacing "Zhang San" with "XXX", the replacement name can be marked after XXX, and the specific form can be "XXX (for replacing name)". Of course, this is just a simple example, and the application does not limit the specific marking method.

[0079] Step 203: receiving a plurality of first response information fed back by the plurality of robots.

[0080] Specifically, after receiving the first input information, the robot will generate first response information matching the first input information, and determine the matching parameter of the first response information corresponding to the first input information. The matching parameter can be specifically represented as a matching degree, a matching grade, a matching score, etc.

[0081] Among them, the degree of matching can be represented by high, medium, and low, and the higher the degree, the higher the matching degree. The matching level can be represented by primary, secondary, and tertiary levels, and the higher the level, the higher the matching degree. The matching score can be represented by a number, such as 90 points, 80 points, etc., and the higher the score, the higher the matching degree.

[0082] To facilitate information identification, optionally, in this embodiment, the first input information sent to multiple robots may carry information such as conversation time and conversation turns, and the multiple first response information fed back by the multiple robots may also carry information such as response time and conversation turns.

[0083] Step 204: Determine that the robot whose matching degree parameter carried in the first response information meets the first preset condition is the target robot;

[0084] The first preset condition is used to filter out first response information with a high degree of matching from multiple first response information, so as to determine the robot sending the filtered first response information as the target robot. Specifically, in one embodiment, the robot whose matching degree parameter carried in the sent first response information meets the preset matching degree parameter can be determined as the target robot.

[0085] Taking the matching parameter as the matching degree as an example, the first response information carrying a high matching degree can be determined, so that the robot sending the information is determined as the target robot. Taking the matching degree parameter as the matching score as an example, the first response information carrying a matching score greater than a preset score can be determined, so that the robot sending the information is determined as the target robot. Taking the matching parameter as the matching level as an example, the first response information carrying a matching level greater than a preset level can be determined, so that the robot sending the determined first response information is determined as the target robot.

[0086] In another way, the matching parameters such as matching degree, matching score or matching level can be sorted from high to low, so as to filter out one or the first N first response information carrying the matching degree, matching score or matching level in the first place, and determine the robot sending the filtered first response information as the target robot.

[0087] It can be seen that the target robot determined in this application can be one or more.

[0088] Among them, steps 202-204 are specific implementations of steps for determining the target robot based on the first input information.

[0089] Step 205: Establishing interaction between the user and the target robot in the intelligent dialogue system.

[0090] Specifically, a direct interaction between the user and the target robot can be established, that is, the interaction between the user and the target robot can be performed without using an electronic device. Alternatively, an indirect interaction between the user and the target robot can be established, that is, the interaction between the user and the target robot is still performed through an electronic device.

[0091] When the user establishes interaction with the target robot, the user can have multiple rounds of interaction with the target robot in the intelligent dialogue system, that is, the target robot can generate response information based on the user's input information to achieve multiple rounds of interaction with the user.

[0092] The third method embodiment of the present application provides an information processing method, which mainly describes an implementation method of determining a target robot based on first input information, such as Figure 3 As shown, the method comprises the following steps:

[0093] Step 301: receiving first input information from a user in an intelligent dialogue system;

[0094] Step 302: Sending the first input information to multiple robots;

[0095] The electronic device can communicate with multiple robots, thereby sending the first input information to the multiple robots. Specifically, the electronic device can provide an open interface, and the robot can be registered on the electronic device, so that the electronic device can communicate with the multiple registered robots.

[0096] In this embodiment, optionally, in order to prevent the user's privacy information from being leaked, before sending the first input information to multiple robots, it can be detected whether the first input information contains sensitive information. If it is determined that it contains sensitive information, the first input information is desensitized, that is, the sensitive information in the first input information is replaced with general information corresponding to the sensitive information, and the desensitized first input information is sent to multiple robots.

[0097] Sensitive information may include various private information such as user personal information, device information used, etc. For example, if the first input information contains "Zhang San", since Zhang San is user personal information, "Zhang San" can be replaced with general information "XXX".

[0098] In this embodiment, optionally, in order to ensure that multiple robots can improve the recognition rate of the first input information after receiving the desensitized first input information, the electronic device can also mark the common information in the desensitized first input information as a sensitive information type and then send it to multiple robots.

[0099] For example, after replacing "Zhang San" with "XXX", the replacement name can be marked after XXX, and the specific form can be "XXX (for replacing name)". Of course, this is just a simple example, and the application does not limit the specific marking method.

[0100] Step 303: receiving a plurality of first response information fed back by the plurality of robots;

[0101] Specifically, after receiving the first input information, the robot generates first response information matching the first input information, and then sends the first response information to the electronic device.

[0102] Step 304: Match the plurality of first response information with preset dimensional features respectively to determine a matching degree parameter;

[0103] After receiving multiple first response information fed back by multiple robots, the electronic device can match the multiple first response information with preset dimensional features respectively to determine the matching degree parameters of each first response information.

[0104] In this embodiment, the preset dimensional features may include: one or more of: historical chat frequency, robot score, content richness, historical user satisfaction, etc.

[0105] The historical chat frequency can be represented by the number of chats the robot has had with users in the historical records. The robot score can be represented by the score given to the robot by historical users. The historical user satisfaction can be represented by the satisfaction of historical users with the robot.

[0106] The electronic device may perform weighted matching of each first response information with at least one dimensional feature, thereby determining a matching parameter, which may be specifically characterized as a matching degree, a matching grade, or a matching score.

[0107] Among them, the degree of matching can be represented by high, medium, and low, and the higher the degree, the higher the matching degree. The matching level can be represented by primary, secondary, and tertiary levels, and the higher the level, the higher the matching degree. The matching score can be represented by a number, such as 90 points, 80 points, etc., and the higher the score, the higher the matching degree.

[0108] To facilitate information recognition by electronic devices, optionally, in this embodiment, the first input information sent to multiple robots may carry information such as conversation time and conversation turns, and the multiple first response information fed back by the multiple robots may also carry information such as response time and conversation turns.

[0109] Step 305: selecting a robot that sends the first response information and whose matching parameter satisfies a first preset condition as a target robot;

[0110] The first preset condition is used to filter out first response information with a high degree of matching from multiple first response information, so as to determine the robot sending the filtered first response information as the target robot. Specifically, in one embodiment, the robot whose matching degree parameter carried in the sent first response information meets the preset matching degree parameter can be determined as the target robot.

[0111] Taking the matching parameter as the matching degree as an example, the first response information carrying a high matching degree can be determined, so that the robot sending the information is determined as the target robot. Taking the matching degree parameter as the matching score as an example, the first response information carrying a matching score greater than a preset score can be determined, so that the robot sending the information is determined as the target robot. Taking the matching parameter as the matching level as an example, the first response information carrying a matching level greater than a preset level can be determined, so that the robot sending the determined first response information is determined as the target robot.

[0112] In another way, the matching parameters such as matching degree, matching score or matching level can be sorted from high to low, and the first one or the first N first response information carrying the matching degree, matching score or matching level at the first place can be screened out, so that the robot sending the screened first response information can be determined as the target robot.

[0113] That is to say, the target robot determined in this application can be one or more.

[0114] Among them, step 302 to step 305 are specific implementations of steps for determining the target robot based on the first input information.

[0115] Step 306: Establishing interaction between the user and the target robot in the intelligent dialogue system.

[0116] Specifically, a direct interaction between the user and the target robot can be established, that is, the interaction between the user and the target robot can be performed without using an electronic device. Alternatively, an indirect interaction between the user and the target robot can be established, that is, the interaction between the user and the target robot is still performed through an electronic device.

[0117] When the user establishes interaction with the target robot, the user can perform multiple rounds of interaction with the target robot, that is, the target robot can generate response information based on the user's input information to achieve multiple rounds of interaction with the user.

[0118] Optionally, in the second method embodiment and the third method embodiment, sending the first input information to multiple robots may include the following steps:

[0119] (1) determining the robot type based on the first input information;

[0120] In the present application, the robot types of the multiple robots communicating with the electronic device are various. Among them, the robot type can be characterized by one or more of the robot's image features, the robot's speaking style, the robot's expertise, the robot's language, etc. The first input information can be used to determine which type of robot is suitable for the user of the first input information. Specifically, the robot type can be determined by the expression form of the first input information, the content of the first input information, and the language of the first input information.

[0121] The image features of the robot are used to characterize the image of the robot, and may include various image features such as cartoon, girl, boy, etc. The robot's expertise refers to the field in which the robot is suitable for answering questions, such as electronic equipment, life, etc. The robot's speaking style refers to the form of expression of the response information generated by the robot. The language used by the robot refers to the input information language that the robot can understand or the language of the generated response information.

[0122] For example, if the first input information is information about a mobile phone problem, then a robot that is good at the field of electronic devices can be determined.

[0123] (2) Sending the first input information to a plurality of robots of the robot type.

[0124] Once the robot type is determined, targeted sending can be carried out, that is, the first input information is sent to multiple robots of the robot type, thereby receiving the first response information fed back by this type of robot, and then determining the target robot, which can increase user favorability and improve communication efficiency.

[0125] In the present application, the target robot may include one or more. When there is one target robot, an interaction between the user and the target robot may be established. If the interaction is a direct interaction between the user and the target robot, the target robot may directly output the first response information in the intelligent dialogue system. If the interaction is an indirect interaction between the user and the target robot, the electronic device may output the first response information in the intelligent dialogue system.

[0126] When the target robots include at least two, the fourth method embodiment of the present application further provides an information processing method, such as Figure 4 As shown, the following steps may be included:

[0127] Step 401: receiving first input information from a user in an intelligent dialogue system;

[0128] Step 402: determining a target robot based on the first input information;

[0129] In this embodiment, the number of target robots is greater than or equal to 2.

[0130] Step 403: establishing interaction between the user and the target robot in the intelligent dialogue system;

[0131] In this case, indirect interaction between the user and at least two target robots can be established through the electronic device.

[0132] Step 404: outputting first response information of the at least two target robots;

[0133] The first response information is information for responding to the first input information; the electronic device outputs the first response information fed back by all the determined target robots.

[0134] Step 405: Obtain second input information from the user;

[0135] Step 406: determining a first target robot among the at least two target robots based on the second input information;

[0136] After seeing the first response information, the user will generally input the second input information into the intelligent dialogue system, so the first target robot that is most relevant to the second input information can be determined.

[0137] It should be noted that since the first response information of multiple target robots is different, it is possible to determine that the target robot sending the corresponding first response information is the first target robot by judging which first response information the user's second input information is feedback about, or determining which first response information the user's second input information is most correlated with.

[0138] Step 407: Maintain the interaction between the user and the first target robot, and cancel the interaction between the user and other target robots except the first target robot.

[0139] Specifically, the electronic device may continue to maintain the distance interaction between the user and the first target robot, or the electronic device may switch the distance interaction between the user and the first target robot to a direct interaction between the user and the first target robot.

[0140] In this embodiment, when there are multiple target robots determined, the final first target robot can be determined based on the user's second input information, thereby maintaining the interaction between the user and the first target robot, and canceling the interaction between the user and other target robots except the first target robot. The present application can automatically determine the first target robot that meets the user's requirements, and further improve the accuracy of the intelligent dialogue system in solving problems for users.

[0141] In an information processing method provided in the present application, after establishing an interaction between a user and a target robot, or establishing an interaction between a user and a first target robot, optionally, it may also include: adjusting the target robot based on the user's input information to adjust it to a target robot that better meets the user's current needs. Specifically, the adjustment method may be similar to the method of determining the target robot in the previous text. It should be noted that the electronic device can shield the user's perception of the adjustment of the target robot, or it can also notify the user that the adjustment of the target robot has been made.

[0142] Corresponding to the above-mentioned information processing method, the device embodiment of the present application also provides an electronic device, which is described below through several device embodiments.

[0143] The first device embodiment of the present application provides an electronic device, such as Figure 5 As shown, the electronic device 100 may include: a first interface 110 and a processor 120. Among them:

[0144] The first interface 110 is used to receive first input information from a user in the intelligent dialogue system;

[0145] The intelligent dialogue system can generate response information based on input information to achieve multiple rounds of interaction with the user. Specifically, the multiple rounds of interaction with the user can be completed by a target robot determined subsequently.

[0146] The processor 120 is used to determine the target robot based on the first input information, and establish interaction between the user and the target robot in the intelligent dialogue system; wherein the intelligent dialogue system can generate response information based on the input information to realize multiple rounds of interaction with the user.

[0147] Specifically, the processor 120 can establish a direct interaction between the user and the target robot, that is, the interaction between the user and the target robot can be performed without the electronic device. Alternatively, the processor 120 can also establish an indirect interaction between the user and the target robot, that is, the interaction between the user and the target robot is still performed through the electronic device.

[0148] When the user establishes interaction with the target robot, the user can have multiple rounds of interaction with the target robot, that is, the target robot can generate response information based on the user's input information to achieve multiple rounds of interaction with the user. It should be noted that the multiple rounds of interaction can be carried out in a conversation window, and can be communicated in text or voice.

[0149] In summary, in this embodiment, by receiving the first input information of the user in the intelligent dialogue system, the target robot is determined based on the first input information, and the interaction between the user and the target robot is established in the intelligent dialogue system, wherein the intelligent dialogue system can generate response information based on the input information to realize multiple rounds of interaction with the user; it can be seen that in the present application, the target robot for interacting with the user can be matched based on the user's first input information, that is, the target robot is assigned to the user in a targeted manner, thereby improving the accuracy of solving problems for the user.

[0150] In the second device embodiment of the present application, the electronic device may further include a second interface, and the processor determines the target robot based on the first input information, including:

[0151] (1) sending the first input information to multiple robots through a second interface;

[0152] Specifically, the second interface may be an open interface, and the robot may be registered on the electronic device through the second interface, so that the processor can communicate with multiple registered robots.

[0153] In this embodiment, optionally, in order to prevent the user's privacy information from being leaked, the processor may detect whether the first input information contains sensitive information before sending the first input information to multiple robots. If it is determined that it contains sensitive information, the first input information is desensitized, that is, the sensitive information in the first input information is replaced with general information corresponding to the sensitive information, thereby sending the desensitized first input information to multiple robots.

[0154] Sensitive information may include various private information such as user personal information, device information used, etc. For example, if the first input information contains "Zhang San", since Zhang San is user personal information, "Zhang San" can be replaced with general information "XXX".

[0155] In this embodiment, optionally, in order to ensure that multiple robots can improve the recognition rate of the first input information after receiving the desensitized first input information, the processor can also mark the general information in the desensitized first input information as a sensitive information type and then send it to multiple robots.

[0156] (2) receiving, through a second interface, a plurality of first response messages fed back by the plurality of robots, wherein the first response messages carry a matching degree parameter in response to the input information;

[0157] Specifically, after receiving the first input information, the robot will generate first response information matching the first input information, and determine the matching parameter of the first response information corresponding to the first input information. The matching parameter can be specifically represented as a matching degree, a matching grade, a matching score, etc.

[0158] Among them, the degree of matching can be represented by high, medium, and low, and the higher the degree, the higher the matching degree. The matching level can be represented by primary, secondary, and tertiary levels, and the higher the level, the higher the matching degree. The matching score can be represented by a number, such as 90 points, 80 points, etc., and the higher the score, the higher the matching degree.

[0159] To facilitate information identification, optionally, in this embodiment, the first input information sent by the processor to multiple robots may carry information such as conversation time and conversation turns, and the multiple first response information fed back by the multiple robots may also carry information such as response time and conversation turns.

[0160] (2) Determine that a robot whose matching degree parameter carried in the first response information satisfies a first preset condition is a target robot.

[0161] The first preset condition is used to filter out first response information with a high degree of matching from multiple first response information, so as to determine the robot sending the filtered first response information as the target robot. Specifically, in one embodiment, the processor can determine that the robot whose matching degree parameter carried in the sent first response information meets the preset matching degree parameter is the target robot.

[0162] Taking the matching parameter as the matching degree as an example, the first response information carrying a high matching degree can be determined, so that the robot sending the information is determined as the target robot. Taking the matching degree parameter as the matching score as an example, the first response information carrying a matching score greater than a preset score can be determined, so that the robot sending the information is determined as the target robot. Taking the matching parameter as the matching level as an example, the first response information carrying a matching level greater than a preset level can be determined, so that the robot sending the determined first response information is determined as the target robot.

[0163] In another way, the processor can sort the matching parameters such as matching degree, matching score or matching level from high to low, filter out the first or the first N first response information that carries the matching degree, matching score or matching level in the first place, and determine the robot that sends the filtered first response information as the target robot.

[0164] It can be seen that the target robot determined by the processor may be one or more.

[0165] In the third device embodiment of the present application, the electronic device may further include a second interface, and the processor may determine the target robot based on the first input information, which may include:

[0166] (1) sending the first input information to multiple robots through a second interface;

[0167] Specifically, the second interface may be an open interface, and the robot may be registered on the electronic device through the second interface, so that the processor can communicate with multiple registered robots.

[0168] In this embodiment, optionally, in order to prevent the user's privacy information from being leaked, the processor may detect whether the first input information contains sensitive information before sending the first input information to multiple robots. If it is determined that it contains sensitive information, the first input information is desensitized, that is, the sensitive information in the first input information is replaced with general information corresponding to the sensitive information, thereby sending the desensitized first input information to multiple robots.

[0169] Sensitive information may include various private information such as user personal information, device information used, etc. For example, if the first input information contains "Zhang San", since Zhang San is user personal information, "Zhang San" can be replaced with general information "XXX".

[0170] In this embodiment, optionally, in order to ensure that multiple robots can improve the recognition rate of the first input information after receiving the desensitized first input information, the processor can also mark the general information in the desensitized first input information as a sensitive information type and then send it to multiple robots.

[0171] (2) receiving, through the second interface, a plurality of first response information fed back by the plurality of robots;

[0172] Specifically, after receiving the first input information, the robot generates first response information matching the first input information, and then sends the first response information to the electronic device.

[0173] (3) matching the plurality of first response information with preset dimensional features respectively to determine a matching degree parameter;

[0174] After receiving multiple first response information fed back by multiple robots, the electronic device can match the multiple first response information with preset dimensional features respectively to determine the matching degree parameters of each first response information.

[0175] In this embodiment, the preset dimensional features may include: one or more of: historical chat frequency, robot score, content richness, historical user satisfaction, etc.

[0176] The historical chat frequency can be represented by the number of chats the robot has had with users in the historical records. The robot score can be represented by the score given to the robot by historical users. The historical user satisfaction can be represented by the satisfaction of historical users with the robot.

[0177] The electronic device may perform weighted matching of each first response information with at least one dimensional feature, thereby determining a matching parameter, which may be specifically characterized as a matching degree, a matching grade, or a matching score.

[0178] Among them, the degree of matching can be represented by high, medium, and low, and the higher the degree, the higher the matching degree. The matching level can be represented by primary, secondary, and tertiary levels, and the higher the level, the higher the matching degree. The matching score can be represented by a number, such as 90 points, 80 points, etc., and the higher the score, the higher the matching degree.

[0179] To facilitate information recognition by electronic devices, optionally, in this embodiment, the first input information sent by the processor to multiple robots through the second interface may carry information such as conversation time and conversation turns, and the multiple first response information fed back by the multiple robots may also carry information such as response time and conversation turns.

[0180] (4) A robot that sends the first response information and whose matching parameter satisfies a first preset condition is selected as a target robot.

[0181] The first preset condition is used to filter out first response information with a high degree of matching from multiple first response information, so as to determine the robot sending the filtered first response information as the target robot. Specifically, in one embodiment, the processor can determine that the robot whose matching degree parameter carried in the sent first response information meets the preset matching degree parameter is the target robot.

[0182] Taking the matching parameter as the matching degree as an example, the first response information carrying a high matching degree can be determined, so that the robot sending the information is determined as the target robot. Taking the matching degree parameter as the matching score as an example, the first response information carrying a matching score greater than a preset score can be determined, so that the robot sending the information is determined as the target robot. Taking the matching parameter as the matching level as an example, the first response information carrying a matching level greater than a preset level can be determined, so that the robot sending the determined first response information is determined as the target robot.

[0183] In another way, the processor can sort the matching parameters such as matching degree, matching score or matching level from high to low, and filter out one or the first N first response information that carries the matching degree, matching score or matching level in the first place, thereby determining the robot that sends the filtered first response information as the target robot.

[0184] That is to say, the target robot determined in this application can be one or more.

[0185] In a fourth device embodiment of the present application, the processor sends the first input information to multiple robots through the second interface, including:

[0186] (1) determining the robot type based on the first input information;

[0187] In the present application, the robot types of the multiple robots communicating with the electronic device are various. Among them, the robot type can be characterized by one or more of the robot's image features, the robot's speaking style, the robot's expertise, the robot's language, etc. The processor can determine which type of robot is suitable for the user of the first input information through the first input information, and specifically can determine the robot type through the expression form of the first input information, the content of the first input information, and the language of the first input information.

[0188] The image features of the robot are used to characterize the image of the robot, and may include various image features such as cartoon, girl, boy, etc. The robot's expertise refers to the field in which the robot is suitable for answering questions, such as electronic equipment, life, etc. The robot's speaking style refers to the form of expression of the response information generated by the robot. The language used by the robot refers to the input information language that the robot can understand or the language of the generated response information.

[0189] (2) Sending the first input information to a plurality of robots of the robot type through a second interface.

[0190] Once the robot type is determined, targeted sending can be carried out, that is, the first input information is sent to multiple robots of the robot type, thereby receiving the first response information fed back by this type of robot, and then determining the target robot, which can increase user favorability and improve communication efficiency.

[0191] In the present application, the target robot may include one or more. When there is one target robot, the processor may establish an interaction between the user and the target robot. If the interaction is a direct interaction between the user and the target robot, the target robot may directly output the first response information in the intelligent dialogue system. If the interaction is an indirect interaction between the user and the target robot, the processor may output the first response information in the intelligent dialogue system.

[0192] When the target robots include at least two, in the fifth device embodiment of the present application, the processor is also used to output first response information of the at least two target robots, obtain second input information of the user, determine the first target robot among the at least two target robots based on the second input information, maintain the interaction between the user and the first target robot, and cancel the interaction between the user and other target robots except the first target robot.

[0193] The first response information is information responding to the first input information, and the processor can output the first response information fed back by all determined target robots.

[0194] After seeing the first response information, the user will generally input the second input information into the intelligent dialogue system, so the first target robot with the greatest relevance to the second input information can be determined.

[0195] It should be noted that since the first response information of multiple target robots is different, it is possible to determine that the target robot sending the corresponding first response information is the first target robot by judging which first response information the user's second input information is feedback about, or determining which first response information the user's second input information is most correlated with.

[0196] Specifically, the processor may continue to maintain the distance interaction between the user and the first target robot, or the processor may switch the distance interaction between the user and the first target robot to a direct interaction between the user and the first target robot.

[0197] In this embodiment, when there are multiple target robots determined, the final first target robot can be determined based on the user's second input information, thereby maintaining the interaction between the user and the first target robot, and canceling the interaction between the user and other target robots except the first target robot. The present application can automatically determine the first target robot that meets the user's requirements, further improving the accuracy of solving problems for users.

[0198] In the present application, after establishing the interaction between the user and a target robot, or establishing the interaction between the user and a first target robot, the processor can optionally adjust the target robot based on the user's input information to adjust it to a target robot that better meets the user's current needs. Specifically, the adjustment method can be similar to the method of determining the target robot in the previous text. It should be noted that the processor can shield the user's perception of the adjustment of the target robot, or can also notify the user that the target robot has been adjusted.

[0199] The sixth device embodiment of the present application also provides an information processing system, such as Figure 6 As shown, the information processing system may include: an electronic device 100 and a robot 200, specifically including: a robot 2001, a robot 2002, ..., a robot 200n, where n is greater than or equal to 2.

[0200] The electronic device 100 includes: a first interface 110 and a processor 120; wherein:

[0201] The first interface 110 is used to receive first input information from a user in the intelligent dialogue system;

[0202] The processor 120 is used to determine a target robot among multiple robots based on the first input information, and establish interaction between the user and the target robot in the intelligent dialogue system; wherein the intelligent dialogue system can generate response information based on the input information to realize multiple rounds of interaction with the user.

[0203] It can be understood that the specific implementation form of the electronic device can refer to the above embodiments of the electronic device, which will not be described in detail here.

[0204] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0205] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An information processing method, applied to an electronic device, comprising: Receiving first input information from a user in the intelligent dialogue system; The electronic device can be applied to an intelligent dialogue system; Determine a target robot based on the first input information; Establishing interaction between the user and the target robot in the intelligent dialogue system; wherein the intelligent dialogue system can generate response information based on input information to realize multiple rounds of interaction with the user; The step of determining a target robot based on the first input information comprises: Sending the first input information to multiple robots; wherein the electronic device provides an open interface, and the robot registers on the electronic device through the open interface, so that the electronic device can communicate with the multiple registered robots, thereby sending the first input information to the multiple robots; Receiving a plurality of first response information fed back by the plurality of robots; Based on the plurality of first response information, determining a robot that meets a first preset condition as a target robot; The target robots include at least two target robots; Outputting first response information of the at least two target robots, where the first response information is information in response to the first input information; Obtaining the second input information of the user; A first target robot is determined among the at least two target robots based on the second input information.

2. The method according to claim 1, wherein determining a robot that meets a first preset condition as a target robot based on the plurality of first response information comprises: The first response information carries a matching degree parameter in response to the first input information; A robot whose matching degree parameter carried in the first response information meets a first preset condition is determined as a target robot.

3. The method according to claim 1, wherein determining a robot that meets a first preset condition as a target robot based on the plurality of first response information comprises: Matching the plurality of first response information with the preset dimensional features respectively to determine a matching degree parameter; The robot whose matching parameter for sending the first response information meets the first preset condition is selected as the target robot.

4. The method according to claim 2 or 3, wherein sending the first input information to a plurality of robots comprises: determining a robot type based on the first input information; The first input information is sent to a plurality of robots of the robot type.

5. The method according to claim 1, further comprising: The interaction between the user and the first target robot is maintained, and the interaction between the user and other target robots except the first target robot is cancelled.

6. An electronic device comprising: A first interface, used to receive first input information from a user in the intelligent dialogue system; The electronic device can be applied to an intelligent dialogue system; a processor, configured to determine a target robot based on the first input information, and establish an interaction between the user and the target robot in the intelligent dialogue system; wherein the intelligent dialogue system can generate response information based on the input information to realize multiple rounds of interaction with the user; The electronic device further comprises: Second interface; The processor determines a target robot based on the first input information, including: sending the first input information to a plurality of robots through the second interface; the plurality of robots are electronic devices registered on the electronic device through the second interface; receiving, through the second interface, a plurality of first response information fed back by the plurality of robots; and determining, based on the plurality of first response information, a robot that meets a first preset condition as a target robot; The target robots include at least two target robots; output first response information of the at least two target robots, wherein the first response information is information in response to the first input information; obtain second input information of the user; and determine the first target robot among the at least two target robots based on the second input information.

7. The electronic device according to claim 6, wherein the processor determines, based on the plurality of first response information, that a robot that meets the first preset condition is a target robot, specifically comprising: The first response information carries a matching degree parameter in response to the input information; A robot whose matching degree parameter carried in the first response information meets a first preset condition is determined as a target robot.

8. The electronic device according to claim 6, wherein the processor determines, based on the plurality of first response information, that a robot that meets the first preset condition is a target robot, specifically comprising: Matching the plurality of first response information with the preset dimensional features respectively to determine a matching degree parameter; The robot whose matching parameter for sending the first response information meets the first preset condition is selected as the target robot.

9. The electronic device according to claim 7 or 8, wherein the processor sends the first input information to a plurality of robots through the second interface, comprising: determining a robot type based on the first input information; The first input information is sent to a plurality of robots of the robot type through the second interface.

10. An information processing system comprising: Multiple robots; An electronic device for communicating with the plurality of robots, the electronic device comprising: A first interface is used to receive first input information of a user in an intelligent dialogue system; the electronic device can be applied to the intelligent dialogue system; A processor, for determining a target robot among the multiple robots based on the first input information, and establishing interaction between the user and the target robot in the intelligent dialogue system; wherein the intelligent dialogue system can generate response information based on the input information to realize multiple rounds of interaction with the user; the determination of the target robot based on the first input information comprises: sending the first input information to multiple robots; receiving multiple first response information fed back by the multiple robots; based on the multiple first response information, determining a robot that meets a first preset condition as a target robot; wherein the electronic device provides an open interface, and the robot is registered on the electronic device through the open interface, so that the electronic device can communicate with the multiple registered robots, thereby sending the first input information to the multiple robots; the target robots include at least two target robots; outputting first response information of the at least two target robots, the first response information being information in response to the first input information; obtaining second input information of the user; and determining the first target robot among the at least two target robots based on the second input information.

Images