Information processing method and device

Abstract

The present application discloses an information processing method and device, which includes: receiving a first request information input by a user; performing intent recognition on the first request information, determining a first task engine responsible for the first request information, wherein the first task engine is provided with a first slot; extracting key information from the first request information according to the first slot; if key information cannot be extracted from the first request information according to the first slot, or if key information is extracted from the first request information according to the first slot and the extracted key information does not meet a condition, then obtaining target key information from the shared parameter list of the user. By using the method and device of the present application, a better user experience and higher human-computer interaction efficiency can be obtained.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an information processing method and device. Background Art

[0002] With the rapid development of the Internet, the application of human-computer interaction systems is becoming more and more extensive. The input of the human-computer interaction system can be requests such as asking about the weather, booking air tickets, encyclopedia knowledge and chatting, and the human-computer interaction system can feedback information that meets the user's needs based on the user's request. For example, the user's input request can be "Beijing's weather tomorrow", and the information fed back to the user by the human-computer interaction system can be "Beijing's weather tomorrow will be sunny and cloudy."

[0003] In the prior art, the human-computer interaction system must obtain the key information that satisfies the conditions in the user's request information. If the key information that satisfies the conditions is not obtained in the user's request information, the human-computer interaction system will feedback the processing failure information to the user, resulting in a poor user experience and low human-computer interaction efficiency. Summary of the invention

[0004] The present application provides an information processing method and device to obtain a better user experience and higher human-computer interaction efficiency.

[0005] In a first aspect, the present application provides an information processing method, comprising: receiving first request information input by a user; performing intent recognition on the first request information, determining a first task engine responsible for the first request information, wherein a first slot is provided in the first task engine; extracting key information from the first request information according to the first slot;

[0006] If no key information can be extracted from the first request information according to the first slot, or if key information is extracted from the first request information according to the first slot and the extracted key information does not meet the conditions, then obtain the target key information in the shared parameter list of the user; wherein the target key information corresponds to a second slot in the second task engine, the second slot has the same slot type as the first slot, the second slot is a slot in the second task engine, and the first task engine is different from the second task engine.

[0007] In the embodiment of the present application, if the key information cannot be extracted for the first slot, or the extracted key information does not meet the conditions, the target key information is obtained in the user's shared parameter list. Compared with the solution in the prior art, the key information cannot be extracted or the extracted key information does not meet the conditions, that is, the information of the processing failure is fed back, so that the user re-enters the request, which can obtain a better user experience and higher human-computer interaction efficiency. In a possible implementation, the shared parameter list includes the corresponding relationship between the second slot and the target key information.

[0008] In a possible implementation, the second task engine is determined by the context parameter of the user or the second task engine is determined according to the correlation between the first task engine and the second task engine.

[0009] In a possible implementation, the shared parameter list includes a correspondence between the first task engine and one or more task engines, a correspondence between slots included in any two task engines having a correspondence, and a correspondence between the second slot and target key information, and the one or more task engines include the second task engine;

[0010] The target key information can be obtained in the user's shared parameter list in the following manner: determine the second task engine based on the correspondence between the first task engine and one or more task engines; determine the second slot that has a correspondence with the first slot of the first task engine among the slots included in the second task engine included in the shared parameter list based on the correspondence between the slots; determine the target key information based on the correspondence between the second slot and the target key information.

[0011] Optionally, the second task engine is responsible for the second request information of the user, the second request information and the first request information occur within a preset time, and the second request information and the first request information occur within a preset number of dialogue rounds, and a round of dialogue may specifically refer to a process in which a user inputs a request information and a human-computer interaction system feeds back a message.

[0012] In the embodiment of the present application, the shared parameter list is combined with the occurrence time of the request information to determine the second task engine, which can more accurately locate the second task engine and improve the accuracy of the target key information filled in the second slot.

[0013] In a possible implementation, the shared parameter list stores a correspondence between the second slot and the target key information, and the target key information can be obtained in the shared parameter list of the user in the following manner: determine the second task engine that is adjacent in time to the first task engine through the context parameters of the user; determine the second slot of the same type as the first slot in the slot of the second task engine; determine the target key information according to the correspondence between the second slot and the target key information. Among them, the second task engine is responsible for the second request information of the user, and the second task engine is provided with a slot of the same type as the first slot, and the time proximity means that the occurrence time of the second request information is adjacent to the occurrence time of the first request information. In a possible implementation, when determining the second slot of the same type as the first slot, when there are two or more slots of the same type as the first slot, they can be selected according to the preset priority information.

[0014] In an embodiment of the present application, only one correspondence is stored in the shared parameter list, namely, the correspondence between different slots of the task engine and the target key information. Compared with the implementation method of the above-mentioned shared parameter list (three correspondences need to be stored in the above-mentioned shared parameter list), the method of the present application can reduce the amount of data stored in the shared parameter list and increase the rate of accessing the shared parameter list.

[0015] In a possible implementation, the shared parameter list is a shared parameter list exclusively used by the second task engine, and the shared parameter list exclusively used by the second task engine may include a corresponding relationship between the second slot and the key information. The following method may be used to obtain the target key information in the shared parameter list of the user: determine the second task engine based on the correlation between the first task engine and the second task engine, and the correlation between the first task engine and the second task engine is greater than a preset threshold; determine the shared parameter list exclusively used by the second task engine based on the second task engine; in the shared parameter list exclusively used by the second task engine, search for a slot of the same slot type as the first slot as the second slot; determine the target key information based on the corresponding relationship between the second slot and the target key information.

[0016] In an embodiment of the present application, each task engine of the human-computer interaction system maintains a shared parameter table, which stores the correspondence between the slots of the task engine and the target key information. Corresponding to the above two shared parameter lists, one is to maintain three correspondences, and the other is to store the correspondence between the slots of multiple task engines and the target key information. The shared parameter list of the present application can further reduce the amount of data stored in the shared parameter list and further improve the rate of accessing the shared parameter list.

[0017] In an embodiment of the present application, the key information that does not meet the conditions includes reference information, and in the correspondence between the second slot and the target key information included in the shared parameter list, the target key information corresponding to the second slot is unique, and the key information corresponding to the second slot is updateable.

[0018] In one possible implementation, the target key information corresponding to the second slot can be updated in the following manner, specifically: receiving a third request information input by a user, the third request information being responsible for the second task engine; extracting the key information corresponding to the second slot of the second task engine in the third request information; and updating the target key information corresponding to the second slot in the correspondence between the second slot and the target key information in the shared parameter list according to the key information corresponding to the second slot extracted in the third request information.

[0019] In an embodiment of the present application, a plurality of slots may be provided in the first task engine, and the first slot may be determined from the plurality of slots in the following manner, specifically: determining a plurality of slots provided in the first task engine, the plurality of slots having priority information; and determining the first slot according to the priority information of the plurality of slots.

[0020] In an example of the present application, the slot type may specifically be time, place, behavior or person, etc.

[0021] In a possible implementation, the shared parameter list may be stored in the local end, such as a memory in the information processing apparatus, or may be obtained from an external storage device via a communication network or an access interface.

[0022] In a second aspect, the present application provides an information processing apparatus for use in a terminal device or a server, comprising: a unit or means for executing each step of the above first aspect.

[0023] In a third aspect, the present application provides an information processing device for a terminal device or a server, comprising at least one processing element and at least one storage element, wherein the at least one storage element is used to store programs and data, and the at least one processing element is used to execute the method provided in the first aspect of the present application.

[0024] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the method described in the first aspect above.

[0025] In a fifth aspect, the present application provides a computer program, wherein the computer program includes computer instructions, and when the computer instructions are executed by a computer, the computer executes the method described in the first aspect.

[0026] In a sixth aspect, the present application provides a human-computer interaction system, including a central control module and a task engine module, wherein the central control module is implemented by the information processing device provided by the present application, and the engine module is used to implement the functions of the first task engine and the second task engine. In a possible implementation, the human-computer interaction system also includes a multi-task parameter sharing management module, and the shared parameter list can be stored in the shared parameter management module. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A human-computer interaction system provided for this application;

[0028] Figure 2 Another human-computer interaction system provided for this application;

[0029] Figure 3 An information processing flow provided for this application;

[0030] Figure 4 Another information processing process provided for this application;

[0031] Figure 5 A schematic diagram of a shared parameter list provided for this application;

[0032] Figure 6 Another schematic diagram of the shared parameter list provided for this application;

[0033] Figure 7 Another schematic diagram of a shared parameter list provided for this application;

[0034] Figure 8 Another information processing flow provided for this application;

[0035] Fig. 9 A structural diagram of a communication device provided by the present application;

[0036] Fig.10 This is another structural diagram of the communication device provided by this application. DETAILED DESCRIPTION

[0037] like Figure 1 As shown, the present application provides a human-computer interaction system, which mainly includes a central control module and a task engine module; the human-computer interaction system may also include a task status library module.

[0038] Among them, the central control module is mainly responsible for distributing the dialogue request to one or more related task engine modules, and then summarizing and deciding the results returned by multiple task engine modules to obtain the final result.

[0039] The task engine module includes multiple task engines, each of which is mainly responsible for a specific area of ​​dialogue business, such as parsing the request information input by the user to obtain key information that meets the conditions. For example, for the flight booking task engine, the key information that meets the flight booking task can be extracted from the request information input by the user, such as the origin information, destination information, and time information.

[0040] The task state library module is mainly used to store the intermediate states of user dialogue tasks.

[0041] In this application, after the task engine module obtains key information that meets the conditions, the task engine module can perform the corresponding task according to the key information, or the central control module can perform the corresponding task according to the key information, or the intelligent terminal can perform the corresponding task according to the key information, or a new module can be developed in the human-computer interaction system to perform the corresponding task according to the key information. In this application, the subject that performs the corresponding task according to the key information is not specifically limited.

[0042] It should be noted that the functions of the human-computer interaction system can be implemented by a server, can be implemented by a terminal device, or can be implemented by a server and a terminal device together.

[0043] Therefore, the human-computer interaction system described above mainly includes a central control module and a task engine module. It can be understood that when the function of the human-computer interaction system is implemented by a server, the server includes a central control module and a task engine module; when the function of the human-computer interaction system is implemented by a terminal device, the terminal device includes a central control module and a task engine module.

[0044] In an example of the present application, taking "after the task engine module obtains key information that meets the conditions, the task engine module sends the key information to the central control module, and the central control module performs the corresponding task" as an example, the working process of the entire human-computer interaction system is described in detail:

[0045] The user inputs request information to the intelligent terminal, wherein the request information may be voice information, text information, or image information. The intelligent terminal forwards the user's request information to the central control module of the human-computer interaction system. The central control module forwards the user's request information to one or more task engines in the task engine module. The task engine may parse the request information, obtain key information that meets the conditions, and send the key information that meets the conditions to the central control module. The central control module may execute the corresponding task based on the key information fed back by the task engine module. At the same time, the task engine may store the corresponding parsing results in the corresponding task state in the task state library module.

[0046] For example, user A inputs a request "I want to book a flight from Beijing to Shanghai tomorrow" in the smart terminal, then the smart terminal can send the request "User A wants to book a flight from Beijing to Shanghai tomorrow" to the central control module, and the central control module can first determine that the request is processed by the "ticket booking task engine", and then send the request "User A wants to book a flight from Beijing to Shanghai tomorrow" to the ticket booking task engine in the task engine module, and the ticket booking task engine can parse the request information of "User A wants to book a flight from Beijing to Shanghai tomorrow" to obtain the following key information that meets the conditions {Intent = "Book a flight", time = "tomorrow", starting point = "Beijing", destination = "Shanghai"}, then the "ticket booking task engine" can feed back the key information to the central control module, and the central control module can book "a flight from Beijing to Shanghai tomorrow" for user A based on the key information fed back by the "ticket booking task engine", and finally generate feedback information of the processing result "a flight from Beijing to Shanghai tomorrow has been booked for you, and the booking information is ****", and send the feedback information to the smart terminal, and the smart terminal can display the feedback information to the user through text, voice or image.

[0047] From the above analysis, it can be seen that Figure 1In the human-computer interaction system shown, when processing the user's task request, it is necessary to obtain key information that meets the conditions for executing the task before processing the user's task request. For example, for a task request to book a flight, it is necessary to obtain key information such as "time, origin and destination" that meets the task of booking a flight before booking a flight for the user according to the user's task request; for a task request to query the weather, it is necessary to obtain key information such as "location and time" that meets the task of querying the weather before querying the weather for the user. If the key information cannot be extracted in a task request, or the key information can be extracted but the extracted key information does not meet the conditions, the human-computer interaction system will feedback prompts such as "processing failed, please re-enter the information", and the user needs to re-enter the request information, which makes the efficiency of human-computer interaction low. For example, if the user first enters the request information "I want to book a flight from Beijing to Shanghai tomorrow", and then enters the request information "How is the weather over there", when processing the request information "How is the weather over there", key information such as weather and location that meet the weather query task cannot be extracted, the human-computer interaction system will result in the feedback "Excuse me, which city do you want to ask about the weather conditions", resulting in a poor user experience and low efficiency of human-computer interaction.

[0048] Based on the above scenario, Figure 2 As shown, the present application provides a human-computer interaction system, which at least includes: a central control module, a task engine module and a multi-task parameter sharing management module. Optionally, it may also include: a task status library module.

[0049] The corresponding functions of the central control module, task engine module and task status library module can be found in the above Figure 1 As shown in the records, no further details will be given here.

[0050] The multi-task parameter sharing management module may store a shared parameter list, the number of which may be one, and the n task engines in the human-computer interaction system may share the shared parameter list. Alternatively, the number of shared parameter lists may be multiple, and each task engine in the human-computer interaction system may occupy one shared parameter list. For example, if the entire human-computer interaction system includes n task engines, then the multi-task parameter sharing management module may also include n shared parameter lists, and each of the n task engines may occupy one of the n shared parameter lists.

[0051] Optionally, the multi-task parameter management module may further include a multi-task parameter sharing management unit for managing a shared parameter list.

[0052] In the embodiment of the present application, the shared parameter list can be generated according to the user's historical conversation parameters. In the embodiment of the present application, when the task engine module cannot extract key information from the request information input by the user, or can extract key information but the extracted key information does not meet the conditions, the target key information that meets the conditions can be obtained in the shared parameter list, without the need for the user to repeatedly input, the user experience is better, and the efficiency of human-computer interaction is effectively improved.

[0053] based on Figure 2 The human-computer interaction system shown in the present application provides an information processing method, the execution subject of the method can be the above Figure 1 or Figure 2 The smart terminal shown in the figure can also be used to run the above Figure 1 or Figure 2 The server of the human-computer interaction system shown in the figure may be, but is not limited to, a cloud server. In the embodiment of the present application, the server running the human-computer interaction system is taken as an example as an execution subject. Figure 3 As shown, the flow of the information processing method is described in detail.

[0054] Step S301: The server receives first request information input by a user.

[0055] In the embodiment of the present application, the first request information may be voice information, text information or image information, etc. The user may input the first request information to the smart terminal, and the smart terminal may forward the first request information to the server.

[0056] Step S302: the server performs intent recognition on the received first request information, and determines a first task engine responsible for the first request information.

[0057] In the embodiment of the present application, the central control module in the server can perform intent recognition on the first request information, and determine the first task engine responsible for the first request information according to the intent recognition result. For example, if the central control module determines that the intent recognition result of the first request information is to book a flight, then the first task engine responsible for the first request information can be determined to be the flight booking task engine.

[0058] In an embodiment of the present application, different slots may be provided in each task engine, and the slot may be specifically a variable, and the value of the slot (slot view) may be specifically the key information corresponding to the slot. In an embodiment of the present application, the slot may also be referred to as an information slot, and the key information corresponding to the slot may also be referred to as slot information. In an embodiment of the present application, the process of the present application is described in detail by taking the first slot provided in the first task engine as an example. It should be noted that in an embodiment of the present application, the words "first, second" and the like in the first task engine, the second task engine, the first slot and the second slot are only used for the purpose of distinguishing descriptions, and cannot be understood as indicating or implying relative importance, nor can they be understood as indicating or implying order.

[0059] Step S303: The server extracts key information from the first request information according to the first slot.

[0060] For example, if the first task engine is a "ticket booking task engine" and the first slot is a "origin slot", the server can extract the key information corresponding to the "origin slot" in the first request information. For another example, if the first slot is a "destination slot", the server can extract the key information corresponding to the "destination slot" in the first request information.

[0061] Step S304: If no key information can be extracted from the first request information according to the first slot, or if key information is extracted from the first request information according to the first slot and the extracted key information does not meet the conditions, the server obtains the target key information from the shared parameter list of the user.

[0062] The shared parameter list includes at least a correspondence between the second slot and the target key information, the second slot and the first slot have the same slot type, the slot type is time, place, behavior or person, etc., the second slot is a slot in the second task engine, and the first task engine is different from the second task engine. The key information that does not meet the conditions may be specifically reference information, and the reference information may be specifically that the key information extracted from the first request information is a reference word, and the reference word may be a reference word such as "this", "that", "here", "there", etc.

[0063] Step S305: The server executes corresponding tasks according to the target key information.

[0064] As can be seen from the above, in the embodiment of the present application, when the key information cannot be extracted from the first request information input by the user, or the key information can be extracted but the extracted key information does not meet the conditions, the target key information can be obtained from the user's shared parameter list, and the corresponding task can be executed according to the target key information. Figure 1 The solution shown, when the key information cannot be extracted, or the extracted key information does not meet the conditions, the user is requested to input the solution again. By adopting the solution of this application, the user experience is better and the human-computer interaction efficiency is higher.

[0065] In an example of the present application, a plurality of slots may be provided in the first task engine, and the level of each slot is the same, and the key information corresponding to each slot may be filled in any order. For example, the first task engine is provided with a "starting slot", a "destination slot" and a "time slot", and the key information corresponding to each slot may be filled in the order of "starting slot", "destination slot" and "time slot", or the key information corresponding to each slot may be filled in the order of "time slot", "destination slot" and "starting slot", etc.

[0066] In another example of the present application, a plurality of slots may be provided in the first task engine, each slot having a different priority, and the key information corresponding to each slot may be filled in according to the priority of the slot. For example, the task engine for booking a flight ticket includes three slots, namely, a "starting place slot", a "destination slot" and a "time slot", and the "time slot" is set with the highest priority, the "starting place slot" with the second highest priority, and the "destination slot" with the lowest priority. Then, the key information corresponding to the "time slot" may be filled in first, and then the key information corresponding to the "starting place slot" may be filled in, and finally the key information corresponding to the "destination slot" may be filled in.

[0067] In the embodiment of the present application, the process of filling the key information corresponding to each slot is described in detail by taking the first slot as an example: first, in the request information input by the user, the key information corresponding to the first slot is extracted. If the key information can be extracted and the extracted key information meets the conditions, the filling of the first slot is completed. If the key information cannot be extracted in the request information, or the key information can be extracted but the extracted key information does not meet the conditions, the target key information is obtained from the user's shared parameter list, and the target key information is used as the key information corresponding to the first slot.

[0068] Optional, in Figure 3 The process shown may also include: the server updates the shared parameter list of the user according to the semantic recognition result of each task engine, and the semantic recognition result includes the intention information and the key information that meets the conditions.

[0069] For example, if the first request input by user A is "book a flight from Beijing to Shanghai tomorrow", then the semantic recognition result obtained by the flight booking task engine may be {intent = "book a flight"; time = "tomorrow", starting place = "Beijing", destination = "Shanghai"}. Among them, the intent information is {intent = "book a flight"}, and the key information that meets the conditions is {time = "tomorrow", starting place = "Beijing", destination = "Shanghai"}.

[0070] In the embodiment of the present application, when the first request information corresponds to N other task engines in addition to the first task engine, for example, the user inputs the first request information "book a ticket from Beijing to Shanghai tomorrow", then the central control module of the human-computer interaction system performs intent recognition on the first request information input by the user, and finds that the first request information corresponds to "booking a ticket", and the entire human-computer interaction system includes "booking a plane ticket task engine", "booking a train ticket task engine" and "booking a bus ticket task engine", then the central control module can send the above-mentioned first request information to the "booking a train ticket task engine", "booking a bus ticket task engine" and "booking a plane ticket task engine" respectively. It can be said that the first request information corresponds to the three task engines of the above-mentioned "booking a train ticket task engine", "booking a bus ticket task engine" and "booking a plane ticket task engine".

[0071] In an embodiment of the present application, when the first task request corresponds to N+1 task engines, the N+1 task engines include the first task engine and the other N task engines mentioned above. Then, the N+1 task engines mentioned above can send their respective semantic recognition results for the first request information to the central control module, and the central control module can select a semantic recognition result that meets the rules from the N+1 semantic recognition results mentioned above, such as the optimal semantic recognition result, and update the shared parameter list of the user.

[0072] like Figure 4 As shown, in an example of the present application, the above Figure 3 The server shown in the figure includes a central control module, a task engine module and a multi-task parameter sharing management module as an example, and the above Figure 3 The information processing flow shown is:

[0073] Step S401: the intelligent terminal receives first request information input by a user, and sends the first request information to a central control module of the human-computer interaction system.

[0074] Step S402: the central control module performs intent recognition on the first request information, obtains one or more task engines related to the first request information, and sends the first request information to one or more task engines in the task engine module.

[0075] Step S403: for a task engine, determine the slot corresponding to the task engine.

[0076] Different task engines may correspond to different slots. For example, the slot corresponding to the flight booking task engine may be the "origin slot", "destination slot" or "location slot". The slot corresponding to the weather query task engine may be the "location slot" or "time slot".

[0077] Step S404: The task engine extracts key information from the first request information according to the slot corresponding to the task engine.

[0078] For example, for the weather query task engine, the corresponding slots may specifically include "location slot" and "time slot", and the weather query task engine may extract the key information corresponding to the "location slot" and "time slot" in the first request information input by the user. For another example, the first request information input by the user may be "query the weather conditions in Beijing tomorrow", then the weather query task engine may extract the key information "Beijing" corresponding to the "location slot" and the key information "tomorrow" corresponding to the "time slot" in the above first request information.

[0079] Step S405: For a slot, if key information can be extracted from the first request information and the extracted key information meets the conditions, then execute step S409; otherwise, execute step S406.

[0080] Step S406: The task engine sends a read instruction to the task parameter sharing management module.

[0081] Step S407: The multi-task parameter sharing management module obtains target key information from the shared parameter list of the user.

[0082] Step S408: The multi-task parameter sharing management module sends the target key information to the task engine.

[0083] Step S409: the task engine obtains a semantic recognition result for the first request information.

[0084] The semantic recognition result includes the intention information for the first request information and key information that meets the conditions.

[0085] Step S410: the task engine sends the semantic recognition result of the first request information to the central control module.

[0086] Step S411: the central control module updates the user's shared parameter list in the multi-task parameter sharing management module according to the semantic recognition result sent by the task engine.

[0087] It should be noted that in the above Figure 4In the process shown, the task engine module reads information from the shared parameter list, and the central control module updates the shared parameter list as an example for explanation. In the embodiment of the present application, the subject that reads information from the shared parameter list and the subject that updates the shared parameter list are not limited. For example, in the present application, the central control module may be responsible for reading information from the shared parameter list and updating the shared parameter list. Alternatively, the task engine module is responsible for reading information from the shared parameter list and updating the shared parameter list. Alternatively, the central control module is responsible for reading information from the shared parameter list, and the task engine module is responsible for updating the shared parameter list. Alternatively, the task engine module is responsible for reading information from the shared parameter list, and the central control module is responsible for updating the shared parameter list.

[0088] In the embodiments of the present application, it will be described in detail. Figure 3 or Figure 4 In the process shown, "how to obtain target key information based on the user's shared parameter list".

[0089] The embodiment of the present application provides the following two types of shared parameter lists, namely, a first shared parameter list and a second shared parameter list. Target key information can be obtained by using the first shared parameter list or the second shared parameter list.

[0090] The first shared parameter list: the number of shared parameter lists is one, and all task engines in the human-computer interaction system share the shared parameter list, that is, only one shared parameter list is stored in the above-mentioned multi-task parameter sharing management module.

[0091] In an example of the present application, for the first shared parameter list, the first shared parameter list may specifically include: the correspondence between the first task engine and one or more task engines, the correspondence between the slots included in any two task engines with a corresponding relationship, and the correspondence between the second slot and the target key information. The one or more task engines include the second task engine. For the first shared parameter list, the following method can be specifically used to obtain the target key information:

[0092] Determining a second task engine according to a correspondence between the first task engine and one or more task engines;

[0093] Optionally, the second task engine may be used to be responsible for the second request information of the user, the second request information and the first request information may occur within a preset time, and the second request information and the first request information may occur within a preset number of dialogue rounds.

[0094] According to the correspondence between the slots, determining, among the slots included in the second task engine included in the shared parameter list, a second slot that has a correspondence with the first slot of the first task engine;

[0095] The target key information is determined according to the corresponding relationship between the second slot and the target key information.

[0096] In this example, three specific correspondences may be stored in the first shared parameter list, namely: the correspondence between different task engines, and if there is a correspondence between two task engines, the correspondence between the slots included in the two task engines, and the correspondence between the slots included in each task engine and the target key information.

[0097] For example, Figure 1 As shown, taking the weather query task engine as an example, the process of obtaining the target key information may be: first obtain the task engine that interacts with the user within a preset time (such as 10 minutes) and a preset number of dialogue rounds (such as 5 rounds of dialogue, the process of one round of dialogue specifically includes the user inputting a request information and the human-computer interaction system feeding back a message). For example, the interactive task engine may include {air ticket booking task engine, takeaway ordering task engine}. Then, obtain the task engine in the shared parameter list that has a corresponding relationship with the weather query task engine, for example, it may be {air ticket booking task engine, train ticket booking task engine, hotel booking task engine}. Then take the intersection of the two, that is, take the intersection of {air ticket booking task engine, takeaway ordering task engine} with {air ticket booking task engine, train ticket booking task engine, hotel booking task engine}. It can be seen that the intersection of the two is {air ticket booking task engine}. Then, in the slots of the air ticket booking task engine, query the slots that have a corresponding relationship with the location slots of the weather query task engine, through Figure 5 It can be seen that the slot that corresponds to the location slot of the weather query task engine is the destination slot of the flight booking task engine; finally, the target key information corresponding to the destination slot, i.e. Shanghai, is used as the key information of the location slot of the weather query task engine.

[0098] In another example of the present application, for the first shared parameter list, the first shared parameter list may specifically include a correspondence between the second slot and the target key information. For the first shared parameter list, the target key information may be determined in the following manner:

[0099] Determining, by using the context parameter of the user, a second task engine that is adjacent in time to the first task engine;

[0100] The second task engine is used to be responsible for the second request information of the user, the second task engine is provided with a slot of the same type as the first slot, and the time proximity means that the occurrence time of the second request information is adjacent to the occurrence time of the first request information;

[0101] Determine, in the slots of the second task engine, a second slot of the same type as the first slot;

[0102] The target key information is determined according to the corresponding relationship between the second slot and the target key information.

[0103] It should be noted that in the example of the present application, the time of the first task engine and the second task engine is adjacent, which can specifically include the following two situations: the first situation: the first task request responsible for the first task engine and the second task request responsible for the second task engine are adjacent in time, that is, the first task request input by the user and the second task request are adjacent in time. For example, the user first inputs the first task request "book a flight from Beijing to Shanghai" in the human-computer interaction system, and then inputs the second task request "how is the weather over there" in the human-computer interaction system. It can be considered that the above-mentioned first task request and the above-mentioned second task request are adjacent in time. At the same time, it is set that the above-mentioned "first task request" is responsible for the "ticket booking" task engine, and the above-mentioned "second task request" is responsible for the "weather query" task engine, then it can be determined that the above-mentioned "ticket booking" task engine and the "weather query" task engine are adjacent in time. The second situation: the first task request responsible for the first task engine and the second task request responsible for the second task engine are separated by a preset time in time, and both are within the preset number of dialogue rounds.

[0104] In this example, only one correspondence is stored in the entire shared parameter list, that is, the correspondence between the slot of each task engine and the key information.

[0105] Still taking the example of filling the location slot of the weather query task engine, the process of obtaining the target key information can be as follows: first, in the user's context parameters, obtain the task engine adjacent to the weather query task engine, that is, the task engine that the user interacts with before interacting with the weather query task engine, for example Figure 6 As shown, the task engine that is adjacent to the weather query task engine in time is the flight booking task engine. Then, in the slots of the flight booking task engine, the slots of the same type as the location slots are searched, for example, the slots of the same type are the destination slots, and finally, the key information corresponding to the destination slot of the flight booking task engine in the shared parameter list, i.e., Shanghai, is used as the key information corresponding to the location slot in the weather query field.

[0106] The second type of shared parameter list: There are multiple shared parameter lists, and each task engine exclusively occupies one shared parameter list. For example, the entire human-computer interaction system includes N task engines, so the multi-task parameter sharing management module can store N shared parameter lists, and each of the N task engines exclusively occupies one shared parameter list among the N shared parameter lists.

[0107] For the second type of shared parameter list, the shared parameter list can specifically store the correspondence between the second slot and the target key information. The target key information can be obtained in the following manner, specifically: obtain the first task engine corresponding to the first request information; obtain the second task engine, wherein the second task engine corresponds to the second vertical domain, the first task engine corresponds to the first vertical domain, the correlation between the first vertical domain and the second vertical domain is greater than a preset threshold, and the correlation between the first vertical domain and the second vertical domain is obtained by clustering historical data; in the shared parameter list exclusively occupied by the second task engine, search for a slot with the same slot type as the first slot as the second slot, and determine the target key information according to the correspondence between the second slot and the target key information.

[0108] In an example of the present application, for example, for a shared parameter list maintained by a flight booking task engine, the following example can be used: Figure 7 shown.

[0109] In the embodiment of the present application, the shared parameter list can be generated according to the historical dialogue parameters between the user and the human-computer interaction system. For example, the user inputs the request information of "booking a flight from Beijing to Shanghai today" to the human-computer interaction system, then the flight booking task engine can extract the key information "Beijing" corresponding to the "origin slot", the key information "Shanghai" corresponding to the "destination slot", and the key information "today" corresponding to the "time slot" from the above request information. Finally, according to the key information corresponding to different slots, the shared parameter list exclusive to the flight booking task engine is updated.

[0110] In the embodiment of the present application, the above example is still used. The user first enters the request information of "booking a flight from Beijing to Shanghai today" in the human-computer interaction system, and generates the above Figure 7The shared parameter list shown. Then the user enters the request information "How is the weather over there" again in the human-computer interaction system, and it can be found that the request information belongs to the weather query task engine for processing. Then the weather query task engine can extract the key information corresponding to the "location slot" and "time slot" respectively from the request information entered by the user. It can be seen that the key information "over there" extracted for the "location slot" is reference information, and the key information that cannot be extracted for the "time slot", that is, the "time slot" is missing information. In an embodiment of the present application, it can be set that both the "missing information" and the "reference information" do not meet the conditions. At this time, the following method can be used to obtain the target key information:

[0111] Obtain the first vertical domain corresponding to the weather query task engine;

[0112] A second vertical domain whose correlation with the first vertical domain is greater than a preset threshold is obtained.

[0113] Among them, the correlation between the first vertical domain and the second vertical domain can be obtained by clustering historical data.

[0114] Obtain the second task engine corresponding to the second vertical domain.

[0115] The target key information is obtained from the shared parameter list exclusively owned by the second task engine.

[0116] In this application, the second task engine can be set as a flight booking task engine. Then, in the above Figure 7 In the shared parameter list shown, obtain the key information that meets the conditions.

[0117] For example, in one example of the present application, Figure 7 In the shared parameter list shown, query the key information that meets the conditions corresponding to the "location slot" in the weather task engine. Figure 7 It can be seen that "Shanghai" is the key information that meets the conditions corresponding to the "location slot" in the weather query task engine. Figure 7 In the shared parameter list shown in the figure, query the key information corresponding to the "time slot" of the weather task engine. Figure 7 It can be seen that "today" is the key information that meets the conditions corresponding to the "time slot" in the weather query task engine.

[0118] From the above analysis, it can be seen that the first shared parameter list and the second shared parameter list both store the corresponding relationship between the second slot and the target key information. In the embodiment of the present application, the key information corresponding to the second slot is unique and updateable.

[0119] In an example of the present application, the key information corresponding to the second slot can be updated in the following manner: the server receives third request information input by the user, and the third request information is responsible for the second task engine; the server extracts the key information corresponding to the second slot of the second task engine in the third request information; the server updates the target key information corresponding to the second slot in the correspondence between the second slot and the target key information in the shared parameter list based on the key information corresponding to the second slot extracted in the third request information.

[0120] For the first and second shared parameter lists mentioned above, such as Figure 8 As shown, the present application provides another process of information processing, including:

[0121] exist Figure 8 In the process shown, a three-round dialogue between a user and a human-computer interaction system is taken as an example for detailed description:

[0122] First round of dialogue: The user inputs the request information "How is the weather in Beijing today" to the human-computer interaction system. The human-computer interaction system can identify the intent of the request information input by the user and determine that the request information belongs to the weather query task engine for processing. The location slot of the weather query task engine can extract the key information "Beijing" from the above request information. The time slot of the weather query task engine can extract the key information "today" from the above request information. The final generated historical parameter list can be seen in Table 1 below.

[0123] User ID intention time Place *** Check the weather today Beijing

[0124] Table 1

[0125] Second round of dialogue: The user continues to input the request information of "book a flight from Beijing to Buenos Aires tomorrow" to the human-computer interaction system. Similarly, the human-computer interaction system can identify the user's request information and determine that the request information belongs to the ticket booking task engine. Then the ticket booking task engine can extract the key information "Beijing" corresponding to the "origin slot", the key information "Buenos Aires" corresponding to the "destination slot" and the key information "tomorrow" corresponding to the time slot from the request information. Finally, the generated historical parameter list can be seen in Table 2 below.

[0126] User ID intention Departure destination time *** Book a flight Beijing Buenos Aires tomorrow

[0127] Table 2

[0128] In the embodiment of the present application, the historical parameter list shown in Table 1 and the historical parameter list shown in Table 2 can be stored in the first shared parameter list or in the second shared parameter list. If stored in the second shared parameter list, the historical parameter list shown in Table 1 can be a shared parameter list exclusively used by the weather query task engine, and the historical parameter list shown in Table 2 can be a shared parameter list exclusively used by the air ticket booking task engine.

[0129] The third round of dialogue: The user inputs the request information "What is the weather over there?" into the human-computer interaction system.

[0130] Step S801: Receive the request information of the third round of dialogue input by the user, "How is the weather over there?"

[0131] Step S802: extract key information from the request information of the third round of dialogue.

[0132] The key information extracted can be found in Table 3 below.

[0133]

[0134]

[0135] Table 3

[0136] Step S803: Obtain the missing necessary information slot set L0 = {"time", "location"} in the weather query scenario.

[0137] Optionally, after step S803, the following steps may be included: step S804, step S805, step S806 and step S807.

[0138] Step S804: Determine whether there is a predefined rule for filling the information slot; if not, execute step S805; if yes, execute step S808.

[0139] The predefined rule refers to whether the shared parameter list can be used to fill the information slot;

[0140] Step S805: Determine whether the missing information slot can use the sensor to supplement the key information. If yes, execute step S806; otherwise, execute step S807;

[0141] Step S806: Fill in "location information" with sensors.

[0142] Step S807: Prompt the user to input “location information”.

[0143] In the embodiment of the present application, the purpose of setting steps S804 to S807 is to set different methods for filling the information slot, such as using a shared parameter list method, a sensor method, or a user manual input method.

[0144] In the embodiment of the present application, step S808 may be directly executed after step S803, that is, the key information of the information slot may be filled directly by using a shared parameter list.

[0145] Step S808: According to the predefined rules, determine one by one whether the slots of L0 are predefined to a certain value in the shared parameter list during scene development, and if so, add the set L1 = {"time", "place"}.

[0146] Step S809: When L1 is not empty, a set L2 = {"place", "time"} is obtained according to the priority of each slot in L1.

[0147] Step S810: Query the user's historical "location" parameters in the shared parameter list according to the user ID.

[0148] Step S811: Determine whether the historical "location" parameter has a value; if there is no value, execute step S812; otherwise, execute step S813.

[0149] Step S812: Prompt the user to enter “location” information.

[0150] Step S813: Fill the value of the historical "location" parameter into the "location" slot.

[0151] In an embodiment of the present application, the “Destination: Buenos Aires” shown in Table 2 above may be filled into the “Location” slot to generate the key information shown in Table 4.

[0152] User ID intention time Place *** Check the weather ？ Buenos Aires

[0153] Table 4

[0154] Step S814: Query the user's historical "time" parameter in the shared parameter list according to the user ID.

[0155] Step S815: Determine whether the historical "time" parameter has a value. If it has a value, execute step S816; otherwise, execute step S817.

[0156] Step S816: Fill the value of the historical "time" parameter into the "time" slot.

[0157] In an embodiment of the present application, the "time: tomorrow" shown in the above Table 2 can be filled into the time slot to generate the key information shown in Table 5.

[0158] User ID intention time Place *** Check the weather tomorrow Buenos Aires

[0159] Table 5

[0160] Step S817: Prompt the user to enter “time” information.

[0161] Through the above method, it can be seen that in the embodiment of the present application, when key information that meets the conditions cannot be extracted from the request information input by the user, the user's historical conversation parameters can be used to obtain key information that meets the conditions, so that the user does not need to enter the request information again, the user experience is better, and the human-computer interaction efficiency is higher.

[0162] Same as above idea, Fig. 9 As shown, the present application provides an information processing device 900, which may be a terminal device or a server, etc., including:

[0163] The transceiver unit 901 is used to receive first request information input by a user;

[0164] It should be noted that the transceiver unit 901 may be a hardware device such as a transceiver, or a logic unit such as a data interface, which is not limited in the present application.

[0165] The processing unit 902 is used to identify the intent of the first request information, determine a first task engine responsible for the first request information, wherein a first slot is provided in the first task engine, extract key information from the first request information according to the first slot, and if key information cannot be extracted from the first request information according to the first slot, or if key information is extracted from the first request information according to the first slot and the extracted key information does not meet a condition, obtain target key information from the shared parameter list of the user;

[0166] Among them, the shared parameter list includes at least the correspondence between the second slot and the target key information, the second slot has the same slot type as the first slot, the second slot is a slot in the second task engine, and the first task engine is different from the second task engine.

[0167] For a detailed description of the transceiver unit 901 and the processing unit 902, please refer to the above Figure 3 The introduction of the information processing method shown will not be repeated here.

[0168] Same as above idea, Fig.10As shown, the embodiment of the present application also provides a structure of an information processing device 100, which can be specifically a terminal device or a server. Optionally, the information processing device 100 can be specifically a central control module in the server, or its functions are implemented by the central control module in the server; further optionally, the information processing device 100 can be specifically a central control module in the terminal device, or its functions are implemented by the central control module in the terminal device. Fig.10 As shown, the information processing device 100 may include a communication interface 101 and a processor 102. The information processing device 100 may also include a memory 103. The memory 103 may be disposed inside the information processing device 100 or outside the information processing device. Fig. 9 The processing unit 902 shown in FIG. 1 may be implemented by the processor 102. The transceiver unit 901 may be implemented by the communication interface 101. The processor 102 receives service data through the communication interface 101.

[0169] In the embodiment of the present application, the communication interface 101 may be a circuit, a bus, a transceiver or any other device that can be used for information exchange.

[0170] In the embodiment of the present application, the processor 102 may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and may implement or execute the disclosed Figure 3 , Figure 4 or Figure 8 The information processing method shown. A general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiment of the present application may be directly embodied as being executed by a hardware processor, or may be executed by a combination of hardware and software units in the processor. The program code executed by the processor 102 for implementing the above method may be stored in the memory 103. The memory 103 is coupled to the processor 102. The processor 102 may operate in conjunction with the memory 103. The memory 103 may be a non-volatile memory, such as a hard disk drive (HDD) or a solid-state drive (SSD), etc., or a volatile memory (volatile memory), such as a random access memory (RAM). The memory 103 is any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto.

[0171] The specific connection medium between the communication interface 101, the processor 102 and the memory 103 is not limited in the embodiment of the present application. Fig.10 In the embodiment, the memory 103, the processor 102 and the communication interface 101 are connected via a bus. Fig.10 The connections between the other components are shown in bold lines, which are only for illustration and are not intended to be limiting. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.10 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0172] Based on the above embodiments, the embodiments of the present application further provide a computer storage medium, in which a software program is stored, and when the software program is read and executed by one or more processors, the method provided in any one or more of the above embodiments can be implemented. The computer storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk, and other media that can store program codes.

[0173] Based on the above embodiments, the present application provides a computer program, which includes computer instructions. When the computer instructions are executed by a computer, the computer executes the method provided by any one or more of the above embodiments.

[0174] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0175] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0176] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0177] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0178] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. An information processing method, characterized in that: include: Receiving first request information input by a user; Performing intent recognition on the first request information, determining a first task engine responsible for the first request information, wherein a first slot is provided in the first task engine; extracting key information from the first request information according to the first slot; If no key information can be extracted from the first request information according to the first slot, or if key information is extracted from the first request information according to the first slot and the extracted key information does not meet the condition, obtaining target key information from the shared parameter list of the user; Among them, the shared parameter list is generated according to the historical conversation parameters of the user; the target key information corresponds to the second slot in the second task engine, the second slot has the same slot type as the first slot, and the first task engine is different from the second task engine.

2. The method according to claim 1, characterized in that The shared parameter list includes a correspondence between the second slot and the target key information.

3. The method according to claim 1, characterized in that The second task engine is determined by the context parameter of the user or the second task engine is determined according to the correlation between the first task engine and the second task engine.

4. The method according to claim 2, characterized in that: The shared parameter list also includes a correspondence between the first task engine and one or more task engines, and a correspondence between slots included in any two task engines having a corresponding relationship, wherein the one or more task engines include the second task engine; The target key information is obtained in the shared parameter list of the user, including: Determining a second task engine according to a correspondence between the first task engine and one or more task engines; According to the correspondence between the slots, determining, among the slots included in the second task engine included in the shared parameter list, a second slot that has a correspondence with the first slot of the first task engine; The target key information is determined according to the corresponding relationship between the second slot and the target key information.

5. The method according to claim 1, characterized in that The second task engine is used to be responsible for the second request information of the user, and the second request information and the first request information occur within a preset time.

6. The method according to claim 1, characterized in that The target key information is obtained in the shared parameter list of the user, including: Determining, by using the context parameter of the user, a second task engine that is adjacent in time to the first task engine; The second task engine is used to be responsible for the second request information of the user, the second task engine is provided with a slot of the same type as the first slot, and the time proximity means that the occurrence time of the second request information is adjacent to the occurrence time of the first request information; Determine, in the slots of the second task engine, a second slot of the same type as the first slot; The target key information is determined according to the corresponding relationship between the second slot and the target key information.

7. The method according to claim 1, characterized in that The shared parameter list is a shared parameter list exclusively used by the second task engine; The target key information is obtained in the shared parameter list of the user, including: Determining the second task engine according to the correlation between the first task engine and the second task engine, wherein the correlation between the first task engine and the second task engine is greater than a preset threshold; Determining, according to the second task engine, a shared parameter list exclusively used by the second task engine; In the shared parameter list exclusively used by the second task engine, searching for a slot having the same slot type as the first slot as the second slot; The target key information is determined according to a corresponding relationship between the second slot and the target key information.

8. The method according to any one of claims 1 to 7, characterized in that: The key information that does not satisfy the condition includes reference information.

9. The method according to any one of claims 1 to 8, characterized in that: The method further comprises: Receiving third request information input by a user, where the second task engine is responsible for the third request information; Extracting key information corresponding to the second slot of the second task engine from the third request information; According to the key information corresponding to the second slot extracted in the third request information, the target key information corresponding to the second slot in the corresponding relationship between the second slot and the target key information in the shared parameter list is updated.

10. The method according to any one of claims 1 to 9, characterized in that: The slot type is time, place, action or person.

11. An information processing device, characterized in that: include: A transceiver unit, configured to receive first request information input by a user; a processing unit, configured to identify the intent of the first request information, determine a first task engine responsible for the first request information, wherein a first slot is provided in the first task engine, extract key information from the first request information according to the first slot, and if key information cannot be extracted from the first request information according to the first slot, or if key information is extracted from the first request information according to the first slot and the extracted key information does not meet a condition, obtain target key information from the shared parameter list of the user; Among them, the shared parameter list is generated according to the historical conversation parameters of the user; the target key information corresponds to the second slot in the second task engine, the second slot has the same slot type as the first slot, and the first task engine is different from the second task engine.

12. The device according to claim 11, characterized in that The shared parameter list includes a correspondence between the second slot and the target key information.

13. The device according to claim 11, characterized in that The second task engine is determined by the context parameter of the user or the second task engine is determined according to the correlation between the first task engine and the second task engine.

14. The device according to claim 12, characterized in that The shared parameter list also includes a correspondence between the first task engine and one or more task engines, and a correspondence between slots included in any two task engines having a corresponding relationship, wherein the one or more task engines include the second task engine; When the processing unit obtains the target key information in the shared parameter list of the user, it is specifically used to: Determining a second task engine according to a correspondence between the first task engine and one or more task engines; According to the correspondence between the slots, determining, among the slots included in the second task engine included in the shared parameter list, a second slot that has a correspondence with the first slot of the first task engine; The target key information is determined according to the corresponding relationship between the second slot and the target key information.

15. The device according to claim 11, characterized in that The second task engine is used to be responsible for the second request information of the user, and the second request information and the first request information occur within a preset time.

16. The device according to claim 11, characterized in that When the processing unit obtains the target key information in the shared parameter list of the user, it is specifically used to: Determining, by using the context parameter of the user, a second task engine that is adjacent in time to the first task engine; The second task engine is used to be responsible for the second request information of the user, the second task engine is provided with a slot of the same type as the first slot, and the time proximity means that the occurrence time of the second request information is adjacent to the occurrence time of the first request information; Determine, in the slots of the second task engine, a second slot of the same type as the first slot; The target key information is determined according to the corresponding relationship between the second slot and the target key information.

17. The device according to claim 11, characterized in that The shared parameter list is a shared parameter list exclusively used by the second task engine; The processing unit obtains target key information in the shared parameter list of the user, specifically for: Determining the second task engine according to the correlation between the first task engine and the second task engine, wherein the correlation between the first task engine and the second task engine is greater than a preset threshold; Determining, according to the second task engine, a shared parameter list exclusively used by the second task engine; In the shared parameter list exclusively used by the second task engine, searching for a slot having the same slot type as the first slot as the second slot; The target key information is determined according to a corresponding relationship between the second slot and the target key information.

18. The device according to any one of claims 11 to 17, characterized in that The key information that does not satisfy the condition includes reference information.

19. The device according to any one of claims 11 to 18, characterized in that The transceiver unit is further used for: Receiving third request information input by a user, where the second task engine is responsible for the third request information; The processing unit is also used to: extract the key information corresponding to the second slot of the second task engine in the third request information; and update the target key information corresponding to the second slot in the correspondence between the second slot and the target key information in the shared parameter list according to the key information corresponding to the second slot extracted in the third request information.

20. The device according to any one of claims 11 to 19, characterized in that The slot type is time, place, action or person.

21. An information processing device, characterized in that: including a processor and a memory; The memory is used to store computer-executable instructions; The processor is used to execute the computer-executable instructions stored in the memory, so that the information processing device performs the method according to any one of claims 1 to 10.

22. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the method according to any one of claims 1 to 10.

23. A computer program product, characterized in that The computer program product comprises computer instructions, and when the computer instructions are executed by a computer, the computer is caused to perform the method according to any one of claims 1 to 10.

Images