(19)
(11)EP 3 502 807 A1

(12)EUROPEAN PATENT APPLICATION
published in accordance with Art. 153(4) EPC

(43)Date of publication:
26.06.2019 Bulletin 2019/26

(21)Application number: 16912890.7

(22)Date of filing:  07.09.2016
(51)International Patent Classification (IPC): 
G05B 15/02(2006.01)
(86)International application number:
PCT/CN2016/000512
(87)International publication number:
WO 2018/032126 (22.02.2018 Gazette  2018/08)
(84)Designated Contracting States:
AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR
Designated Extension States:
BA ME
Designated Validation States:
MA MD

(30)Priority: 18.08.2016 CN 201610682959

(71)Applicant: Beijing VRV Software Corporation Limited
Beijing 100081 (CN)

(72)Inventors:
  • LIN, Hao
    Beijing 100081 (CN)
  • ZHONG, Li
    Beijing 100081 (CN)

(74)Representative: Kolster Oy Ab 
(Salmisaarenaukio 1) P.O. Box 204
00181 Helsinki
00181 Helsinki (FI)

  


(54)METHOD AND APPARATUS FOR ASSISTING HUMAN-COMPUTER INTERACTION


(57) Provided are a method and apparatus for assisting human-computer interaction, applied to a human-computer interaction auxiliary device connected with an executing device. The method comprises: acquiring a first control instruction, wherein the first control instruction comprises a voice control instruction and/or a text control instruction (S110); parsing the first control instruction (S120); generating a corresponding second control instruction according to the first control instruction, wherein the second control instruction is a preset control instruction that can be parsed by at least one of the executing device (S140); and searching for, according to the first control instruction, a target executing device corresponding to the first control instruction, and sending the second control instruction to the target executing device corresponding to the first control instruction (S150). In this way, an effect of assisting the executing device in parsing an instruction issued by a user is achieved without increasing investment in improving an information receiving interface or intelligence level of the executing device.




Description

Technical Field



[0001] The present disclosure relates to the field of information technology and the Internet of Things (loT), and in particular to a method and apparatus for assisting human-computer (man-machine) interaction.

Background Art



[0002] With the rapid development of the mobile Internet, the Internet of Things, and the artificial intelligence technology, more and more intelligence executing devices have the function of receiving digitalized control information, and parsing instructions of users, by receiving information such as voice or text and the like sent by the users, so as to carry out corresponding actions.

[0003] At present, the executing device can only understand some control instructions of standard forms, and when the control instruction issued by the user is an instruction of a non-standard form (e.g., "It is kind hot, turn on the air conditioner at 26°C"), or a voice instruction of a non-standard pronunciation (e.g., a voice instruction issued in a local dialect), the executing device will not be able to parse the instruction issued by the user, and cannot execute an action required by the user in time.

[0004] In the prior solutions, the user is alternatively required to issue an instruction of a standard form, so that it can be parsed by the executing device, thus, the user has to remember different instruction forms and use a standard pronunciation, which is very inconvenient in use, and reduces the user experience; or the device manufacturers are alternatively required to improve the intelligence level of the executing devices, and improve the capability of the executing devices to understand control instructions of non-standard forms, thus it is necessary to increase a large amount of capital investment to improve the executing devices.

[0005] Therefore, how to provide an economic and effective method to assist the executing device in parsing the control instruction issued by the user, has become an urgent problem to be solved by those skilled in the art.

Summary



[0006] In order to overcome the above-mentioned shortcomings in the prior art, the technical problem to be solved by the present disclosure is to provide a method and apparatus for assisting human-computer interaction, which are independent from an executing device and capable of assisting the executing device in parsing a control instruction issued by a user.

[0007] Regarding to the method, the present disclosure provides a method for assisting human-computer interaction, which is applied to a human-computer interaction assisting device connected to an executing device, the method comprises:

acquiring a first control instruction, wherein the first control instruction includes a voice control instruction and/or a text control instruction;

parsing the first control instruction;

generating a corresponding second control instruction based on the first control instruction, wherein the second control instruction is a preset control instruction that can be parsed by at least one of the executing devices;

searching for a target executing device corresponding to the first control instruction based on the first control instruction, and sending the second control instruction to the target executing device the first control instruction corresponding thereto.



[0008] Further, in the method for assisting human-computer interaction described above, the step of acquiring a first control instruction comprises:

receiving a request for assisted parsing sent by the executing device when it fails to parse the first control instruction;

acquiring the first control instruction which fails to be parsed and is sent by the executing device.



[0009] Further, in the method for assisting human-computer interaction described above, the method further comprises:
sending a parsing failure notification, when the human-computer interaction assisting device fails to parse the first control instruction.

[0010] Further, in the method for assisting human-computer interaction described above, the step of acquiring a first control instruction comprises:

acquiring an interactive information between different users, or between a user and the executing device, or between the different executing devices;

parsing and extracting the first control instruction contained in the interactive information.



[0011] Further, in the method for assisting human-computer interaction described above, the step of generating a corresponding second control instruction based on the first control instruction comprises:

acquiring a key field in the first control instruction, the key field includes a target executing device, an action to be executed, and an execution parameter;

generating the second control instruction based on the key field.



[0012] The present disclosure further provides a method for assisting human-computer interaction, which is applied to an executing device and a human-computer interaction assisting device connected to each other, the method comprises:

acquiring a first control instruction by the human-computer interaction assisting device, wherein the first control instruction includes a voice control instruction or a text control instruction of a language form;

parsing the first control instruction;

generating a corresponding second control instruction based on the first control instruction, wherein the second control instruction is a preset control instruction that can be parsed by at least one of the executing devices;

searching for a target executing device corresponding to the first control instruction based on the first control instruction, and sending the second control instruction to the target executing device the first control instruction corresponding thereto;

responding to the second control instruction, and executing an action corresponding to the second control instruction by the executing device.



[0013] Further, in the method for assisting human-computer interaction described above, the step of acquiring a first control instruction by the human-computer interaction assisting device comprises:

obtaining, by the executing device, the first control instruction sent by a user;

sending a request for assisted parsing to the human-computer interaction assisting device when the parsing of the first control instruction is unsuccessful;

receiving the request for assisted parsing sent by the executing device when it fails to parse the first control instruction;

acquiring the first control instruction which fails to be parsed and is sent by the executing device.



[0014] Further, in the method for assisting human-computer interaction described above, the method further comprises:
sending a parsing failure notification to the user and the executing device, when the human-computer interaction assisting device fails to parse the first control instruction.

[0015] Further, in the method for assisting human-computer interaction described above, the step of acquiring a first control instruction by the human-computer interaction assisting device comprises:

acquiring, by the human-computer interaction assisting device, an interactive information between different users, or between a user and the executing device, or between the different executing devices;

parsing and extracting the first control instruction contained in the interactive information.



[0016] Regarding to the apparatus, the present disclosure provides an apparatus for assisting human-computer interaction, which is applied to a human-computer interaction assisting device connected to an executing device, the apparatus comprises:

a first control instruction acquisition module, configured to acquire a first control instruction, wherein the first control instruction includes a voice control instruction and/or a text control instruction;

a parsing module, configured to parse the first control instruction;

a second control instruction generating module, configured to generate a corresponding second control instruction based on the first control instruction, wherein the second control instruction is a preset control instruction that can be parsed by at least one of the executing devices; and

a second control instruction sending module, configured to search for a target executing device corresponding to the first control instruction based on the first control instruction, and to send the second control instruction to the target executing device the first control instruction corresponding thereto.



[0017] Compared with the prior art, the present disclosure has the following beneficial effects:
In a method and apparatus for assisting human-computer interaction according to the present disclosure, a human-computer interaction assisting device, independent from the executing device, is disposed, such that the first control instruction that cannot be understood by the executing device is parsed by the human-computer interaction assisting device, and a second control instruction that can be understood by the executing device is generated and sent to the executing device. In this way, an effect of assisting the executing device in parsing an instruction issued by a user is achieved without increasing investment in improving an information receiving interface or intelligence level of the executing device. The method of the present disclosure is simple and easily feasible, effectively saves the cost, and improves the user experience.

Brief Description of Drawings



[0018] In order to more clearly illustrate technical solutions of embodiments of the present disclosure, drawings required for use in the embodiments will be introduced briefly below, it is to be understood that the drawings below are merely illustrative of some embodiments of the present disclosure, and therefore should not be considered as limiting the scope of the disclosure, it would be understood by those of ordinary skill in the art that other relevant drawings could also be obtained from these drawings without any inventive effort.

FIG. 1 is a schematic diagram of an application environment according to an embodiment of the present disclosure;

FIG. 2 is a structural block diagram of a human-computer interaction assisting device according to an embodiment of the present disclosure;

FIG. 3 is a first schematic flowchart of a method for assisting human-computer interaction according to an embodiment of the present disclosure;

FIG. 4 is a first schematic flowchart of sub-steps of step S110 of the present disclosure;

FIG. 5 is a second schematic flowchart of sub-steps of the step S110 of the present disclosure;

FIG. 6 is a second schematic flowchart of a method for assisting human-computer interaction according to an embodiment of the present disclosure;

FIG. 7 is a schematic flowchart of sub-steps of step S140 of the present disclosure;

FIG. 8 is a third schematic flowchart of a method for assisting human-computer interaction according to an embodiment of the present disclosure;

FIG. 9 is a first schematic flowchart of sub-steps of step S210 of the present disclosure;

FIG. 10 is a second schematic flowchart of sub-steps of the step S210 of the present disclosure;

FIG. 11 is a fourth schematic flowchart of a method for assisting human-computer interaction according to an embodiment of the present disclosure; and

FIG. 12 is a structural block diagram of a human-computer interaction assisting apparatus according to an embodiment of the present disclosure.



[0019] Reference numerals in the above figures are corresponding to the following terms:
Human-computer interaction assisting device 100
Human-computer interaction assisting apparatus 110
First control instruction acquisition module 111
Parsing module 112
Second control instruction generating module 113
Second control instruction sending module 114
Memory 120
Processor 130
Communication unit 140
Executing Device 200
Network 300

Detailed Description of Embodiments



[0020] In order to make the objects, technical solutions, and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described below clearly and completely with reference to the drawings of the embodiments of the present disclosure. It is apparent that the embodiments to be described are some, but not all of the embodiments of the present disclosure. Generally, the components of the embodiments of the present disclosure, as described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations.

[0021] Thus, the following detailed description of the embodiments of the present disclosure, as represented in the figures, is not intended to limit the scope of the present disclosure as claimed, but is merely representative of selected embodiments of the present disclosure. All the other embodiments obtained by those of ordinary skill in the art in light of the embodiments of the present disclosure without inventive efforts would fall within the scope of the present disclosure as claimed.

[0022] It should be noted that similar reference numerals and letters refer to similar items in the following figures, and thus once an item is defined in one figure, it may not be further defined or explained in the following figures.

[0023] In the description of the present disclosure, it should be noted that terms such as "first", "second", and "third" are used for distinguishing the description, and should not be understood as an indication or implication of relative importance.

[0024] In the description of the present disclosure, it should also be noted that terms "provided", "mounted", "coupled", and "connected" should be understood broadly unless otherwise expressly specified or defined. For example, connection may be fixed connection or detachable connection or integral connection, may be mechanical connection or electric connection, or may be direct coupling or indirect coupling via an intermediate medium or internal communication between two elements. The specific meanings of the above-mentioned terms in the present disclosure could be understood by those of ordinary skill in the art according to specific situations.

[0025] FIG. 1 shows a schematic diagram showing an interaction of communication between a human-computer interaction assisting device 100 and at least one executing device 200 according to a preferable embodiment of the present disclosure. The human-computer interaction assisting device 100 may communicate with the executing device 200 through a network 300, to implement data communication or interaction between the human-computer interaction assisting device 100 and the executing device 200. The network 300 may be, but is not limited to, a wired network or a wireless network. The network 300 may be, but is not limited to, a local area network or the Internet.

[0026] FIG. 2 shows a schematic block diagram of a human-computer interaction assisting device 100 shown in FIG. 1. The human-computer interaction assisting device 100 comprises a human-computer interaction assisting apparatus 110, a memory 120, a processor 130, and a communication unit 140.

[0027] The elements of the memory 120, the processor 130, and the communication unit 140 are electrically connected directly or indirectly to each other, to implement data transmission or interaction. For example, these elements may be electrically connected to each other via one or more communication buses or signal lines. The human-computer interaction assisting apparatus 110 includes at least one software functional module that may be stored in the memory 120 in the form of software or firmware, or solidified in an operating system (OS) of the human-computer interaction assisting device 100. The processor 130 is configured to execute an executable module stored in the memory 120, such as a software functional module, a computer program, and so on, included in the human-computer interaction assisting apparatus 110.

[0028] Here, the memory 120 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electric erasable programmable read-only memory (EEPROM), or the like. Here, the memory 120 is configured to store a program, and the processor 130 executes the program after receiving an execution instruction. The communication unit 140 is configured to establish a communication connection between the human-computer interaction assisting device 100 and the executing device 200 through the network 300, and is configured to send and receive data through the network 300.

[0029] FIG. 3 shows a schematic flowchart of a method for assisting human-computer interaction which is applied to a human-computer interaction assisting device 100 shown in FIG. 1, the method comprises the following steps.

[0030] In step S110, the human-computer interaction assisting device 100 acquires a first control instruction, wherein the first control instruction includes a voice control instruction and/or a text control instruction.

[0031] Specifically, referring to FIG. 4, in a first example of the present embodiment, the step S110 may comprise the following sub-steps:
in sub-step S111, a request, for assisted parsing sent by the executing device 200 when it fails to parse the first control instruction, is received.

[0032] In this example, the executing device 200 receives the first control instruction sent by a user, wherein the user may send the first control instruction by means of sending a voice instruction directly to the executing device 200, or sending a voice or text instruction to the executing device 200 through a user terminal. When the executing device 200 fails to parse the first control instruction, a request for assisted parsing is sent to the human-computer interaction assisting device 100.

[0033] In sub-step S112, the first control instruction, which fails to be parsed and is sent by the executing device 200, is acquired.

[0034] After receiving the request for assisted parsing, the human-computer interaction assisting device 100 acquires, from the executing device 200, a first control instruction that fails to be parsed by the same.

[0035] Specifically, referring to FIG. 5, in a second example of the present embodiment, the step S110 may comprise the following sub-steps:
in sub-step S113, an interactive information between different users, or between a user and the executing device, or between the different executing devices is acquired.

[0036] In this example, an instant communication group is formed, through the network 300, between different users, and/or between a user and the executing device, and/or between the different executing devices, and the human-computer interaction assisting device 100 acquires an interactive information in this group. Here, the interactive information may be, but is not limited to, a voice information or a text information.

[0037] In sub-step S114, the first control instruction contained in the interactive information is parsed and extracted.

[0038] The human-computer interaction assisting device 100 sifts out and extracts, from the interactive information, the first control instruction contained therein.

[0039] In step S120, the first control instruction is parsed.

[0040] Specifically, in the present embodiment, the human-computer interaction assisting device 100 parses the first control instruction by a speech recognition model and/or a semantic analysis model. Here, the speech recognition model includes, but is not limited to, a hidden Markov (HMM) model and an artificial neural network model; the semantic analysis model includes, but is not limited to, a word-dependent (WD) model, a concept-dependent (CD) model, and a core-dependent (KD) model.

[0041] In the first example of the present embodiment, referring to FIG. 6, the method may further comprise step S130.

[0042] In step S130, a parsing failure notification is sent when the human-computer interaction assisting device 100 fails to parse the first control instruction.

[0043] When the human-computer interaction assisting device 100 fails to parse the first control instruction, a notification of the parsing failure is sent to the user or the user terminal, to prompt the user to re-issue an instruction.

[0044] In step S140, a corresponding second control instruction is generated based on the first control instruction, wherein the second control instruction is a preset control instruction that can be parsed by at least one of the executing devices 200.

[0045] Specifically, referring to FIG. 7, the step S140 may comprise the following sub-steps.

[0046] In sub-step S141, a key field in the first control instruction is acquired, where the key field may include, but is not limited to, a target executing device, an action to be executed, and an execution parameter.

[0047] In the present embodiment, the human-computer interaction assisting device 100 may set different kinds of extraction of key fields, for different types of executing devices connected thereto (e.g., smart home appliances, smart wearable devices, and remote monitoring cameras, etc.).

[0048] In sub-step S142, the second control instruction is generated based on the key field.

[0049] The human-computer interaction assisting device 100 generates the second control instruction, which matches the information in the key field, based on the type of a target executing device specified in the key field, using a corresponding instruction format.

[0050] In step S150, a search is performed for a target executing device 200 corresponding to the first control instruction based on the first control instruction, and the second control instruction is sent to the target executing device 200 the first control instruction corresponding thereto.

[0051] The human-computer interaction assisting device 100 sends the parsed second control instruction to the executing device 200 based on the executing device 200 of the first control instruction.

[0052] Referring to FIG. 8, the present embodiment further provides a method for assisting human-computer interaction, the method comprises the following steps.

[0053] In step S210, the human-computer interaction assisting device 100 acquires a first control instruction, wherein the first control instruction includes a voice control instruction or a text control instruction in a language form.

[0054] Referring to FIG. 9, in a third example of the present embodiment, the step S210 may comprise the following sub-steps:

sub-step S211 of obtaining, by the executing device 200, the first control instruction sent by a user;

sub-step S212 of sending a request for assisted parsing to the human-computer interaction assisting device 100 when the parsing of the first control instruction is unsuccessful;

sub-step S213 of receiving the request for assisted parsing sent by the executing device 200 when it fails to parse the first control instruction; and

sub-step S214 of acquiring the first control instruction which fails to be parsed and is sent by the executing device 200.



[0055] Referring to FIG. 10, in a fourth example of the present embodiment, the step S210 may comprise the following sub-steps:

sub-step S215 of acquiring, by the human-computer interaction assisting device 100, an interactive information between different users, or between a user and the executing device 200, or between the different executing devices 200; and

sub-step S216 of parsing and extracting the first control instruction contained in the interactive information.



[0056] In step S220, the first control instruction is parsed.

[0057] Referring to FIG. 11, in the third example of the present embodiment, the method further comprises step S230.

[0058] In step S230, a parsing failure notification is sent to the user and the executing device 200, when the human-computer interaction assisting device 100 fails to parse the first control instruction.

[0059] In step S240, a corresponding second control instruction is generated based on the first control instruction, wherein the second control instruction is a preset control instruction that can be parsed by at least one of the executing devices 200.

[0060] In step S250, a search is performed for a target executing device 200 corresponding to the first control instruction based on the first control instruction, and the second control instruction is sent to the target executing device 200 the first control instruction corresponding thereto.

[0061] In step S260, the executing device 200 responds to the second control instruction, and executes an action corresponding to the second control instruction.

[0062] Referring to FIG. 12, the present embodiment further provides a human-computer interaction assisting apparatus 110, which is applied to a human-computer interaction assisting device 100 connected to at least one executing device 200, the apparatus comprises:

a first control instruction acquisition module 111, configured to acquire a first control instruction, wherein the first control instruction includes a voice control instruction and/or a text control instruction;

a parsing module 112, configured to parse the first control instruction;

a second control instruction generating module 113, configured to generate a corresponding second control instruction based on the first control instruction, wherein the second control instruction is a preset control instruction that can be parsed by at least one of the executing devices 200; and

a second control instruction sending module 114, configured to search for a target executing device 200 corresponding to the first control instruction based on the first control instruction, and to send the second control instruction to the target executing device 200 the first control instruction corresponding thereto.



[0063] In summary, in a method and apparatus for assisting human-computer interaction according to the present disclosure, the human-computer interaction assisting device 100, independent from the executing device 200, is disposed, such that the first control instruction that cannot be understood by the executing device 200 is parsed by the human-computer interaction assisting device 100, and a second control instruction that can be understood by the executing device 200 is generated and sent to the executing device 200. In this way, an effect of assisting the executing device 200 in parsing an instruction issued by a user is achieved without increasing investment in improving an information receiving interface or intelligence level of the executing device 200. The method of the present disclosure is simple and easily feasible, effectively saves the cost, and improves the user experience.

[0064] The above description is merely illustrative of preferred embodiments of the present disclosure and is not intended to limit the present disclosure, it would be understood by those skilled in the art that various modifications and variations can be made to the present disclosure. Any modifications, equivalent alternatives, improvements and so on made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.


Claims

1. A method for assisting human-computer interaction, which is applicable to a human-computer interaction assisting device connected to an executing device, characterized in that the method comprises:

acquiring a first control instruction, wherein the first control instruction comprises a voice control instruction and/or a text control instruction;

parsing the first control instruction;

generating a corresponding second control instruction based on the first control instruction, wherein the second control instruction is a preset control instruction that can be parsed by at least one of the executing devices;

searching for a target executing device corresponding to the first control instruction based on the first control instruction, and sending the second control instruction to the target executing device the first control instruction corresponding thereto.


 
2. The method for assisting human-computer interaction according to claim 1, wherein the step of acquiring a first control instruction comprises:

receiving a request for assisted parsing sent by the executing device when the executing device fails to parse the first control instruction; and

acquiring the first control instruction which is fail to be parsed and is sent by the executing device.


 
3. The method for assisting human-computer interaction according to claim 2, wherein the method further comprises:
sending a parsing failure notification when the human-computer interaction assisting device fails to parse the first control instruction.
 
4. The method for assisting human-computer interaction according to claim 1, wherein the step of acquiring a first control instruction comprises:

acquiring an interactive information between different users, or between a user and the executing device, or between the different executing devices; and

parsing and extracting the first control instruction contained in the interactive information.


 
5. The method for assisting human-computer interaction according to claim 1, wherein the step of generating a corresponding second control instruction based on the first control instruction comprises:

acquiring a key field in the first control instruction, wherein the key field comprises a target executing device, an action to be executed, and an execution parameter; and

generating the second control instruction based on the key field.


 
6. A method for assisting human-computer interaction, which is applicable to an executing device and a human-computer interaction assisting device connected to each other, wherein the method comprises:

acquiring a first control instruction by the human-computer interaction assisting device, wherein the first control instruction comprises a voice control instruction or a text control instruction in a language form;

parsing the first control instruction;

generating a corresponding second control instruction based on the first control instruction, wherein the second control instruction is a preset control instruction that can be parsed by at least one of the executing devices;

searching for a target executing device corresponding to the first control instruction based on the first control instruction, and sending the second control instruction to the target executing device the first control instruction corresponding thereto; and

responding to the second control instruction, and executing an action corresponding to the second control instruction by the executing device.


 
7. The method for assisting human-computer interaction according to claim 6, wherein the step of acquiring a first control instruction by the human-computer interaction assisting device comprises:

obtaining, by the executing device, the first control instruction sent by a user;

sending a request for assisted parsing to the human-computer interaction assisting device when the parsing of the first control instruction is unsuccessful;

receiving the request for assisted parsing sent by the executing device when the executing device fails to parse the first control instruction; and

acquiring the first control instruction which is fail to be parsed and is sent by the executing device.


 
8. The method for assisting human-computer interaction according to claim 7, wherein the method further comprises:
sending a parsing failure notification to the user and the executing device when the human-computer interaction assisting device fails to parse the first control instruction.
 
9. The method for assisting human-computer interaction according to claim 6, wherein the step of acquiring a first control instruction by the human-computer interaction assisting device comprises:

acquiring, by the human-computer interaction assisting device, an interactive information between different users, or between a user and the executing device, or between the different executing devices; and

parsing and extracting the first control instruction contained in the interactive information.


 
10. An apparatus for assisting human-computer interaction, which is applicable to a human-computer interaction assisting device connected to an executing device, characterized in that the apparatus comprises:

a first control instruction acquisition module, configured to acquire a first control instruction, wherein the first control instruction comprises a voice control instruction and/or a text control instruction;

a parsing module, configured to parse the first control instruction;

a second control instruction generating module, configured to generate a corresponding second control instruction based on the first control instruction, wherein the second control instruction is a preset control instruction that can be parsed by at least one of the executing devices; and

a second control instruction sending module, configured to search for a target executing device corresponding to the first control instruction based on the first control instruction, and to send the second control instruction to the target executing device the first control instruction corresponding thereto.


 




Drawing





































Search report