CN113271383A - Voice number checking method and device - Google Patents
Voice number checking method and device Download PDFInfo
- Publication number
- CN113271383A CN113271383A CN202110533592.3A CN202110533592A CN113271383A CN 113271383 A CN113271383 A CN 113271383A CN 202110533592 A CN202110533592 A CN 202110533592A CN 113271383 A CN113271383 A CN 113271383A
- Authority
- CN
- China
- Prior art keywords
- name
- organization
- organization name
- user
- voice
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 230000008520 organization Effects 0.000 claims abstract description 310
- 230000007246 mechanism Effects 0.000 claims abstract description 133
- 239000000284 extract Substances 0.000 claims description 7
- 230000003993 interaction Effects 0.000 abstract description 13
- 206010063385 Intellectualisation Diseases 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 230000035558 fertility Effects 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
- H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
- H04M3/4931—Directory assistance systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1822—Parsing for meaning understanding
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
- H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
- H04M3/4936—Speech interaction details
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/527—Centralised call answering arrangements not requiring operator intervention
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Signal Processing (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a method and a device for voice number searching, wherein the method for voice number searching comprises the following steps: responding to voice directory assistance information input by a user received by the voice robot, extracting a first organization name from the voice directory assistance information, and if the first organization name does not exist in a plurality of preset organization name sets, judging whether a second organization name similar to the first organization name exists in the plurality of organization name sets or not; if a second organization name similar to the first organization name exists in the plurality of organization name sets, confirming whether the semantics of the first organization name and the second organization name are the same to the user; and if receiving a semantic identity instruction of the user, feeding back number information corresponding to the second mechanism name to the user, and enriching a mechanism name set according to the semantic identity instruction of the user so as to realize self-learning. By using the voice interaction mode, the difficulties of inaccurate directory inquiry information and digitalization and intellectualization of directory inquiry service are solved.
Description
Technical Field
The invention belongs to the technical field of intelligent voice directory assistance, and particularly relates to a voice directory assistance method and device.
Background
At present, the common number searching modes mainly comprise two types: firstly, the internet search is directly inquired, a user searches for numbers through an internet search engine, the returned result is wide in foot-plane, valuable information is difficult to locate quickly, the searching efficiency is low, and a lot of information does not have authenticity. The second is to dial a related hotline (e.g., 114) and the user asks the agent for the organization name that he wants to query.
If the seat is manual, the organization directory needs to be manually inquired and the telephone records in the directory are reported to the user, the manual seat processing mode has low efficiency, only one seat can be connected with one user each time, and if the seat needs to be served for 24 hours, the user needs to take work in turn, so the cost is high. If the seat is a robot, the inquiry result can be quickly broadcasted to the user after voice recognition, but various short names of the same mechanism cannot be flexibly processed, the self-learning capability is not provided, and the experience of voice interaction with the user can be greatly reduced.
Disclosure of Invention
An embodiment of the present invention provides a voice directory assistance method and apparatus, which are used to solve at least one of the above technical problems.
In a first aspect, an embodiment of the present invention provides a voice directory assistance method, including: responding to voice directory assistance information input by a user and received by a voice robot, extracting a first organization name from the voice directory assistance information, and inquiring whether the first organization name exists in a plurality of preset organization name sets or not; if the first organization name exists in the plurality of organization name sets, feeding back number information corresponding to the first organization name to the user; if the first mechanism name does not exist in the preset mechanism name sets, the voice robot judges whether a second mechanism name similar to the first mechanism name exists in the mechanism name sets or not; if a second organization name similar to the first organization name exists in the plurality of organization name sets, confirming whether the semantics of the first organization name and the second organization name are the same to the user; and if receiving the instruction with the same semantic meaning of the user, the voice robot feeds back number information corresponding to the second mechanism name to the user.
In a second aspect, an embodiment of the present invention provides a voice directory assistance device, including: the extraction program module is configured to respond to voice directory assistance information input by a user and received by the voice robot, extract a first organization name from the voice directory assistance information and inquire whether the first organization name exists in a plurality of preset organization name sets or not; a presence processing program module configured to feed back number information corresponding to the first organization name to the user if the first organization name exists in the plurality of organization name sets; the similarity judgment program module is configured to judge whether a second mechanism name similar to the first mechanism name exists in the plurality of mechanism name sets or not by the voice robot if the first mechanism name does not exist in the plurality of preset mechanism name sets; a confirmation program module configured to confirm to the user whether a second organization name similar to the first organization name exists in the plurality of organization name sets, the first organization name and the second organization name being semantically identical; and the feedback program module is configured to feed back number information corresponding to the second mechanism name to the user by the voice robot if the instruction that the semantics of the user are the same is received.
In a third aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the method of the first aspect.
The method and the device provided by the application solve the problems of inaccurate directory number searching information, incapability of flexibly processing short-name voice robots and digitalization and intellectualization of directory number searching services in a voice interaction mode through the technologies of voice recognition, natural language understanding, semantic similarity matching and the like. By using the voice directory inquiry method, a user can inquire a certain mechanism number more quickly and more accurately.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
Fig. 1 is a flowchart of a voice directory assistance method according to an embodiment of the present invention;
fig. 2 is a flowchart of another voice directory assistance method according to an embodiment of the present invention;
fig. 3 is a flowchart of another voice directory assistance method according to an embodiment of the present invention;
fig. 4 is a flowchart of another voice directory assistance method according to an embodiment of the present invention;
fig. 5 is a flowchart of another voice directory assistance method according to an embodiment of the present invention;
fig. 6 is a flowchart of another voice directory assistance method according to an embodiment of the present invention;
FIG. 7 is a flow chart of a directory look-up scheme storage structure according to an embodiment of the present invention;
FIG. 8 is a block diagram of a solution architecture provided by an embodiment of the present invention;
FIG. 9 is a flowchart illustrating an example of an actual dialog of a voice directory assistance scheme according to an embodiment of the present invention;
FIG. 10 is a flow chart of a software implementation provided in accordance with an embodiment of the present invention;
fig. 11 is a block diagram of a voice directory assistance device according to an embodiment of the present invention;
fig. 12 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, which shows a flowchart of an embodiment of the voice directory assistance method of the present application, the voice directory assistance method of the present embodiment may be applied to a terminal with communication or real-time voice conversation functions, such as a smart phone, a tablet, a computer, etc., for example, when a number of an organization needs to be searched, the number is directly searched by using the above-mentioned device through a voice robot, without time and geographical limitation, and is convenient and fast.
As shown in fig. 1, in step 101, in response to a voice directory assistance message input by a user being received by a voice robot, extracting a first organization name from the voice directory assistance message, and querying whether the first organization name exists in a preset plurality of organization name sets;
in step 102, if the first organization name exists in the plurality of organization name sets, feeding back number information corresponding to the first organization name to the user;
in step 103, if the first mechanism name does not exist in the preset mechanism name sets, the voice robot determines whether a second mechanism name similar to the first mechanism name exists in the mechanism name sets;
in step 104, if a second organization name similar to the first organization name exists in the plurality of organization name sets, confirming to the user whether the first organization name and the second organization name are semantically the same;
in step 105, if the instruction of the same semantic meaning of the user is received, the voice robot feeds back number information corresponding to the second organization name to the user.
In this embodiment, for step 101, in response to the voice directory assistance information received by the voice robot from the user, the voice directory assistance device extracts the first organization name from the voice directory assistance information, queries whether the first organization name exists in a preset plurality of organization name sets, for example, the voice information input by the user is an instruction of "query for phone number of shanghai transportation university", and the voice robot extracts the first organization name "shanghai transportation university", and searches whether information of organization names related to "shanghai transportation university" exists from a preset database organization name set.
Then, for step 102, if the first organization name exists in the plurality of organization name sets, feeding back number information corresponding to the first organization name to the user, for example, the voice robot finds that "shanghai transportation university" exists in an organization set related to "shanghai transportation university", and the voice robot broadcasts the number information of "shanghai transportation university" to the user.
Then, for step 103, if the first mechanism name does not exist in the preset mechanism name sets, the voice robot determines whether a second mechanism name similar to the first mechanism name exists in the mechanism name sets, for example, if the user inputs "shanghai jiu", the voice robot does not find the mechanism related to "shanghai jiu" in the mechanism set, and the voice robot finds the mechanism name similar to "shanghai jiu" according to the determination and analysis.
Then, in step 104, if a second organization name similar to the first organization name exists in the plurality of organization name sets, confirming to the user whether the first organization name and the second organization name are semantically the same, for example, the voice machine finds an organization name set of "shanghai transportation university" similar to "shanghai transportation," and the voice machine reports to the user whether the organization inquired about "shanghai transportation university" is present.
Finally, in step 105, if the instruction that the semantics of the user are the same is received, the voice robot feeds back the number information corresponding to the name of the second organization to the user, for example, the voice robot receives the instruction that the user is "yes", and the voice robot broadcasts the number information of the searched "shanghai transportation university" organization to the user. In some optional embodiments, the voice robot may enrich the organization name collection according to the confirmation feedback of the user, so as to realize self-learning, for example, after the user feeds back that the semanteme is the same or similar, the semanteme name (for example, "Shanghai Merge") inquired by the user can be added into the organization name collection, so as to enrich the organization name collection, so as to realize self-learning. In still other embodiments, if the user inquires "turn" and inquires about a plurality of organization names with the same or similar semantics as "turn" such as "beijing transportation university" and "shanghai transportation university", at this time, even if the user selects or confirms "shanghai transportation university" later, it is not suitable to directly add "turn" to the organization name set of "shanghai transportation university", because the abbreviation may also correspond to "beijing transportation university" in the subsequent organization name inquiry, and if the abbreviation is directly added to the organization name set of "shanghai transportation university", it may cause that the abbreviation may directly correspond to "shanghai transportation university" when the abbreviation is used for inquiry later, and further may seriously affect the accuracy of the inquiry and the user experience.
According to the method, similar or identical mechanism names are searched in the set according to the preset mechanism name set through the voice interaction mode of the user and the voice robot, number information corresponding to the mechanism names is fed back to the user, further, if the mechanism names which are not in the set are short, the mechanism names can be stored in the corresponding mechanism name full-name set, the problem that the time limit of 24-hour on duty is difficult to guarantee by manual service is solved, meanwhile, the labor cost is avoided, and the working efficiency is improved.
Further referring to fig. 2, a flowchart of another voice directory assistance method according to an embodiment of the present invention is shown, where the flowchart mainly includes a step further defined by a flow of "the voice robot determines whether a second organization name similar to the first organization name exists in the plurality of organization name sets" in step 103 "in fig. 1.
As shown in fig. 2, in step 201, the voice robot calculates semantic similarity between the abbreviation in the plurality of organization name sets and the first organization name;
in step 202, if there is a similarity between a second organization name in at least one organization name set and the first organization name, which is greater than or equal to the semantic similarity threshold, it is determined that there is a second organization name similar to the first organization name in the plurality of organization name sets.
In this embodiment, for step 201, the voice robot calculates semantic similarity between the abbreviation in the multiple mechanism name sets and the first mechanism name, for example, the voice robot calculates semantic similarity between the abbreviation in the originally set mechanism name set and the mechanism name or abbreviation that is similar to the mechanism name or abbreviation that the user needs to query.
Finally, for step 202, if there is a similarity between the second organization name in at least one organization name set and the first organization name in the voice robot search result and the semantic similarity threshold value or more, confirming that a second organization name similar to the first organization name exists in the plurality of organization name sets, for example, the voice robot finds the organization name of Shanghai transportation university in the organization name set prestored in the database, calculating to obtain that the similarity between the organization name of 'Shanghai Jie' to be searched by the user and the existing organization name in the collection of the organization name of 'Shanghai transportation university' is more than or equal to a preset similarity threshold through a preset threshold, it is confirmed that there is an organization name similar to the organization name to be queried by the user in the "shanghai transportation university" organization name set.
According to the method, whether the mechanism name similar to the mechanism name required to be searched by the user exists in the mechanism names stored in the system or not is judged through the preset semantic identity threshold, and the mechanism name similar to the mechanism name required to be searched by the user can be quickly found out under the condition that the same mechanism name does not exist.
In some optional embodiments, the similarity between a plurality of second organization names and the first organization name is greater than or equal to the semantic similarity threshold, only one second organization name with the highest similarity is obtained, for example, the result found by the voice robot is "shanghai transportation university", "shanghai jungdong", "transportation university", and a preset semantic similarity threshold is calculated with the "shanghai jungdong" that the user needs to find, and the organization name with the highest similarity is obtained, for example, if the similarity between "shanghai jungdong" and the "shanghai jungdong" that the user needs to find forever is the highest, only "shanghai jungdong" is obtained, so that the user is prevented from confirming too many similar organization names, which greatly affects the user-ground interaction experience. According to the method, the plurality of mechanism names and the mechanism names which are similar to the mechanism name needing to be searched by the user are searched through the voice robot, and only one mechanism name with the highest similarity is selected according to the preset threshold, so that the problem that the plurality of similar mechanism names are difficult to select is solved.
In some optional embodiments, each of the plurality of organization name sets has a complete organization name uniquely corresponding to the organization name set, and the organization name set includes an abbreviation of the complete organization name and a full name of the complete organization name, for example, the organization name of "shanghai transportation university" is changed to include "shanghai transportation university", "shanghai transportation university" and the like in the set, and each set must have a full name of the organization name, such as "shanghai transportation university", wherein the organization name set of "shanghai transportation university" may further include its abbreviation of "shanghai transportation university", "shanghai transportation university" and the like. According to the method, the complete mechanism name must be provided in the preset mechanism name set, so that the voice robot searches the mechanism name set which needs to be searched by the user more quickly and accurately.
Please refer to fig. 3, which shows a flowchart of a voice directory assistance method according to another embodiment of the present invention, and the flowchart mainly refers to a flowchart of a step defined further by the flow of step 105 "the voice robot feeds back number information corresponding to the second organization name to the user" in the flowchart of fig. 1.
As shown in fig. 3, in step 301, a complete organization name of the organization name set corresponding to the second organization name is obtained;
in step 302, the number information corresponding to the second organization name and the corresponding complete organization name are fed back to the user.
In this embodiment, for step 301, the voice robot acquires a complete organization name of an organization name set corresponding to the second organization name, for example, the robot acquires a corresponding organization name set such as { "shanghai transportation university", "shanghai intersection size" }, and the voice robot acquires a complete organization name such as "shanghai transportation university" in the set.
Then, for step 302, the voice robot feeds back the number information corresponding to the second organization name and the corresponding complete organization name to the user, for example, the voice robot broadcasts the number information "021- ×" corresponding to the complete organization names "shanghai transportation university" and "shanghai transportation university" to the user.
The method of the embodiment finds out the mechanism name set which needs to be found by the user through the voice robot, and confirms whether the mechanism is the mechanism or not to the user, if so, the mechanism; the full name of the organization name and the corresponding number information of the set are broadcasted to the user, so that the user can know the full name of the organization name and the corresponding telephone number more clearly, and the opportunity that the user confirms whether the broadcasted organization name is the organization name which the user wants to inquire once again is given through the whole process of broadcasting the organization name.
Please refer to fig. 4, which shows a flowchart of a voice directory assistance method according to another embodiment of the present invention, the flowchart mainly defines a step of "if a second organization name similar to the first organization name exists in the plurality of organization name sets in step 104 in fig. 1, confirm to the user whether the first organization name and the second organization name are semantically the same" in the flowchart.
As shown in fig. 4, in step 401, if there is one and only one second organization name in the plurality of organization name sets is similar to the first organization name, it is confirmed to the user whether the first organization name and the second organization name are semantically the same;
in step 402, if a plurality of second organization names in the plurality of organization name sets are similar to the first organization name, determining to the user whether any of the plurality of second organization names are semantically identical.
In this embodiment, for step 401, if there is only one second organization name in the plurality of organization name sets similar to the first organization name, it is determined to the user whether the first organization name is semantically the same as the second organization name, for example, a plurality of organization name sets "shanghai transportation university", "shanghai traffic university", "shanghai jungdong", and the like, where "shanghai transportation university" is similar to "shanghai traffic university" that the user needs to search for, and the voice robot determines to the user whether the "shanghai transportation university" is present.
Then, for step 402, if there are a plurality of second organization names in the plurality of organization name sets similar to the first organization name, confirming to the user whether any of the plurality of second organization names is semantically the same, for example, the organization name searched by the user input is "transportation university", the voice robot finds a plurality of organization names "shanghai transportation university", "beijing transportation university" and "nanjing transportation university" and asks the user whether: "Shanghai transportation university" and "Beijing transportation university" are also "Nanjing transportation university".
In the method of the embodiment, one or more mechanism name sets are found out to be similar to the mechanism name which needs to be found by the user through the voice robot, and whether the mechanism name is the mechanism name or not is confirmed to the user; in the mode of confirming with the user, the voice robot can not generate errors when searching the mechanism name required by the user.
Referring to fig. 5, a flowchart of another voice directory assistance method according to an embodiment of the present invention is shown, and the flowchart mainly illustrates steps further defined in the flowchart of fig. 4.
As shown in fig. 5, in step 501, if the semantic identity instruction of the user is received, the voice robot feeds back number information corresponding to the second organization name to the user;
in step 502, if there is and only one second organization name similar to the first organization name and the user confirms that the semantics are the same, the first organization name is stored into the organization name set corresponding to the second organization name to enrich the organization name set for realizing self-learning of the voice robot, and number information corresponding to the second organization name is fed back to the user.
In this embodiment, for step 501, the voice robot receives the semantic identity instruction of the user, and the voice robot feeds back the number information corresponding to the second organization name to the user, for example, the voice robot receives the organization name "shanghai transportation university" searched by the user, and the voice robot directly broadcasts the number information corresponding to the "shanghai transportation university" to the user.
Then, for step 502, if there is and only one second organization name similar to the first organization name and the user confirms that the semantics are the same, the first organization name is stored in the organization name set corresponding to the second organization name, and the number information corresponding to the second organization name is fed back to the user, for example, the organization name "shanghai transportation university" searched by the voice robot is most similar to the organization name "shanghai transportation university" that the user needs to search, the user also confirms that the organization name is "shanghai transportation university", and the voice robot stores the name "shanghai transportation university" into the set of "shanghai transportation university" for short, and simultaneously broadcasts the number information of "shanghai transportation university" to the user.
According to the method, whether the mechanism name searched by the voice robot exists is determined through the voice robot and the user, if the mechanism name which the user needs to search does not exist in the database, the voice robot stores the new mechanism name in the corresponding mechanism name set, and number information corresponding to the mechanism name is broadcasted to the user, so that the mechanism name number required by the user can be searched more accurately. Further, under the condition that there is one and only one organization name which is similar and the user confirms that the semantics are the same, the self-learning of the voice robot can be realized by storing the organization name into the organization name set with the user confirmed semantics being the same, namely, the organization name can be directly positioned into the corresponding organization name set when the inquiry of the organization name appears next time.
Please refer to fig. 6, which shows a flowchart of a voice directory assistance method according to another embodiment of the present invention, the flowchart mainly defines a step of "if there is one and only one second organization name in the plurality of organization name sets is similar to the first organization name" step 401 in fig. 4, confirm to the user whether the first organization name and the second organization name are semantically the same "step.
As shown in fig. 6, in step 601, the number attribution of the incoming call of the user is queried;
in step 602, if there are a plurality of second organization names in the plurality of organization name sets similar to the first organization name, determining whether there is an organization name related to the number attribution in the plurality of second organization names;
in step 603, if a third organization name related to the number attribution exists in the plurality of second organization names, it is confirmed to the user whether the third organization name and the second organization name are semantically the same.
In this embodiment, for step 601, the voice robot queries the number attribution of the incoming call of the user, for example, the voice robot determines the number attribution and the specific city of the user according to the location information and the phone number information of the user.
Then, for step 602, the voice robot searches for a plurality of second organization names in the plurality of organization name sets to be similar to the first organization name, determines whether an organization name related to the number attribution exists in the plurality of second organization names, for example, the organization name that the user needs to find is "transportation", the voice robot finds "Shanghai transportation university", "Beijing transportation university", "Nanjing transportation university" in the plurality of organization name sets ", the voice robot judges that the position of the user is Shanghai according to the number attribution of the user or the position information of the user, the voice robot finds out the plurality of organization name sets 'Shanghai transportation university', 'Beijing transportation university' and 'Nanjing transportation university' according to the position information of the user and judges whether similar organization names exist in the area where the user is located.
Finally, in step 603, the voice robot finds out that a third organization name related to the number attribution exists in the plurality of second organization names, and confirms to the user whether the third organization name is the same as the second organization name in semantic meaning, for example, the voice robot finds out "shanghai transportation university", "shanghai public transportation group", and "shanghai transportation police team" according to the position information of the user, and confirms to the user whether an organization needing to be found exists.
According to the method, the efficiency of searching the mechanism name required to be searched by the user is improved by determining the home location of the user number, so that the voice robot is more accurate in the searching process.
It should be noted that the above method steps are not intended to limit the execution order of the steps, and in fact, some steps may be executed simultaneously or in the reverse order of the steps, which is not limited herein.
The following description is provided to enable those skilled in the art to better understand the present disclosure by describing some of the problems encountered by the inventors in implementing the present disclosure and by describing one particular embodiment of the finally identified solution.
The inventor finds that the traditional directory enquiry scheme has the following disadvantages in the process of implementing the application:
(1) the user searches for the number through the online search engine, the returned result is wide in range, valuable information is difficult to locate quickly, and the searching efficiency is low. For questions and answers such as posts, the method is not effective. The result of the user's search is likely to be a record three to five years away from the present time, and the actual organization's phone may have been updated; for an official network of a certain organization or organization, a user often needs to find a telephone of a certain department, and needs to find an entrance of the corresponding department in the official network and can find the telephone of the department after entering.
(2) The telephone call is made by a person looking up a directory via the hotline 114, which is inefficient. After receiving the user's telephone call, the service person 114 needs to perform manual inquiry in the system and return the result to the user through the telephone. The time efficiency of the series of actions completed by the manual agents is low, and one agent can only be butted with one user at one time; moreover, the manual seat is limited by time, and the shift is needed to provide 24-hour service, so that the cost is high.
The scheme in the prior art has the following defects that various short names of the same mechanism can not be flexibly processed, and the self-learning capability is not provided, so that the experience of voice interaction with a user can be greatly reduced.
1) Because mechanisms have different abbreviations, such as: the short names of Chinese science and technology university include Chinese science and technology university, Chinese science and technology university and the like, the two methods are used for inquiring numbers based on a number repository, and the short names and the descriptions cannot be greatly generalized, so that the effect is poor;
2) the user says about the organization, because of spoken voice, there are many diversified descriptions, such as "the Chinese science of fertility", "the science of fertility", and the like, and the system cannot be generalized by self-learning about the abbreviation according to the user descriptions.
The inventor finds that technical schemes of the application are not easy to think by technical personnel in the field in the process of realizing the application, because on one hand, 114 directory numbers are mostly served by human seats, the same mechanism has different names, and a voice robot cannot flexibly process short names, which increases the difficulty of digitalization and intellectualization of directory number searching business; on the other hand, the thinking has the leading advantage of years of voice interaction experience, and a plurality of voice robots required by different scenes are introduced for government construction, and a plurality of landing cases exist. These lay a solid foundation for the conception and the realization of the patent.
Please refer to fig. 7, which illustrates a directory plan storage structure according to an embodiment of the present application.
In the present invention, we propose a self-learning optimization method and system for voice directory assistance, and fig. 7 shows a storage structure of the solution proposed in this patent, which is not only a simple "organization name-telephone" correspondence, but also includes a set for short. When the name of the organization spoken by the user is the full name of the organization or the corresponding abbreviation set, the system broadcasts the telephone number through voice. Taking "Beijing post and telecommunications university" as an example, modern people are more accustomed to calling its abbreviation: north post; however, people who have been living in the seventies are habitually called "Beijing post and electronics academy". Both calling methods refer to the same mechanism, so a short set is added to deal with flexible conversation scenes. Compared with the traditional 114 directory enquiry, the scheme not only breaks through the limitation of manual service, but also realizes the short-term set of enquiry mechanisms on the basis of full-scale enquiry, and effectively deals with different short-terms of the same mechanism in the actual conversation.
Referring to fig. 8, a block diagram of a solution architecture provided by an embodiment of the present application is shown.
The related service modules of the scheme are as follows: ASR (Automatic Speech Recognition), NLU (Natural Language Understanding), NLG (Natural Language Generation), TTS (Text To Speech), SSM (Semantic similarity matching); the protocol for accessing the session center is sip (session initiation protocol). Fig. 8 shows an architecture diagram of the voice directory assistance self-learning optimization method. When the mechanism name $ { query } obtained through voice recognition does not accord with the full name, and the set for short is not hit, the system matches $ { query } with the existing full name and set for short through semantic similarity, selects the mechanism full name $ { orgname } with the highest similarity, and asks whether the user is the mechanism; if the system is confirmed, the system is added to the short form set of the mechanism, and therefore dialogue self-learning is achieved. When the next user asks the phone of the organization in the same abbreviation, the system can find the name in the abbreviation set since it has already been learned.
Please refer to fig. 9, which shows an example of an actual dialog of the voice directory assistance scheme provided in an embodiment of the present application.
Fig. 9 lists possible dialog processes for an actual user when interacting with the system: it is assumed that in the data storage of the system, the element "Beijing post and Electricity institute" is not in the short term set corresponding to the organization "Beijing post and Electricity university". The user 1 asks the Beijing post electric institute for a telephone, and the system recording mechanism $ { query } - "Beijing post electric institute". And inquiring the 'Beijing post and telecommunications college' in the set of the full name and the short name, and after comparing the 'query' with the full name and the short name by similarity, the 'post and telecommunications college' has the highest score. The full name $ { orgname } corresponding to the set of the element 'post and telecommunications university' is 'Beijing post and telecommunications university' voice robot inquires whether the user refers to 'Beijing post and telecommunications university', and after obtaining a positive answer from the user, the number $ { tel } ═ 11 ×) corresponding to the 'Beijing post and telecommunications university' is broadcasted to the user, and the name of 'Beijing post and telecommunications institute' is added to the short name set. Thereafter, if the organization queried when the user 2 inquires about the phone of "beijing post and telecommunications university" is "beijing post and telecommunications college", the updated abbreviation set will be directly returned to the user's phone of "beijing post and telecommunications university" when it has been queried through the self-learning system (the storage structure is referred to fig. 7).
Referring again to fig. 10, a flow chart of a software implementation provided by an embodiment of the present application is shown.
Fig. 10 shows a software implementation flowchart of the directory lookup scheme proposed by this patent: after the user answers the voice, the system converts the voice into a text through the ASR, and then understands the directory search intention of the user through the NLU and extracts the mechanism entity name in the text. If the name is inquired in the mechanism full name and short name set, the telephone is broadcasted to the user; if the query in the database is not successful, the system matches the name with the mechanism full name and the short name set to obtain the mechanism full name $ { orgname } with high similarity score, and then confirms whether the mechanism is the mechanism to the user. After understanding the confirmation intention of the user, the corresponding telephone is broadcasted to the user, and the new mechanism name is added to the telephone directory, so that the dialogue type self-learning is realized.
After the user dials the hotline, the voice robot extracts the organization name which the user wants to inquire through voice interaction with the user. If the mechanism name is in the full name or the corresponding short name set, the robot broadcasts the corresponding telephone to the user; if the mechanism does not exist in the directory any more, the directory inquiry system compares the name of the mechanism of the user and the mechanism in the directory through the semantic similarity, and if the similarity calculation result is greater than a certain set threshold value, the user is confirmed whether the mechanism exists in the directory or not; if the user gives a positive, the system adds a new title to the database, and the new title is updated continuously, so that the result can be inquired more quickly when other users inquire. Through a series of operations of inquiry, similarity matching, broadcast, updating and the like, the system has good closed-loop performance and can adapt to the diversity of language expressions.
The scheme of the application is mainly designed and optimized from the following aspects:
the current number searching system on the market can not flexibly process various short names of the same mechanism, does not have self-learning capability, can greatly reduce the experience feeling of voice interaction with a user, is improved and optimized mainly from the aspects, and improves the experience feeling and the practicability of the user on the voice interaction.
Referring to fig. 11, a block diagram of a voice directory assistance device according to an embodiment of the present invention is shown.
As shown in fig. 11, the voice directory assistance device 1100 includes an extraction program module 1110, a presence processing program module 1120, a similarity determination program module 1130, a confirmation program module 1140, and a feedback program module 1150.
The extraction program module 1110 is configured to, in response to the voice directory assistance information input by the user being received by the voice robot, extract a first organization name from the voice directory assistance information, and query whether the first organization name exists in a preset plurality of organization name sets; a presence handler module 1120 configured to, if the first organization name exists in the plurality of organization name sets, feed back number information corresponding to the first organization name to the user; a similarity determination program module 1130 configured to determine, if the first mechanism name does not exist in the preset mechanism name sets, whether a second mechanism name similar to the first mechanism name exists in the mechanism name sets by the voice robot; a confirmation program module 1140 configured to confirm to the user whether the first organization name and the second organization name are semantically identical if a second organization name similar to the first organization name exists in the plurality of organization name sets; and a feedback program module 1150 configured to, if the semantic identity instruction of the user is received, feed back number information corresponding to the second mechanism name to the user by the voice robot.
It should be understood that the modules recited in fig. 11 correspond to various steps in the methods described with reference to fig. 1, 2, 3, 4, 5, and 6. Thus, the operations and features described above for the method and the corresponding technical effects are also applicable to the modules in fig. 11, and are not described again here.
It should be noted that the modules in the embodiments of the present disclosure are not limited to the scheme of the present disclosure, for example, the determining module may be described as a module that determines whether the interaction state is a playing scene when the device is in the interaction state. In addition, the related function module may also be implemented by a hardware processor, for example, the determining module may also be implemented by a processor, which is not described herein again.
Embodiments of the present invention also provide a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium, where the computer program includes program instructions, and when the program instructions are executed by a computer, the computer executes any one of the above voice directory assistance methods.
Fig. 12 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 12, the electronic device includes: one or more processors 1201 and a memory 1202, one processor 1201 being exemplified in fig. 12. The apparatus of the voice directory assistance method may further include: an input device 1203 and an output device 1204. The processor 1201, the memory 1202, the input device 1203, and the output device 1204 may be connected by a bus or other means, and the bus connection is exemplified in fig. 12. The memory 1202 is a non-volatile computer-readable storage medium as described above. The processor 1201 executes various functional applications and data processing of the server by executing nonvolatile software programs, instructions and modules stored in the memory 1202, so as to implement the voice directory assistance method of the above-mentioned method embodiment. The input device 1203 may receive input numeric or character information and generate key signal inputs related to user settings and function controls of the voice directory assistance device. The output device 1204 may include a display device such as a display screen.
The product can execute the method provided by the embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the method provided by the embodiment of the present invention.
As an embodiment, the electronic device is applied to a voice directory assistance device, and is used for a client, and the electronic device includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to:
responding to voice directory assistance information input by a user and received by a voice robot, extracting a first organization name from the voice directory assistance information, and inquiring whether the first organization name exists in a plurality of preset organization name sets or not;
if the first organization name exists in the plurality of organization name sets, feeding back number information corresponding to the first organization name to the user;
if the first mechanism name does not exist in the preset mechanism name sets, the voice robot judges whether a second mechanism name similar to the first mechanism name exists in the mechanism name sets or not;
if a second organization name similar to the first organization name exists in the plurality of organization name sets, confirming whether the semantics of the first organization name and the second organization name are the same to the user;
and if receiving the instruction with the same semantic meaning of the user, the voice robot feeds back number information corresponding to the second mechanism name to the user.
The electronic device of the embodiments of the present application exists in various forms, including but not limited to:
(1) a mobile communication device: such devices are characterized by mobile communications capabilities and are primarily targeted at providing voice, data communications. Such terminals include smart phones (e.g., iphones), multimedia phones, functional phones, and low-end phones, among others.
(2) Ultra mobile personal computer device: the equipment belongs to the category of personal computers, has calculation and processing functions and generally has the characteristic of mobile internet access. Such terminals include: PDA, MID, and UMPC devices, etc., such as ipads.
(3) A portable entertainment device: such devices can display and play multimedia content. Such devices include audio and video players (e.g., ipods), handheld game consoles, electronic books, as well as smart toys and portable car navigation devices.
(4) The server is similar to a general computer architecture, but has higher requirements on processing capability, stability, reliability, safety, expandability, manageability and the like because of the need of providing highly reliable services.
(5) And other electronic devices with data interaction functions.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods of the various embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A voice directory assistance method, comprising:
responding to voice directory assistance information input by a user and received by a voice robot, extracting a first organization name from the voice directory assistance information, and inquiring whether the first organization name exists in a plurality of preset organization name sets or not;
if the first organization name exists in the plurality of organization name sets, feeding back number information corresponding to the first organization name to the user;
if the first mechanism name does not exist in the preset mechanism name sets, the voice robot judges whether a second mechanism name similar to the first mechanism name exists in the mechanism name sets or not;
if a second organization name similar to the first organization name exists in the plurality of organization name sets, confirming whether the semantics of the first organization name and the second organization name are the same to the user;
and if receiving the instruction with the same semantic meaning of the user, the voice robot feeds back number information corresponding to the second mechanism name to the user.
2. The method of claim 1, wherein the voice robot presets a semantic similarity threshold, and the determining whether a second organization name similar to the first organization name exists in the plurality of organization name sets comprises:
calculating semantic similarity between the short names in the plurality of organization name sets and the first organization name;
and if the similarity between the second organization name in at least one organization name set and the first organization name is larger than or equal to the semantic similarity threshold, confirming that the second organization name similar to the first organization name exists in the plurality of organization name sets.
3. The method of claim 2, wherein the method further comprises:
and if the similarity between the plurality of second organization names and the first organization name is larger than or equal to the semantic similarity threshold, only one second organization name with the highest similarity is obtained.
4. The method of claim 1, wherein the plurality of sets of institution names comprises:
each mechanism name set in the mechanism name sets is provided with a complete mechanism name which is uniquely corresponding to the mechanism name set, and the mechanism name set comprises a short name of the complete mechanism name and a full name of the complete mechanism name.
5. The method of claim 1, wherein the voice robot feeding back number information corresponding to the second organization name to the user comprises:
acquiring a complete organization name of the organization name set corresponding to the second organization name;
and feeding back the number information corresponding to the second organization name and the corresponding complete organization name to the user.
6. The method of claim 1, wherein the confirming to the user whether the first organization name and the second organization name are semantically identical if there is a second organization name in the plurality of organization name sets that is similar to the first organization name comprises:
if one and only one second organization name in the plurality of organization name sets is similar to the first organization name, confirming whether the first organization name and the second organization name are semantically the same to the user;
and if a plurality of second organization names in the plurality of organization name sets are similar to the first organization name, confirming whether any second organization name in the plurality of second organization names is identical in semantic meaning to the user.
7. The method of claim 6, wherein the method comprises:
if receiving the instruction of the same semantic meaning of the user, the voice robot feeds back number information corresponding to the second mechanism name to the user;
if there is only one second mechanism name similar to the first mechanism name and the user confirms that the semantics are the same, the first mechanism name is stored into a mechanism name set corresponding to the second mechanism name to enrich the mechanism name set so as to realize self-learning of the voice robot, and number information corresponding to the second mechanism name is fed back to the user.
8. The method of claim 6, wherein a plurality of second institution names in the plurality of institution name sets are similar to the first institution name, and wherein confirming to the user whether any of the plurality of second institution names are semantically identical comprises:
inquiring the number attribution of the incoming call of the user;
if a plurality of second organization names in the plurality of organization name sets are similar to the first organization name, judging whether the organization names related to the number attribution place exist in the plurality of second organization names;
and if the plurality of second organization names have third organization names related to the number attribution, confirming whether the third organization names are semantically the same as the second organization names to the user.
9. A voice directory assistance apparatus comprising:
the extraction program module is configured to respond to voice directory assistance information input by a user and received by the voice robot, extract a first organization name from the voice directory assistance information and inquire whether the first organization name exists in a plurality of preset organization name sets or not;
a presence processing program module configured to feed back number information corresponding to the first organization name to the user if the first organization name exists in the plurality of organization name sets;
the similarity judgment program module is configured to judge whether a second mechanism name similar to the first mechanism name exists in the plurality of mechanism name sets or not by the voice robot if the first mechanism name does not exist in the plurality of preset mechanism name sets;
a confirmation program module configured to confirm to the user whether a second organization name similar to the first organization name exists in the plurality of organization name sets, the first organization name and the second organization name being semantically identical;
and the feedback program module is configured to feed back number information corresponding to the second mechanism name to the user by the voice robot if the instruction that the semantics of the user are the same is received.
10. An electronic device, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110533592.3A CN113271383A (en) | 2021-05-12 | 2021-05-12 | Voice number checking method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110533592.3A CN113271383A (en) | 2021-05-12 | 2021-05-12 | Voice number checking method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113271383A true CN113271383A (en) | 2021-08-17 |
Family
ID=77231085
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110533592.3A Pending CN113271383A (en) | 2021-05-12 | 2021-05-12 | Voice number checking method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113271383A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220028373A1 (en) * | 2020-07-24 | 2022-01-27 | Comcast Cable Communications, Llc | Systems and methods for training voice query models |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1984189A (en) * | 2006-04-07 | 2007-06-20 | 华为技术有限公司 | Method for quering telephone number |
| CN104469029A (en) * | 2014-11-21 | 2015-03-25 | 科大讯飞股份有限公司 | Method and device for telephone number query through voice |
| WO2018102980A1 (en) * | 2016-12-06 | 2018-06-14 | 吉蒂机器人私人有限公司 | Speech interaction method, device and system |
| CN109274847A (en) * | 2018-11-06 | 2019-01-25 | 芋头科技（杭州）有限公司 | Call method and device, intelligent sound equipment and controller and medium |
| CN111105783A (en) * | 2019-12-06 | 2020-05-05 | 中国人民解放军61623部队 | Comprehensive customer service system based on artificial intelligence |
| CN112040073A (en) * | 2020-07-15 | 2020-12-04 | 国网山东省电力公司信息通信公司 | Intelligent directory assistance server, directory assistance system and directory assistance method |
-
2021
- 2021-05-12 CN CN202110533592.3A patent/CN113271383A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1984189A (en) * | 2006-04-07 | 2007-06-20 | 华为技术有限公司 | Method for quering telephone number |
| CN104469029A (en) * | 2014-11-21 | 2015-03-25 | 科大讯飞股份有限公司 | Method and device for telephone number query through voice |
| WO2018102980A1 (en) * | 2016-12-06 | 2018-06-14 | 吉蒂机器人私人有限公司 | Speech interaction method, device and system |
| CN109274847A (en) * | 2018-11-06 | 2019-01-25 | 芋头科技（杭州）有限公司 | Call method and device, intelligent sound equipment and controller and medium |
| CN111105783A (en) * | 2019-12-06 | 2020-05-05 | 中国人民解放军61623部队 | Comprehensive customer service system based on artificial intelligence |
| CN112040073A (en) * | 2020-07-15 | 2020-12-04 | 国网山东省电力公司信息通信公司 | Intelligent directory assistance server, directory assistance system and directory assistance method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220028373A1 (en) * | 2020-07-24 | 2022-01-27 | Comcast Cable Communications, Llc | Systems and methods for training voice query models |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8412529B2 (en) | Method and system for enhancing verbal communication sessions | |
| CN108962233B (en) | Voice conversation processing method and system for voice conversation platform | |
| US8537980B2 (en) | Conversation support | |
| JP6730994B2 (en) | Question/answer information processing method, device, storage medium, and device | |
| CN107833574A (en) | Method and apparatus for providing voice service | |
| US20110161077A1 (en) | Method and system for processing multiple speech recognition results from a single utterance | |
| CN109543019A (en) | Dialogue service method and device for vehicle | |
| CN112487810B (en) | Intelligent customer service method, device, equipment and storage medium | |
| KR20080114693A (en) | A search tool providing optional use of human search guides | |
| CN110223692B (en) | Multi-turn dialogue method and system for voice dialogue platform cross-skill | |
| WO2020038145A1 (en) | Service data processing method and apparatus, and related device | |
| US11334618B1 (en) | Device, system, and method of capturing the moment in audio discussions and recordings | |
| US11721328B2 (en) | Method and apparatus for awakening skills by speech | |
| CN113271383A (en) | Voice number checking method and device | |
| CN109783822B (en) | Data sample identification system and method based on verification code | |
| CN109286554B (en) | Social function unlocking method and device in social application | |
| CN114227702A (en) | Intelligent conference guiding method and device based on robot and robot | |
| JP2002123283A (en) | Voice recognition operating device | |
| CN109964473A (en) | The method and device of voice service response | |
| CN112988956B (en) | Method and device for automatically generating dialogue, and method and device for detecting information recommendation effect | |
| CN110109597B (en) | Singing list switching method, device, system, terminal and storage medium | |
| JP2005011089A (en) | Interactive device | |
| CN110675869A (en) | Method and device for controlling applications in smart city app through voice | |
| EP2712162B1 (en) | Method and system for inputting information to mobile terminal as well as mobile terminal | |
| CN112861542A (en) | Method and device for limiting scene voice interaction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |