Man-machine conversation method and device, electronic equipment and storage medium

Abstract

The application discloses a human-computer conversation method and device, electronic equipment and storage medium, wherein the method comprises: carrying out n rounds of human-computer conversation with a user according to an interactive product i generating an interactive voice B i ; playing the interactive voice B i to the user, receiving a first reply voice C i ; matching the first reply voice C i in a historical planning library D i‑1 to obtain a matching result E i ; if the matching result E i is empty, updating the historical planning library D i‑1 according to the first reply voice C i to obtain a historical planning library D i ; if the matching result E i is not empty, generating a prompt voice F i according to the first reply voice C i and the matching result E i , playing the prompt voice F i to the user, receiving a second reply voice G i , updating the historical planning library D i‑1 according to the second reply voice G i to obtain a historical planning library D i , wherein the second reply voice G i is a reply voice of the prompt voice F i input by the user through a user terminal.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of human-computer conversation, and in particular to a human-computer conversation method and device, an electronic device and a storage medium. BACKGROUND

[0002] As a new entertainment carrier, an interactive product usually includes interactive novels, interactive games, voice games and the like, and a common factor of the interactive product is that a certain degree of interaction with a user is needed to advance a story. At present, an interactive manner of the interactive product is usually that after a plot is played, some choices are played or displayed to the user. Then, based on a selection of the user, a corresponding subsequent plot is matched to continue the story until the whole story is completed. This interactive manner makes a plot change according to the selection by giving the user certain choices, and then makes the same story have different narrative feelings under different choices. However, in this manner, the system only simply receives input information of the user to match and play a corresponding plot, and the interactivity between the system and the user is low, and then the overall participation and experience of the user are not high, which affects the playing experience of the user. SUMMARY

[0003] In order to solve the above problems in the prior art, the embodiments of the present application provide a human-computer conversation method, device, electronic device and storage medium, which can improve the interactivity with the user and then improve the participation and experience of the user.

[0004] In a first aspect, the embodiments of the present application provide a human-computer conversation method, which is applied to a server and includes:

[0005] n rounds of human-computer conversation are performed between the interactive product and the user, wherein n is an integer greater than or equal to 1, and n is determined by a total number of interactive nodes in the interactive product;

[0006] The i-th round of human-computer conversation includes:

[0007] According to an interactive node A in the interactive product i generating an interactive voice B i , wherein the interactive node A i is the i-th interactive node arranged in a time axis order in the interactive product, and i is an integer greater than or equal to 1;

[0008] sending the interactive voice B to a user end i , so that the user end plays the interactive voice B to the user i , and receiving a first reply voice C from the user end i , wherein the first reply voice C i is a reply voice of the user to the interactive voice B i input by the user through the user end;

[0009] According to the first reply voice C i In the historical planning database D i-1 The matching process is performed to obtain the matching result E. i Where, when i=1, the historical planning database D i-1 Empty;

[0010] If the matching result is E i If empty, then based on the first reply voice C i Historical planning database D i-1 Update the database to obtain the historical planning database D. i ;

[0011] If the matching result is E i If not empty, then according to the first reply voice C i Matching result E i Generate prompt voice F i Send a prompt voice message F to the user's device. i To enable the client to play a prompt voice message to the user. i And receive a second voice reply from the user's end. i According to the second reply voice G i Historical planning database D i-1 Update the database to obtain the historical planning database D. i Among them, the second reply voice G i It is the user's input of the prompt voice F through the user terminal. i The audio of the response.

[0012] In one possible implementation, according to the first response voice C i Matching result E i Generate prompt voice F i ,include:

[0013] Analysis of the first reply voice C i Confirm completion of the first reply voice message C i The first duration required for the planned event, and the first response voice C i The planned execution duration;

[0014] Analysis of matching results E i Confirm the matching result E i The second duration required for the corresponding event;

[0015] Based on the first duration, the second duration, and the planned duration, the matching result E is determined. i The corresponding event and the first reply voice C i The synchronization relationship between the planned events;

[0016] Generate prompt voice F based on synchronization relationship.i .

[0017] In a possible implementation, the synchronization relationship includes: synchronizable and non-synchronizable, and the matching result E is determined according to the first time length, the second time length, and the planned time length i The corresponding event and the first reply voice C i The synchronization relationship between the planned events includes:

[0018] When it is determined that the sum of the first time length and the second time length is less than or equal to the planned time length, the synchronization relationship is determined as synchronizable;

[0019] When it is determined that the sum of the first time length and the second time length is greater than the planned time length, the first reply voice C i is analyzed, and the matching result E is determined according to the first completion element of the planned event i , the matching result E is analyzed, and the second completion element of the corresponding event is determined i i The second completion element of the corresponding event is determined.

[0020] When it is determined that there is an intersection between the first completion element and the second completion element, the synchronization relationship is determined as synchronizable;

[0021] When it is determined that there is no intersection between the first completion element and the second completion element, the synchronization relationship is determined as non-synchronizable.

[0022] In a possible implementation, after it is determined that there is an intersection between the first completion element and the second completion element, the method further includes:

[0023] Determining a completion time length of the first completion element to obtain a third time length;

[0024] Determining a completion time length of the second completion element to obtain a fourth time length;

[0025] Determining a matching result E i The execution time period of the corresponding event and the first reply voice C i The execution time period of the planned event, and the length of the intersection is obtained as a fifth time length;

[0026] Determining that the fifth time length is greater than a sixth time length, wherein the sixth time length is a maximum time length between the third time length and the fourth time length.

[0027] In a possible implementation, when the matching result E i includes a plurality of historical planned events, and the synchronization relationship is non-synchronizable, a prompt voice F i is generated according to the synchronization relationship, and the prompt voice F includes:

[0028] ​determine a planning period of each of the plurality of historical planning events, to obtain a plurality of first time periods;

[0029] determine a minimum changeable period of each of the historical planning events according to the at least one first time period, to obtain a plurality of second time periods;

[0030] determine the historical planning event corresponding to the maximum value in the plurality of second time periods as a target event;

[0031] generate a voice for changing the target event as a prompt voice F i .

[0032] In a possible implementation, the second reply voice G i is generated according to the prompt voice F i-1 . i

[0033] information extraction is performed on the second reply voice G i , to obtain modification information;

[0034] determine a modification object from the first reply voice C i and the matching result E i according to the modification information;

[0035] when the first reply voice C i is the modification object, a first modification event is generated according to the first reply voice C i and the second reply voice G i , and the first modification event is added to the historical planning library D i-1 , to obtain the historical planning library D i ;

[0036] when the matching result E i is the modification object, a second modification event is generated by modifying the event corresponding to the matching result E i according to the second reply voice G i , a third modification event is generated according to the first reply voice C i , and the event corresponding to the matching result E i-1 in the historical planning library D i is replaced by the second modification event, and the third modification event is added to the historical planning library D i-1 , to obtain the historical planning library D i .

[0037] In a possible implementation, the method further includes:

[0038] ​Through n rounds of human-computer dialogue, m pairs of question-and-answer voices are obtained. Each pair of question-and-answer voices includes a prompt voice and a reply voice that answers the prompt voice. m is an integer greater than or equal to 0 and less than or equal to n.

[0039] Information is extracted from each pair of question-and-answer voice recordings to obtain m sets of modified data, where each set of modified data corresponds one-to-one with a pair of question-and-answer voice recordings.

[0040] Extract information from m modified data to identify k modified objects and the number of modifications to each of the k modified objects, where k is an integer greater than or equal to 1 and less than or equal to m;

[0041] Generate a user capability report based on m modified data, k modified objects, and the number of modifications to each modified object.

[0042] Secondly, embodiments of this application provide a human-computer interaction device, which is applied to a server and includes:

[0043] The dialogue module is used to conduct n rounds of human-computer dialogue with the user based on the interactive product, where n is an integer greater than or equal to 1, and n is determined by the total number of interactive nodes in the interactive product;

[0044] The i-th round of human-computer dialogue includes:

[0045] Based on interaction node A in the interactive product i Generate interactive voice B i Among them, interactive node A i Let i be the i-th interactive node arranged in chronological order in the interactive product, where i is an integer greater than or equal to 1;

[0046] Send interactive voice B to the user terminal i To enable the user terminal to play interactive voice B to the user i And receive the first reply voice C from the user's end. i Among them, the first reply voice C i It is the interactive voice input by the user through the user terminal. i The answer was in voice format;

[0047] According to the first reply voice C i In the historical planning database D i-1 The matching process is performed to obtain the matching result E. i Where, when i=1, the historical planning database D i-1 Empty;

[0048] If the matching result is E i If empty, then based on the first reply voice C i Historical planning database D i-1Update the database to obtain the historical planning database D. i ;

[0049] If the matching result is E i If not empty, then according to the first reply voice C i Matching result E i Generate prompt voice F i Send a prompt voice message F to the user's device. i To enable the client to play a prompt voice message to the user. i And receive a second voice reply from the user's end. i According to the second reply voice G i Historical planning database D i-1 Update the database to obtain the historical planning database D. i Among them, the second reply voice G i It is the user's input of the prompt voice F through the user terminal. i The audio of the response.

[0050] Thirdly, embodiments of this application provide an electronic device, including: a processor connected to a memory for storing a computer program, and the processor for executing the computer program stored in the memory to cause the electronic device to perform the method as described in the first aspect.

[0051] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that causes a computer to perform the method as described in the first aspect.

[0052] Fifthly, embodiments of this application provide a computer program product, the computer program product including a non-transitory computer-readable storage medium storing a computer program, and a computer operable to perform the method as described in the first aspect.

[0053] Implementing the embodiments of this application has the following beneficial effects:

[0054] In this embodiment, based on the interactive nodes of the interactive product, corresponding interactive voice is generated to ask the user a question. Then, based on the user's first reply voice, historical reply voices in the historical planning database are matched. When a match is found, the first reply voice and the matching result are combined again to generate a prompt voice to interact with the user again. Simultaneously, the historical planning database is updated based on the user's second reply voice. Therefore, compared with the interaction method of traditional interactive novels, by analyzing the user's current reply and historical replies to generate corresponding interactive voices to interact with the user, user participation is improved, thereby enhancing the user's reading experience. Attached Figure Description

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those of ordinary skill in the art without any creative effort based on these drawings.

[0056] Figure 1 A hardware structure schematic diagram of a man-machine conversation device provided by the embodiments of the present application;

[0057] Figure 2 A schematic diagram of a man-machine conversation system applicable to the man-machine conversation method provided by the embodiments of the present application;

[0058] Figure 3 A flowchart of a man-machine conversation method provided by the embodiments of the present application;

[0059] Figure 4 A function module composition block diagram of a man-machine conversation device provided by the embodiments of the present application;

[0060] Figure 5 A structure schematic diagram of an electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0061] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without any creative effort belong to the scope of protection of the present application.

[0062] The terms "first", "second", "third", and "fourth" and the like in the specification and claims of the present application and the drawings are used to distinguish different objects, and are not used to describe a particular sequence. In addition, the terms "include" and "have" and any variations thereof are intended to cover the inclusions without exclusivity. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but can optionally include other steps or units not listed or can optionally include other steps or units inherent to such processes, methods, products or devices.

[0063] Reference to an "implementation" in this document means that a particular feature, result or characteristic described in connection with an implementation can be included in at least one implementation of the application. The appearance of the phrase in various places in the specification is not necessarily all referring to the same implementation, or is not necessarily referring to a separate or alternative implementation, in isolation or in combination with other implementations. It is explicitly and implicitly understood by those skilled in the art that implementations described herein can be combined with other implementations.

[0064] Reference to an "implementation" in this document means that a particular feature, result or characteristic described in connection with an implementation can be included in at least one implementation of the application. The appearance of the phrase in various places in the specification is not necessarily all referring to the same implementation, or is not necessarily referring to a separate or alternative implementation, in isolation or in combination with other implementations. It is explicitly and implicitly understood by those skilled in the art that implementations described herein can be combined with other implementations. Figure 1 Figure 1 A schematic diagram of a hardware structure of a human-computer dialogue device according to an implementation of the application is shown in FIG. 1. The human-computer dialogue device 100 includes at least one processor 101, a communication line 102, a memory 103, and at least one communication interface 104.

[0065] In this implementation, the processor 101 can be a general central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of programs according to the solutions of the application.

[0066] The communication line 102 can include a path for transmitting information between the above-mentioned components.

[0067] The communication interface 104 can be any kind of device (such as an antenna) for transmitting and receiving signals, for communicating with other devices or communication networks, such as Ethernet, RAN, wireless local area networks (WLAN), etc.

[0068] The memory 103 can be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited thereto.​

[0069] In this embodiment, the memory 103 can exist independently and be connected to the processor 101 via the communication line 102. Alternatively, the memory 103 can be integrated with the processor 101. The memory 103 provided in this embodiment is typically non-volatile. The memory 103 stores computer execution instructions for implementing the scheme of this application, and its execution is controlled by the processor 101. The processor 101 executes the computer execution instructions stored in the memory 103 to implement the method provided in the following embodiments of this application.

[0070] In an optional implementation, the computer execution instructions may also be referred to as application code, and this application does not specifically limit this.

[0071] In an optional implementation, processor 101 may include one or more CPUs, for example... Figure 1 CPU0 and CPU1 in the CPU.

[0072] In an optional implementation, the human-computer interaction device 100 may include multiple processors, such as... Figure 1 Processors 101 and 107 are shown in the diagram. Each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor here may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0073] In optional implementations, if the human-computer interaction device 100 is a server, for example, it can be a standalone server or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. Then the human-computer interaction device 100 may further include an output device 105 and an input device 106. The output device 105 communicates with the processor 101 and can display information in various ways. For example, the output device 105 can be a liquid crystal display (LCD), a light emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector, etc. The input device 106 communicates with the processor 101 and can receive user input in various ways. For example, the input device 106 can be a mouse, keyboard, touchscreen device, or sensor device, etc.

[0074] The man-machine dialogue device 100 can be a general device or a special device. The type of the man-machine dialogue device 100 is not limited in the embodiments of the present application.

[0075] Secondly, it needs to be explained that the man-machine dialogue method provided in the embodiments of the present application can be applied to the scene of training the specific ability of the user. For example, the planning, planning, layout and other abilities of the user can be trained and cultivated by the man-machine dialogue method.

[0076] Specifically, Figure 2 A schematic diagram of a man-machine dialogue system applicable to the man-machine dialogue method provided in the embodiments of the present application is shown, which can include a server 201 and a user terminal 202. The server 201 is used to analyze the interaction nodes of the interactive product, generate corresponding voice and send it to the user terminal 202, receive the reply voice of the user returned by the user terminal 202, analyze the reply voice of the user in combination with the historical reply of the user, generate a prompt voice and send it to the user terminal 202. The user terminal 202 can be a smart phone (such as an Android phone, an iOS phone, a Windows Phone phone, etc.), a tablet computer, a palm computer, a notebook computer, a mobile internet device (MID, Mobile Internet Devices for short: MID) and the like, which is used to receive the plot voice and the prompt voice generated by the server 201, play it to the user, and receive the reply voice of the user and feed it back to the server 201. Thus, deep man-machine dialogue is realized.

[0077] In the following, the man-machine dialogue method disclosed in the present application will be described by taking the scene of training the planning ability of the user by the interactive product, i.e. the interactive novel, as an example. Based on this, in the following content, the interactive product will be represented by the interactive novel. At the same time, the man-machine dialogue method in other interactive products and scenes is similar to the method in the scene of training the planning ability of the user by the interactive novel, which will not be described again in the embodiments.

[0078] In the embodiments, the user accesses by the related software, WeChat applet, webpage and the like installed on the user terminal. After successful access, the user can browse the list of interactive novels and select the interested ones for reading. For example, the user can click the interactive novel of interest to send a reading instruction to the server. After receiving the reading instruction of the user on the interactive novel, the server determines the data of the corresponding interactive novel based on the reading instruction, and carries out n rounds of man-machine dialogue with the user based on the data.

[0079] Specifically, refer to Figure 3 , Figure 3A flowchart illustrating the i-th round of human-computer dialogue method provided in this application embodiment, the human-computer dialogue method including the following steps:

[0080] 301: Based on interactive node A in the interactive novel i Generate interactive voice B i .

[0081] In this embodiment, interactive node A i Let i be the i-th interactive node in the interactive novel, arranged chronologically, where i is an integer greater than or equal to 1. Specifically, the interactive novel includes a pre-set interactive script containing multiple storylines arranged chronologically. Each storyline includes multiple interactive nodes, and each interactive node corresponds to user actions and machine response actions. User actions include user input of a response voice, and machine response actions include the server providing interactive voice and outputting a machine response voice after receiving the user's response voice.

[0082] In an optional implementation, interactive voice B is generated. i Previously, it was necessary to determine whether the current interaction node was the target interaction node. For example, a target interaction node is one where the user needs to plan the main events corresponding to the current storyline. For instance, if the current storyline involves the user's character A and B discussing a trip, then if the current interaction node is B asking A when to go on the trip, then this current interaction node is the target interaction node, and the user needs to answer with the travel planning time at this node. Based on this, the server can generate corresponding interactive voice B according to the storyline content of the target interaction node. i To interact with users.

[0083] 302: Send interactive voice B to the user terminal i To enable the user terminal to play interactive voice B to the user i And receive the first reply voice C from the user's end. i .

[0084] In this embodiment, the first response voice C i It is the interactive voice input by the user through the user terminal. i The audio of the response.

[0085] 303: Based on the first reply voice message C i In the historical planning database D i-1 The matching process is performed to obtain the matching result E. i .

[0086] In the embodiment, the historical planning library is used to store the interaction data of the user when reading the interactive novel. Specifically, after the server generates the corresponding interaction voice and plays it to the user terminal, the user will reply based on the interaction voice and input the first reply voice to the user terminal. The historical planning library is a database for storing the verified and extracted data of the reply voice. When i = 1, i.e., the first round of human-computer dialogue, the historical planning library D i-1 is empty, i.e., D0 is empty.

[0087] For example, in the embodiment, the time information planned in the first reply voice C i is matched in the historical planning library D i-1 to determine the historical planning record with time overlap as the matching result E i . Specifically, after obtaining the first reply voice C i input by the user, the planning content of the user is analyzed to obtain the time information included in the planning content. At the same time, the server obtains the historical planning record of the user in the historical planning library D i-1 , determines whether there is a historical planning record overlapping with the time information included in the current planning content in the historical planning record, and if so, extracts it as the matching result E i .

[0088] 304: Determine whether the matching result E i is empty, if yes, jump to step 305, otherwise jump to step 306.

[0089] 305: Update the historical planning library D i according to the first reply voice C i-1 to obtain the historical planning library D i .

[0090] In the embodiment, when the matching result E i is empty, it means that there is no historical planning conflicting with the current planning time, so the first reply voice C i can be extracted and sorted into corresponding planning events and stored in the historical planning library D i-1 , and then the historical planning library D i-1 is updated to obtain the historical planning library D i .

[0091] 306: Generate a prompt voice F i according to the first reply voice C i and the matching result E i , and send the prompt voice F i to the user terminal to play the prompt voice F to the user.i and receives a second reply voice G from the user terminal i , according to the second reply voice G i updates the historical planning library D i-1 , and obtains a historical planning library D i .

[0092] In the embodiment, the second reply voice G i is a reply voice of the user to the prompt voice F i input by the user terminal. When the matching result E i is not empty, it means that there is a historical planning that conflicts with the current planning time. Based on this, further analysis needs to be performed on these historical planning to determine whether to change the current planning or the matching historical planning, and then generate the corresponding prompt voice F i .

[0093] For example, first, the first reply voice C i can be analyzed to determine the first duration required to complete the event planned by the first reply voice C i , and the execution duration planned by the first reply voice C i . At the same time, the matching result E i is analyzed to determine the second duration required to complete the event corresponding to the matching result E i . Then, according to the first duration, the second duration and the planning duration, the synchronization relationship between the event corresponding to the matching result E i and the event planned by the first reply voice C i is determined, and then the prompt voice F i is generated according to the synchronization relationship.

[0094] In the embodiment, the synchronization relationship can include: synchronizable and unsynchronizable. When determining the synchronization relationship between the event corresponding to the matching result E i and the event planned by the first reply voice C i , first, the size relationship between the sum of the first duration and the second duration and the planning duration can be determined to preliminarily determine whether they can be performed simultaneously. Specifically, when it is determined that the sum of the first duration and the second duration is less than or equal to the planning duration, it is determined that the synchronization relationship is synchronizable. That is, it is determined whether the content of the current plot can be performed simultaneously with other events, if yes, it is marked as synchronizable, if not, it is marked as unsynchronizable. When the mark of the plot corresponding to the reference planning record is synchronizable, and the mark of the current plot is also synchronizable, it is determined that the time period required for the event corresponding to the reference planning record and the current plot, such as the time period corresponding to the planning time, is greater than the sum of the two, it is considered that they can be performed simultaneously.

[0095] In the embodiment, when it is determined that the sum of the first duration and the second duration is greater than the planned duration, then the first reply voice C i is analyzed to determine the first completion element of the planned event i , the matching result E i is analyzed to determine the second completion element of the corresponding event i . Then, when it is determined that there is an intersection between the first completion element and the second completion element, it is determined that the synchronization relationship is synchronizable. Specifically, when the sum of the first duration and the second duration is greater than the planned duration, it is further determined whether the two events can be overlapped and performed, and if so, it is considered that they can be simultaneously performed. In determining whether they can be overlapped and performed, the completion elements of the event corresponding to the reference planning record and the event corresponding to the current plot are determined, and whether they can be overlapped and performed is determined according to the coincidence degree of the completion elements. For example, the planned event A going to an amusement park on Saturday is with B, so the completion elements include the amusement park and B, and the current plot planning is to take an article to B on Saturday, so the completion elements include the article and B, and the completion elements both include B, so it is considered that they can be overlapped and performed, and then they can be simultaneously performed.

[0096] In an optional embodiment, after it is determined that there is an intersection between the first completion element and the second completion element, it can also be determined whether the events that can be overlapped and performed can be completed within the intersection duration of the execution period of the event corresponding to the matching result E i and the execution period of the event planned by the first reply voice C i . That is, the completion duration of the first completion element is determined to obtain a third duration, the completion duration of the second completion element is determined to obtain a fourth duration, and the intersection duration of the execution period of the event corresponding to the matching result E i and the execution period of the event planned by the first reply voice C i is determined to obtain a fifth duration. Then, it is determined that the fifth duration is greater than a sixth duration, where the sixth duration is the maximum duration between the third duration and the fourth duration. Specifically, it is determined whether the events that can be simultaneously performed can be completed within the period in which the event corresponding to the matching result E i and the event planned by the first reply voice C i have an intersection, and if so, it is considered that the two events can be simultaneously performed.

[0097] In the embodiment, after determining that the two can be performed simultaneously, the server outputs corresponding prompt voice Fi, which prompts the user that the current planning needs to be performed simultaneously with the previous planning, and asks whether to change. If the user does not change, the current planning information is recorded and the reading of the interactive story continues. For example, the user plans to go to the amusement park on Saturday in the previous plot, and the current plot is to take the item to B, and the user also plans the time on Saturday, which can be taking the item to B when going to the amusement park on Saturday.

[0098] In the embodiment, when it is determined that there is no intersection between the first completion element and the second completion element, it is determined that the synchronization relationship is not synchronously performed. When it is determined that the synchronization relationship is not simultaneously performed, the server outputs a prompt voice, which prompts the user that there is a conflict between the current planning and the historical planning, and lets the user select to adjust one of the planning contents. After receiving the prompt voice, the user can input a second reply voice G i through the user end to determine the selected changed planning and the change scheme.

[0099] For example, after obtaining the second reply voice G i of the user, information extraction can be performed on the second reply voice G i to obtain modification information, and then the modification information is used to determine the modification object in the first reply voice C i and the matching result E i . When the first reply voice C i is the modification object, a first modification event is generated according to the first reply voice C i and the second reply voice G i , and the first modification event is added to the historical planning library D i-1 to obtain the historical planning library D i ; when the matching result E i is the modification object, a second modification event is generated by modifying the event corresponding to the matching result E i according to the second reply voice G i , a third modification event is generated according to the first reply voice C i , and the event corresponding to the matching result E i-1 in the historical planning library D i is replaced by the second modification event, and the third modification event is added to the historical planning library D i-1 to obtain the historical planning library D i .

[0100] Specifically, if the user selects to adjust the current planning content, the server determines the planning range according to the historical planning records and the constraints of the current plot, and outputs the planning range to the user, guiding the user to plan within the planning range. If the user selects to adjust the planning content of the historical planning, the current plot is jumped to the interaction node corresponding to the historical planning, and then the planning content of the user at the interaction node is obtained, and after the user completes the modification of the historical planning, the current interaction node is jumped back. When modifying the planning content in the historical planning, it is also necessary to consider whether there is a conflict with the planning in other planning records, so the user may need to jump to multiple interaction nodes in turn to modify the previous planning.

[0101] In the embodiment, before the user jumps to the interaction node corresponding to the historical planning, it is also necessary to determine the number of current historical planning, i.e., the matching result E i The number of historical planning events included, if there are multiple historical planning, it is determined whether there are planning that need to be performed simultaneously in the multiple historical planning, if they are all planning that need to be performed simultaneously, prompt information is output before jumping, prompting the user to need to change the planning content corresponding to the multiple historical planning at the same time. Exemplarily, the planning period of each historical planning event in the multiple historical planning events can be determined, obtaining multiple first time periods. At the same time, according to at least one first time period, the minimum changeable time period of each historical planning event is determined, obtaining multiple second time periods. Then, the historical planning event corresponding to the maximum value in the multiple second time periods is determined as the target event, and the voice for changing the target event is generated as the prompt voice F i . Specifically, the planning time of each historical planning is obtained, the minimum changeable time of each historical planning is determined according to the planning time, the minimum changeable time is the time that meets the story plot and does not coincide with other existing planning time, the reference planning record with the maximum minimum changeable time is determined as the target event, and the user is prompted to change the planning in the target event preferentially.

[0102] In addition, the man-machine conversation method provided in the embodiment can also be used to generate a capability report of the user, which is then displayed to the user after the user finishes reading the interactive novel. Specifically, through n rounds of man-machine conversation, m pairs of question and answer audios can be obtained, where each pair of question and answer audios includes a prompt audio and a reply audio for answering the prompt audio, and m is an integer greater than or equal to 0 and less than or equal to n. That is, when there is a plan that cannot be performed at the same time, the server will associate and record the prompt audio with the reply audio of the user while generating the corresponding prompt audio, forming a pair of question and answer audios. Then, information extraction is performed on each pair of question and answer audios to obtain m pieces of modification data, where the m pieces of modification data correspond to the m pairs of question and answer audios one by one. Then, information extraction is performed on the m pieces of modification data to determine k modification objects and the number of modifications of each modification object in the k modification objects, where k is an integer greater than or equal to 1 and less than or equal to m. Finally, according to the m pieces of modification data, the k modification objects and the number of modifications of each modification object, a capability report of the user is generated and sent to the user end for display to the user. The user can determine the number of conflicts, the category, the proportion of each category, etc. of his / her own planning in this reading by reading the capability report, and further determine his / her own planning ability.

[0103] In summary, in the man-machine conversation method provided in the present application, based on the interaction nodes of the interactive product, corresponding interaction audios are generated to ask the user, and then based on the first reply audio of the user, historical reply audios in the historical planning library are matched, when there is a matching result, the first reply audio and the matching result are again combined to generate a prompt audio to interact with the user again, and at the same time, the historical planning library is updated based on the second reply audio of the user. Thus, compared with the traditional interactive novel interaction mode, by analyzing the current reply and historical reply of the user to generate corresponding interaction audios to interact with the user, the user's participation is improved, and the user's reading experience is improved. At the same time, through the man-machine conversation mode, the user is guided to plan events, and when the planning conflicts, the user is guided to change the planning, thereby realizing the entertainment function and cultivating the planning ability of the user, and outputting an accurate capability report to play a good auxiliary role in cultivating the user's ability.

[0104] Reference Figure 4 , Figure 4 A functional module composition block diagram of a man-machine conversation device provided in the embodiment of the present application is shown in FIG. 4. Figure 4 As shown in FIG. 4, the man-machine conversation device 400 includes:

[0105] A conversation module 401 is configured to perform n rounds of man-machine conversation with the user according to the interactive product, where n is an integer greater than or equal to 1, and n is determined by the total number of interaction nodes in the interactive product.

[0106] The i-th round of human-computer dialogue includes:

[0107] Based on interaction node A in the interactive product i Generate interactive voice B i Among them, interactive node A i Let i be the i-th interactive node arranged in chronological order in the interactive product, where i is an integer greater than or equal to 1;

[0108] Send interactive voice B to the user terminal i To enable the user terminal to play interactive voice B to the user i And receive the first reply voice C from the user's end. i Among them, the first reply voice C i It is the interactive voice input by the user through the user terminal. i The answer was in voice format;

[0109] According to the first reply voice C i In the historical planning database D i-1 The matching process is performed to obtain the matching result E. i Where, when i=1, the historical planning database D i-1 Empty;

[0110] If the matching result is E i If empty, then based on the first reply voice C i Historical planning database D i-1 Update the database to obtain the historical planning database D. i ;

[0111] If the matching result is E i If not empty, then according to the first reply voice C i Matching result E i Generate prompt voice F i Send a prompt voice message F to the user's device. i To enable the client to play a prompt voice message to the user. i And receive a second voice reply from the user's end. i According to the second reply voice G i Historical planning database D i-1 Update the database to obtain the historical planning database D. i Among them, the second reply voice G i It is the user's input of the prompt voice F through the user terminal. i The audio of the response.

[0112] In an embodiment of the present invention, based on the first response voice C i Matching result E i Generate prompt voice F i Regarding the dialogue module 401, it is specifically used for:

[0113] analyzing the first reply voice C i , determining a first duration required for completing the event planned by the first reply voice C i , and an execution duration planned by the first reply voice C i ;

[0114] analyzing the matching result E i , determining a second duration required for completing the event corresponding to the matching result E i ;

[0115] determining, according to the first duration, the second duration and the planned duration, a synchronization relationship between the event corresponding to the matching result E i and the event planned by the first reply voice C i ;

[0116] generating a prompt voice F i according to the synchronization relationship.

[0117] In an embodiment of the present application, the synchronization relationship includes: synchronizable and unsynchronizable, based on which, in the aspect of determining, according to the first duration, the second duration and the planned duration, the synchronization relationship between the event corresponding to the matching result E i and the event planned by the first reply voice C i , the dialogue module 401 is specifically configured to:

[0118] when determining that the sum of the first duration and the second duration is less than or equal to the planned duration, determining that the synchronization relationship is synchronizable;

[0119] when determining that the sum of the first duration and the second duration is greater than the planned duration, analyzing the first reply voice C i , determining a first completion element of the event planned by the first reply voice C i , analyzing the matching result E i , determining a second completion element of the event corresponding to the matching result E i ;

[0120] when determining that there is an intersection between the first completion element and the second completion element, determining that the synchronization relationship is synchronizable;

[0121] when determining that there is no intersection between the first completion element and the second completion element, determining that the synchronization relationship is unsynchronizable.

[0122] In an embodiment of the present application, after determining that there is an intersection between the first completion element and the second completion element, the dialogue module 401 is specifically configured to:

[0123] determining a completion duration of the first completion element, obtaining a third duration;

[0124] Determine the completion time of the second completion element to obtain the fourth completion time;

[0125] Determine the matching result E i The execution time of the corresponding event and the first response voice C i The fifth duration is the sum of the intersections of the planned execution periods.

[0126] The fifth duration is determined to be greater than the sixth duration, where the sixth duration is the maximum duration between the third and fourth durations.

[0127] In an embodiment of the present invention, when the matching result E i When multiple historical planning events are involved, and their synchronization relationships are not synchronized, a prompt voice F is generated based on the synchronization relationship. i Regarding the dialogue module 401, it is specifically used for:

[0128] The planning period for each historical planning event among multiple historical planning events is determined, resulting in multiple first time periods;

[0129] Based on at least one first time period, determine the minimum modifiable time period for each historical planning event, resulting in multiple second time periods;

[0130] The historical planning events corresponding to the maximum values ​​in multiple second time periods are identified as target events;

[0131] Generate a voice prompt F that modifies the target event. i .

[0132] In an embodiment of the present invention, based on the second response voice G i Historical planning database D i-1 Update the database to obtain the historical planning database D. i Regarding the dialogue module 401, it is specifically used for:

[0133] Regarding the second reply voice G i Extract information to obtain the modified information;

[0134] According to the modified information, in the first reply voice C i Matching result E i The object to be modified is determined in the middle;

[0135] When the first reply voice C i When modifying an object, based on the first response voice C i Second reply voice G i Generate the first modification event and add it to the historical planning database D. i-1 In the middle, the historical planning database D is obtained. i ;

[0136] When the matching result E i For the modification object, according to the second reply voice G i The matching result E i The corresponding event is modified to generate a second modified event, according to the first reply voice C i Generate a third modified event, and replace the historical planning library D i-1 The matching result E i The corresponding event, the third modified event is added to the historical planning library D i-1 , obtain the historical planning library D i .

[0137] In an embodiment of the present application, the man-machine dialogue device 400 can further include an analysis module 402, which is specifically used for:

[0138] Through n rounds of man-machine dialogue, m pairs of question and answer voices are obtained, wherein each pair of question and answer voice in the m pairs of question and answer voices includes a prompt voice and a reply voice answering the prompt voice, m is an integer greater than or equal to 0 and less than or equal to n;

[0139] Information extraction is performed on each pair of question and answer voice to obtain m pieces of modification data, wherein the m pieces of modification data correspond one-to-one to the m pairs of question and answer voices;

[0140] Information extraction is performed on the m pieces of modification data to determine k modification objects and the number of modifications of each modification object in the k modification objects, wherein k is an integer greater than or equal to 1 and less than or equal to m;

[0141] According to the m pieces of modification data, the k modification objects and the number of modifications of each modification object, a capability report of the user is generated.

[0142] Referring to Figure 5 , Figure 5 A structural schematic diagram of an electronic device provided in an embodiment of the present application. As shown in Figure 5 The electronic device 500 includes a transceiver 501, a processor 502 and a memory 503. They are connected through a bus 504. The memory 503 is used to store computer programs and data, and can transmit the data stored in the memory 503 to the processor 502.

[0143] The processor 502 is used to read the computer program in the memory 503 to perform the following operations:

[0144] According to the interactive product, n rounds of man-machine dialogue are carried out with the user, wherein n is an integer greater than or equal to 1, and n is determined by the total number of interactive nodes in the interactive product;

[0145] Wherein, the i th round of man-machine dialogue includes:

[0146] Based on interaction node A in the interactive product i Generate interactive voice B i Among them, interactive node A i Let i be the i-th interactive node arranged in chronological order in the interactive product, where i is an integer greater than or equal to 1;

[0147] Send interactive voice B to the user terminal i To enable the user terminal to play interactive voice B to the user i And receive the first reply voice C from the user's end. i Among them, the first reply voice C i It is the interactive voice input by the user through the user terminal. i The answer was in voice format;

[0148] According to the first reply voice C i In the historical planning database D i-1 The matching process is performed to obtain the matching result E. i Where, when i=1, the historical planning database D i-1 Empty;

[0149] If the matching result is E i If empty, then based on the first reply voice C i Historical planning database D i-1 Update the database to obtain the historical planning database D. i ;

[0150] If the matching result is E i If not empty, then according to the first reply voice C i Matching result E i Generate prompt voice F i Send a prompt voice message F to the user's device. i To enable the client to play a prompt voice message to the user. i And receive a second voice reply from the user's end. i According to the second reply voice G i Historical planning database D i-1 Update the database to obtain the historical planning database D. i Among them, the second reply voice G i It is the user's input of the prompt voice F through the user terminal. i The audio of the response.

[0151] In an embodiment of the present invention, based on the first response voice C i Matching result E i Generate prompt voice F i In this regard, processor 502 is specifically used to perform the following operations:

[0152] analyzing the first reply voice C i , determining a first duration required for completing the event planned by the first reply voice C i , and an execution duration planned by the first reply voice C i ;

[0153] analyzing the matching result E i , determining a second duration required for completing the event corresponding to the matching result E i ;

[0154] determining, according to the first duration, the second duration and the planned duration, a synchronization relationship between the event corresponding to the matching result E i and the event planned by the first reply voice C i ;

[0155] generating a prompt voice F i according to the synchronization relationship.

[0156] In an embodiment of the present application, the synchronization relationship includes: synchronizable and unsynchronizable, based on which, in the aspect of determining, according to the first duration, the second duration and the planned duration, the synchronization relationship between the event corresponding to the matching result E i and the event planned by the first reply voice C i , the processor 502 is specifically configured to perform the following operations:

[0157] when determining that the sum of the first duration and the second duration is less than or equal to the planned duration, determining that the synchronization relationship is synchronizable;

[0158] when determining that the sum of the first duration and the second duration is greater than the planned duration, analyzing the first reply voice C i , determining a first completion element of the event planned by the first reply voice C i , analyzing the matching result E i , and determining a second completion element of the event corresponding to the matching result E i ;

[0159] when determining that there is an intersection between the first completion element and the second completion element, determining that the synchronization relationship is synchronizable;

[0160] when determining that there is no intersection between the first completion element and the second completion element, determining that the synchronization relationship is unsynchronizable.

[0161] In an embodiment of the present application, after determining that there is an intersection between the first completion element and the second completion element, the processor 502 is specifically configured to perform the following operations:

[0162] determining a completion duration of the first completion element, to obtain a third duration;

[0163] Determine the completion time of the second completion element to obtain the fourth completion time;

[0164] Determine the matching result E i The execution time of the corresponding event and the first response voice C i The fifth duration is the sum of the intersections of the planned execution periods.

[0165] The fifth duration is determined to be greater than the sixth duration, where the sixth duration is the maximum duration between the third and fourth durations.

[0166] In an embodiment of the present invention, when the matching result E i When multiple historical planning events are involved, and their synchronization relationships are not synchronized, a prompt voice F is generated based on the synchronization relationship. i In this regard, processor 502 is specifically used to perform the following operations:

[0167] The planning period for each historical planning event among multiple historical planning events is determined, resulting in multiple first time periods;

[0168] Based on at least one first time period, determine the minimum modifiable time period for each historical planning event, resulting in multiple second time periods;

[0169] The historical planning events corresponding to the maximum values ​​in multiple second time periods are identified as target events;

[0170] Generate a voice prompt F that modifies the target event. i .

[0171] In an embodiment of the present invention, based on the second response voice G i Historical planning database D i-1 Update the database to obtain the historical planning database D. i In this regard, processor 502 is specifically used to perform the following operations:

[0172] Regarding the second reply voice G i Extract information to obtain the modified information;

[0173] According to the modified information, in the first reply voice C i Matching result E i The object to be modified is determined in the middle;

[0174] When the first reply voice C i When modifying an object, based on the first response voice C i Second reply voice G i Generate the first modification event and add it to the historical planning database D. i-1 In the middle, the historical planning database D is obtained. i ;

[0175] When the matching result E i When the modification object is modified, the second reply voice G i The matching result E i The corresponding event is modified to generate a second modified event, and the first reply voice C i A third modified event is generated, and the second modified event replaces the historical planning library D i-1 The matching result E i The corresponding event is added to the historical planning library D i-1 The third modified event is obtained from the historical planning library D i .

[0176] In an embodiment of the application, the processor 502 is further configured to perform the following operations:

[0177] Through n rounds of human-computer dialogue, m pairs of question and answer voices are obtained, wherein each pair of question and answer voice in the m pairs of question and answer voices includes a prompt voice and a reply voice answering the prompt voice, m is an integer greater than or equal to 0 and less than or equal to n;

[0178] Information extraction is performed on each pair of question and answer voice to obtain m pieces of modification data, wherein the m pieces of modification data correspond one-to-one to the m pairs of question and answer voices;

[0179] Information extraction is performed on the m pieces of modification data to determine k modification objects and the number of modifications of each modification object in the k modification objects, wherein k is an integer greater than or equal to 1 and less than or equal to m;

[0180] According to the m pieces of modification data, the k modification objects and the number of modifications of each modification object, a capability report of the user is generated.

[0181] It should be understood that the human-computer dialogue device in the present application can include a smart phone (such as an Android phone, an iOS phone, a Windows Phone phone, etc.), a tablet computer, a palm computer, a notebook computer, a mobile Internet device (MID, Mobile Internet Devices for short), a robot or a wearable device, etc. The above-mentioned human-computer dialogue device is only an example, not an exhaustive list, and includes but is not limited to the above-mentioned human-computer dialogue device. In actual application, the above-mentioned human-computer dialogue device can also include a smart vehicle terminal, a computer device, etc.

[0182] Those skilled in the art can clearly understand the present application by the description of the foregoing embodiments. Based on such understanding, all or part of the technical solutions of the present application that contribute to the background art can be embodied in the form of a software product. The computer software product can be stored in a storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, or the like, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the method described in each embodiment or part of the embodiments of the present application.

[0183] Therefore, the embodiments of the present application further provide a computer-readable storage medium storing a computer program. The computer program is executed by a processor to implement part or all of the steps of any of the human-computer dialogue methods described in the foregoing method embodiments. For example, the storage medium can include a hard disk, a floppy disk, an optical disk, a magnetic tape, a disk, a USB flash disk, a flash memory, or the like.

[0184] The embodiments of the present application further provide a computer program product including a non-transitory computer-readable storage medium storing a computer program. The computer program is operable to cause a computer to perform part or all of the steps of any of the human-computer dialogue methods described in the foregoing method embodiments.

[0185] It should be noted that, for the foregoing method embodiments, in order to simply describe, each of the method embodiments is described as a series of action combinations, but those skilled in the art should know that the present application is not limited to the order of the actions described, because according to the present application, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0186] In the foregoing embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0187] In the several embodiments provided by the present application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the division of the units described above is merely a logical function division, and there can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical or other forms.

[0188] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one place or distributed on multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiment scheme according to actual needs.

[0189] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically, or two or more units can be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of a software program module.

[0190] The integrated unit, if realized in the form of a software program module and sold or used as an independent product, can be stored in a computer readable memory. Based on this understanding, the technical scheme of the present application essentially or the part that contributes to the prior art or the whole or part of the technical scheme can be embodied in the form of a software product. The computer software product is stored in a memory and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0191] A person of ordinary skill in the art can understand that all or part of the steps in the above-described embodiments can be completed by programs instructing related hardware, and the programs can be stored in a computer readable memory, which can include: a flash disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0192] The embodiments of the present application are described in detail above, and specific examples are applied to the principles and embodiments of the present application. The above description of the embodiments is only to help understand the method and core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, the specific embodiments and application range will be changed; in view of the above, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A human-computer dialogue method, characterized in that, The method is applied to a server, and the method includes: The interactive product engages in n rounds of human-computer dialogue with the user, where n is an integer greater than or equal to 1, and n is determined by the total number of story nodes in the interactive product. The i-th round of human-computer dialogue includes: According to plot node A in the interactive product i Generate interactive voice B i , wherein the plot node A i The i-th plot node in the interactive product, arranged in chronological order, is where i is an integer greater than or equal to 1. Send the interactive voice B to the user terminal i So that the user terminal plays the interactive voice B to the user. i and receive the first response voice C from the user terminal. i Among them, the first reply voice C i It is the interactive voice B input by the user through the user terminal. i The answer was in voice format; According to the first reply voice C i In the historical planning database D i-1 The matching process is performed to obtain the matching result E. i Where, when i=1, the historical planning database D i-1 Empty; If the matching result E i If empty, then according to the first reply voice C i For the historical planning database D i-1 Update the database to obtain the historical planning database D. i ; If the matching result E i If not empty, then according to the first reply voice C i And the matching result E i Generate prompt voice F i Send the prompt voice F to the user terminal i So that the user terminal plays the prompt voice F to the user. i and receive a second response voice G from the user terminal. i According to the second reply voice G i For the historical planning database D i-1 Update the database to obtain the historical planning database D. i Among them, the second reply voice G i It is the user's input of the prompt voice F through the user terminal. i The audio of the response.

2. The method according to claim 1, characterized in that, According to the first reply voice C i And the matching result E i Generate prompt voice F i ,include: Analysis of the first response voice C i Confirm completion of the first response voice C i The first duration required for the planned event, and the first response voice C i The planned execution duration; Analyze the matching result E i Determine the completion of the matching result E. i The second duration required for the corresponding event; The matching result E is determined based on the first duration, the second duration, and the execution duration. i The corresponding event is related to the first reply voice C. i The synchronization relationship between the planned events; The prompt voice F is generated based on the synchronization relationship. i .

3. The method according to claim 2, characterized in that, The synchronization relationship includes: synchronous and non-synchronous processes. The matching result E is determined based on the first duration, the second duration, and the execution duration. i The corresponding event is related to the first reply voice C. i The planned synchronization relationships between events include: When it is determined that the sum of the first duration and the second duration is less than or equal to the execution duration, the synchronization relationship is determined to be synchronous. When it is determined that the sum of the first duration and the second duration is greater than the execution duration, the first response voice C is analyzed. i Determine the first response voice C i The first completion element of the planned event, analyzed in the matching result E i Determine the matching result E i The second completion element of the corresponding event; When it is determined that there is an intersection between the first completion element and the second completion element, the synchronization relationship is determined to be synchronous. When it is determined that there is no intersection between the first completion element and the second completion element, the synchronization relationship is determined to be non-synchronous.

4. The method according to claim 3, characterized in that, After determining that there is an intersection between the first completion element and the second completion element, the method further includes: The completion time of the first completion element is determined to obtain the third duration; Determine the completion duration of the second completion element to obtain the fourth duration; Determine the matching result E i The execution time of the corresponding event is the same as the first response voice C. i The fifth duration is the sum of the intersections of the planned execution periods. The fifth duration is determined to be greater than the sixth duration, wherein the sixth duration is the maximum duration between the third duration and the fourth duration.

5. The method according to claim 3, characterized in that, When the matching result E i When multiple historical planning events are included, and the synchronization relationship is not synchronous, the prompt voice F is generated based on the synchronization relationship. i ,include: The planning period for each of the multiple historical planning events is determined to obtain multiple first time periods; Based on at least one first time period, determine the minimum modifiable time period for each historical planning event to obtain multiple second time periods; The historical planning event corresponding to the maximum value among the multiple second time periods is determined as the target event; Generate a voice prompt F that modifies the target event. i .

6. The method according to any one of claims 1-5, characterized in that, According to the second reply voice G i For the historical planning database D i-1 Update the database to obtain the historical planning database D. i ,include: Regarding the second reply voice G i Extract information to obtain the modified information; According to the modified information, in the first reply voice C i And the matching result E i The object to be modified is determined in the middle; When the first reply voice C i When modifying an object, according to the first response voice C i And the second reply voice G i Generate a first modification event and add the first modification event to the historical planning database D. i-1 In the process, the historical planning database D is obtained. i ; When the matching result E i When modifying an object, according to the second response voice G i For the matching result E i The corresponding event is modified to generate a second modified event, based on the first reply voice C. i Generate a third modification event and replace the historical planning library D with the second modification event. i-1 The matching result E described in the text i The corresponding event will be added to the historical planning database D. i-1 In the process, the historical planning database D is obtained. i .

7. The method according to claim 6, characterized in that, The method further includes: Through the n rounds of human-computer dialogue, m pairs of question-and-answer voices are obtained, wherein each pair of question-and-answer voices in the m pairs of question-and-answer voices includes a prompt voice and a reply voice that answers the prompt voice, and m is an integer greater than or equal to 0 and less than or equal to n; Information is extracted from each pair of question-and-answer voice recordings to obtain m sets of modified data, wherein each set of modified data corresponds one-to-one with the m pairs of question-and-answer voice recordings. Information is extracted from the m modified data to determine k modification objects and the number of modifications for each of the k modification objects, where k is an integer greater than or equal to 1 and less than or equal to m; A capability report for the user is generated based on the m modified data, the k modified objects, and the number of modifications to each modified object.

8. A human-computer dialogue device, characterized in that, The device is used in a server, and the device includes: The dialogue module is used to conduct n rounds of human-computer dialogue with the user based on the interactive product, where n is an integer greater than or equal to 1, and n is determined by the total number of plot nodes in the interactive product. The i-th round of human-computer dialogue includes: According to plot node A in the interactive product i Generate interactive voice B i , wherein the plot node A i The i-th plot node in the interactive product, arranged in chronological order, is where i is an integer greater than or equal to 1. Send the interactive voice B to the user terminal i So that the user terminal plays the interactive voice B to the user. i and receive the first response voice C from the user terminal. i Among them, the first reply voice C i It is the interactive voice B input by the user through the user terminal. i The answer was in voice format; According to the first reply voice C i In the historical planning database D i-1 The matching process is performed to obtain the matching result E. i Where, when i=1, the historical planning database D i-1 Empty; If the matching result E i If empty, then according to the first reply voice C i For the historical planning database D i-1 Update the database to obtain the historical planning database D. i ; If the matching result E i If not empty, then according to the first reply voice C i And the matching result E i Generate prompt voice F i Send the prompt voice F to the user terminal i So that the user terminal plays the prompt voice F to the user. i and receive a second response voice G from the user terminal. i According to the second reply voice G i For the historical planning database D i-1 Update the database to obtain the historical planning database D. i Among them, the second reply voice G i It is the user's input of the prompt voice F through the user terminal. i The audio of the response.

9. An electronic device, characterized in that, The method includes a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the one or more programs include instructions for performing the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is executed by a processor to implement the method as described in any one of claims 1-7.

Images