1. An intelligent voice call method, characterized in that the method comprises:

acquiring a driving line code of an execution device and an execution device code;

correspondingly adding a trigger word for each execution equipment code, and storing the trigger word, the execution equipment codes and the corresponding drive line codes in a trigger index list in a group; the trigger word is used for positioning and triggering execution equipment to start work, and the trigger word comprises work content which can be correspondingly completed by the execution equipment and a service subject range corresponding to an answer;

acquiring call voice uploaded by a client;

analyzing the call voice to obtain the problem requirement of the user at the client;

judging whether the problem requirement is a pre-reserve problem or not;

when the problem requirement is not a pre-reserve problem, driving the execution equipment to acquire reply information according to the problem requirement;

and feeding back the acquired reply information to the client in real time.

2. The intelligent voice call method according to claim 1, wherein the analyzing the call voice to obtain the question requirement of the user at the client specifically comprises:

recognizing all contents of call voice, and converting the voice contents into character contents;

identifying a business body and a problem descriptor in the text content;

and taking the business main body and the question descriptor as the question requirements of the client user to perform corresponding reply.

3. The intelligent voice call method according to claim 2, wherein the determining whether the question demand is a pre-reserve question specifically comprises:

searching in a pre-stored problem library according to the identified service body and the problem descriptors;

when a pre-reserved question containing a business main body and all question descriptors is retrieved, calling out a pre-reserved answer corresponding to the retrieved pre-reserved question, and sending the pre-reserved answer to a client;

when the pre-reserve question containing the business main body and partial question descriptors is searched, the text content converted by the conversation voice, the searched pre-reserve question and the corresponding pre-reserve answer are sent to the manual judgment end for secondary judgment.

4. The intelligent voice call method according to claim 3, wherein the secondary judgment specifically comprises:

obtaining a judgment result fed back by a manual judgment end;

when the judgment result is that the pre-stored answer can answer the question requirement in the text content, the question requirement is a pre-stored question, and the pre-stored answer is sent to the client;

and when the judgment result is that the pre-reserve answer cannot answer the question requirement in the text content, the question requirement is not a pre-reserve question, and the pre-reserve answer is not sent to the client.

5. The intelligent voice call method according to claim 1, wherein when the question requirement is not a pre-reserve question, driving the execution device to acquire the reply message according to the question requirement specifically comprises:

retrieving the trigger words in the trigger index list according to the service main body and the problem description words;

when the service main body and the problem descriptor are matched with one trigger word in the trigger index list, identifying the drive line code through the trigger word;

according to the identified drive line code, sending a starting signal from the corresponding drive line to start the execution equipment;

acquiring reply information fed back by the execution equipment;

and feeding back the acquired reply information to the client in a fixed format.

6. The intelligent voice call method according to claim 1, further comprising:

when the automatic voice reply is carried out synchronously with the conversation voice uploaded by the client, the automatic voice reply content is immediately stopped;

when the conversation voice uploaded by the client stops for a specified time, combining the conversation voice acquired before the automatic voice reply stops and the conversation voice acquired again after the automatic voice reply stops to form complete conversation voice;

and continuing to analyze the call voice.

7. The intelligent voice call method according to any one of claims 1 to 6, further comprising:

when the call voice uploaded by the client side has noise or the voice content is not consistent, the obtained call voice is proved to be bad call voice, and prompt voice with bad communication condition is fed back to the client side;

acquiring call voice repeatedly uploaded again after the client receives the prompt voice;

covering the bad call voice acquired last time with the call voice acquired again;

and continuing to analyze the call voice acquired again.

8. An intelligent voice call apparatus, the apparatus comprising:

the code acquisition module is used for acquiring a driving line code of the execution equipment and an execution equipment code;

the trigger word adding module is used for correspondingly adding a trigger word for each execution equipment code and storing the trigger word, the execution equipment codes and the corresponding drive line codes in a trigger index list in a group;

the voice acquisition module is used for acquiring call voice uploaded by the client;

the voice analysis module is used for analyzing the call voice to obtain the problem requirements of the user at the client;

the problem judging module is used for judging whether the problem requirement is a pre-reserve problem or not;

the reply information acquisition module is used for driving the execution equipment to acquire reply information according to the problem requirement when the problem requirement is not a pre-reserve problem;

and the reply information feedback module is used for feeding back the acquired reply information to the client in real time.

9. An intelligent voice call system, the system comprising:

the intelligent voice call device according to claim 8, configured to analyze the obtained call voice, and automatically answer a problem requirement in the call voice after the judgment processing;

the manual judgment end is used for carrying out secondary judgment on the text content converted from the call voice sent by the intelligent voice call device, the retrieved pre-stored questions and the corresponding pre-stored answers, judging whether the pre-stored answers can answer the question requirements in the text content or not, and feeding back the judgment result to the intelligent voice call device;

the database is used for storing pre-stored questions and corresponding pre-stored answers and/or trigger index lists and/or voice audio backups generated in the whole intelligent voice call process and/or historical data generated in the operation process of the intelligent voice call device;

and the execution equipment starts working when receiving a starting signal sent by the intelligent voice call device and feeds back the acquired reply information to the intelligent voice call device.

Background

With the advent of artificial intelligence and the continuous innovation of technology, some robots related to voice interaction begin to move into the field of view of the public, and the combination of intelligent voice robots with various industries is more and more extensive, and the appearance of the intelligent voice robots will change the working properties of the existing telephone services.

The intelligent voice is a cognition and recognition process, an intelligent voice system firstly processes an original voice signal and then performs feature extraction so as to eliminate the influence caused by noise and voice difference among different speakers and enable the processed signal to more comprehensively respond to the essence of voice feature extraction.

However, the existing intelligent voice system has a single function, and can only reply to preset contents, when a client asks a question except the preset contents, the intelligent voice communication system cannot reply or the replied contents are wrong, the intelligent voice communication system cannot answer the question with the answer changing along with the environment at any time, and the degree of matching with the surrounding environment and surrounding workers is not enough, so that the working range is limited.

Disclosure of Invention

The embodiment of the invention provides an intelligent voice call method, an intelligent voice call device and an intelligent voice call system, and aims to solve the problems that the existing intelligent voice call system cannot answer the problem that the answer changes along with the environment at any time, and the working range is limited due to insufficient matching degree with the surrounding environment and surrounding workers.

The embodiment of the invention is realized in such a way that, on one hand, an intelligent voice call method comprises the following steps:

acquiring a driving line code of an execution device and an execution device code;

correspondingly adding a trigger word for each execution equipment code, and storing the trigger word, the execution equipment codes and the corresponding drive line codes in a trigger index list in a group; the trigger word is used for positioning and triggering execution equipment to start work, and the trigger word comprises work content which can be correspondingly completed by the execution equipment and a service subject range corresponding to an answer;

acquiring call voice uploaded by a client;

analyzing the call voice to obtain the problem requirement of the user at the client;

judging whether the problem requirement is a pre-reserve problem or not;

when the problem requirement is not a pre-reserve problem, driving the execution equipment to acquire reply information according to the problem requirement;

and feeding back the acquired reply information to the client in real time.

As a modified scheme of the invention: the analyzing the call voice to obtain the problem requirement of the user at the client specifically comprises:

recognizing all contents of call voice, and converting the voice contents into character contents;

identifying a business body and a problem descriptor in the text content;

and taking the business main body and the question descriptor as the question requirements of the client user to perform corresponding reply.

As a further improvement of the invention: the step of judging whether the problem demand is a pre-reserve problem specifically comprises the following steps:

searching in a pre-stored problem library according to the identified service body and the problem descriptors;

when a pre-reserved question containing a business main body and all question descriptors is retrieved, calling out a pre-reserved answer corresponding to the retrieved pre-reserved question, and sending the pre-reserved answer to a client;

when the pre-reserve question containing the business main body and partial question descriptors is searched, the text content converted by the conversation voice, the searched pre-reserve question and the corresponding pre-reserve answer are sent to the manual judgment end for secondary judgment.

As another improvement of the invention: the secondary judgment specifically comprises:

obtaining a judgment result fed back by a manual judgment end;

when the judgment result is that the pre-stored answer can answer the question requirement in the text content, the question requirement is a pre-stored question, and the pre-stored answer is sent to the client;

and when the judgment result is that the pre-reserve answer cannot answer the question requirement in the text content, the question requirement is not a pre-reserve question, and the pre-reserve answer is not sent to the client.

As a further scheme of the invention: when the problem requirement is not a pre-reserve problem, driving the execution device to acquire the reply information according to the problem requirement specifically includes:

retrieving the trigger words in the trigger index list according to the service main body and the problem description words;

when the service main body and the problem descriptor are matched with one trigger word in the trigger index list, identifying the drive line code through the trigger word;

according to the identified drive line code, sending a starting signal from the corresponding drive line to start the execution equipment;

acquiring reply information fed back by the execution equipment;

and feeding back the acquired reply information to the client in a fixed format.

As an optimization scheme of the invention: the intelligent voice call method further comprises the following steps:

when the automatic voice reply is carried out synchronously with the conversation voice uploaded by the client, the automatic voice reply content is immediately stopped;

when the conversation voice uploaded by the client stops for a specified time, combining the conversation voice acquired before the automatic voice reply stops and the conversation voice acquired again after the automatic voice reply stops to form complete conversation voice;

and continuing to analyze the call voice.

As another scheme of the invention: the intelligent voice call method further comprises the following steps:

when the call voice uploaded by the client side has noise or the voice content is not consistent, the obtained call voice is proved to be bad call voice, and prompt voice with bad communication condition is fed back to the client side;

acquiring call voice repeatedly uploaded again after the client receives the prompt voice;

covering the bad call voice acquired last time with the call voice acquired again;

and continuing to analyze the call voice acquired again.

In another aspect, an intelligent voice communicator includes:

the code acquisition module is used for acquiring a driving line code of the execution equipment and an execution equipment code;

the trigger word adding module is used for correspondingly adding a trigger word for each execution equipment code and storing the trigger word, the execution equipment codes and the corresponding drive line codes in a trigger index list in a group;

the voice acquisition module is used for acquiring call voice uploaded by the client;

the voice analysis module is used for analyzing the call voice to obtain the problem requirements of the user at the client;

the problem judging module is used for judging whether the problem requirement is a pre-reserve problem or not;

the reply information acquisition module is used for driving the execution equipment to acquire reply information according to the problem requirement when the problem requirement is not a pre-reserve problem;

and the reply information feedback module is used for feeding back the acquired reply information to the client in real time.

In addition, an intelligent voice call system includes:

the intelligent voice call device is used for analyzing the acquired call voice and automatically replying the problem requirement in the call voice after judgment and processing;

the manual judgment end is used for carrying out secondary judgment on the text content converted from the call voice sent by the intelligent voice call device, the retrieved pre-stored questions and the corresponding pre-stored answers, judging whether the pre-stored answers can answer the question requirements in the text content or not, and feeding back the judgment result to the intelligent voice call device;

the database is used for storing pre-stored questions and corresponding pre-stored answers and/or trigger index lists and/or voice audio backups generated in the whole intelligent voice call process and/or historical data generated in the operation process of the intelligent voice call device;

and the execution equipment actively starts working when receiving the starting signal sent by the intelligent voice call device and feeds back the acquired reply information to the intelligent voice call device.

The invention has the beneficial effects that: analyzing the call voice uploaded by the client to obtain the problem requirement of a client user, and judging whether the problem requirement is a pre-reserve problem or not; when the problem requirement is not a pre-reserve problem, driving the execution equipment to acquire reply information according to the problem requirement; the intelligent voice call system has the capability of collecting data to the surrounding environment or seeking help to surrounding workers according to problem demands, arranges the acquired reply information and feeds the reply information back to the client in real time. The intelligent voice call system can answer some questions with answers changing along with the environment at any time, the degree of cooperation of the intelligent voice call system with the surrounding environment and surrounding workers is improved, the intelligent voice call system is more intelligent, and the working range is further expanded.

Drawings

FIG. 1 is a schematic diagram of an intelligent voice call system;

fig. 2 is a main flow chart of an intelligent voice call method;

FIG. 3 is a flow chart of actively obtaining reply information in an intelligent voice call method;

FIG. 4 is a flow chart of active reply voice termination in an intelligent voice call method;

fig. 5 is a flow chart of call voice repeat acquisition in an intelligent voice call method;

fig. 6 is a schematic diagram of an internal structure of an intelligent voice call device.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

The method and the system analyze the call voice uploaded by the client to obtain the problem requirement of a user at the client, and judge whether the problem requirement is a pre-reserve problem or not; when the problem requirement is not a pre-reserve problem, driving the execution equipment to acquire reply information according to the problem requirement; the intelligent voice call system has the capability of collecting data to the surrounding environment or seeking help to surrounding workers according to problem demands, arranges the acquired reply information and feeds the reply information back to the client in real time. The intelligent voice call system can answer some questions with answers changing along with the environment at any time, the degree of cooperation of the intelligent voice call system with the surrounding environment and surrounding workers is improved, the intelligent voice call system is more intelligent, and the working range is further expanded.

Fig. 1 is a schematic structural diagram of an intelligent voice call system according to an embodiment of the present invention, where the intelligent voice call system includes:

and the intelligent voice call device 1 is used for analyzing the acquired call voice and automatically replying the problem requirement in the call voice after judgment and processing.

And the manual judgment end 2 is used for carrying out secondary judgment on the text content converted from the call voice sent by the intelligent voice call device, the retrieved pre-stored questions and the corresponding pre-stored answers, judging whether the pre-stored answers can answer the question requirements in the text content, and feeding back the judgment result to the intelligent voice call device.

And the database 3 is used for storing pre-stored questions and corresponding pre-stored answers and/or trigger index lists and/or voice audio backups generated in the whole intelligent voice call process and/or historical data generated in the operation process of the intelligent voice call device.

And the execution equipment 4 actively starts working when receiving the starting signal sent by the intelligent voice call device 1, and feeds back the acquired reply information to the intelligent voice call device 1. The execution device can be one or more of a group combination of an identification module, a request module and a transfer module; the identification module is used for identifying the change condition and the existing condition of the surrounding environment and can be a camera, an infrared scanning device and the like; the request module is used for requesting help from manual service or directly surfing the Internet in a large network environment to search relevant information and the like; the transfer module is used for transferring the current speaking right to the personnel in the idle state.

In addition, the intelligent voice call device 1 performs voice call with the client 5 in real time, replies to the question requirements proposed by the user of the client 5, some replies are fixed answers, and can directly call and send the pre-stored answers to the client 5, and some reply messages need the intelligent voice call device 1 to drive the execution equipment 4 to obtain the answer to the outside. The way to obtain the information to the outside can be that the execution device 4 scans the surrounding environment or searches for network resources to obtain the information, or can send the sorted problem requirements to the staff, and the staff replies the information manually.

Fig. 2 shows a main flow chart of an intelligent voice call method according to an embodiment of the present invention, where the intelligent voice call method includes:

step S10: the drive line code of the execution device 4 and the execution device code are acquired.

Step S11: and correspondingly adding a trigger word for each execution equipment code, and storing the trigger word, the execution equipment code and the corresponding drive line code in a trigger index list in a group. The trigger word is used for positioning and triggering the execution device 4 to start work, and the trigger word comprises work content which can be correspondingly completed by the execution device 4 and a service subject range corresponding to an answer.

Step S12: and acquiring the call voice uploaded by the client 5.

Step S13: and analyzing the call voice to obtain the problem requirement of the user of the client 5.

Step S14: and judging whether the problem demand is a pre-reserve problem or not.

Step S15: when the problem requirement is not a pre-reserve problem, the execution device 4 is driven to acquire reply information according to the problem requirement.

Step S16: and feeding back the acquired reply information to the client 5 in real time.

Step S17: when the question requirement is a pre-reserve question, a pre-reserve answer corresponding to the pre-reserve question is called out, and the pre-reserve answer is sent to the client 5.

In a case of this embodiment, the analyzing the call voice to obtain the problem requirement of the user of the client 5 specifically includes:

step S130: and recognizing all contents of the call voice, and converting the voice contents into character contents.

Step S131: a business body and a problem descriptor in the textual content are identified. For example, the business entity is a bank registration, the question descriptor is how many people, etc.; or the service main body is the service of the current connected business hall, and the problem description is how much the service to be processed is waiting.

Step S132: and (4) taking the business main body and the question descriptor as the question requirements of the user of the client 5 to perform corresponding reply. The questions described in the customer's call speech are extracted, which is a prerequisite for answering the question requirements.

In one aspect of this embodiment, the determining whether the problem requirement is a pre-reserve problem specifically includes:

step S140: and searching in a pre-stored problem library according to the identified business main body and the problem descriptors.

Step S141: when a pre-reserve question containing a business body and all question descriptors is retrieved, a pre-reserve answer corresponding to the retrieved pre-reserve question is called out, and the pre-reserve answer is sent to the client 5.

Step S142: when the pre-reserve question containing the business main body and partial question descriptors is searched, the text content converted by the conversation voice, the searched pre-reserve question and the corresponding pre-reserve answer are sent to the manual judgment end 2 for secondary judgment. Since the situation is complicated at this time, manual judgment needs to be introduced.

In a case of the foregoing embodiment, the secondary determination specifically includes:

step S20: and obtaining a judgment result fed back by the manual judgment end 2.

Step S21: when the judgment result is that the pre-reserved answer can answer the question requirement in the text content, the question requirement is the pre-reserved question, and the pre-reserved answer is sent to the client 5.

Step S22: when the judgment result is that the pre-reserve answer cannot answer the question requirement in the text content, the question requirement is not a pre-reserve question, and the pre-reserve answer is not sent to the client 5. At this time, steps subsequent to step S13 need to be performed.

Fig. 3 shows a flowchart of actively acquiring reply information in an intelligent voice call method according to an embodiment of the present invention, where when a problem requirement is not a pre-reserve problem, driving the execution device 4 to acquire the reply information according to the problem requirement specifically includes:

step S150: and retrieving the trigger words in the trigger index list according to the service main bodies and the problem description words.

Step S151: when the service main body and the problem descriptor are matched with one trigger word in the trigger index list, the drive line code is identified through the trigger word.

Step S152: an activation signal is sent from the corresponding drive line in accordance with the identified drive line code, activating the actuator device 4.

Step S153: reply information fed back by the execution apparatus 4 is acquired. The execution device 4 may detect the surrounding environment or consult with other human judgment terminals 2, etc. For example, whether the current business hall is suitable for business handling before is detected; according to the statistics, the time period for handling the service is recommended to the client 5, and the clients are dispersed.

Step S154: and feeding back the acquired reply information to the client 5 in a fixed format.

Fig. 4 shows a flow chart of active reply voice suspension in an intelligent voice call method according to an embodiment of the present invention, where the intelligent voice call method further includes:

step S40: when the voice automatic reply is performed synchronously with the call voice uploaded by the client 5, the voice automatic reply content is immediately stopped.

Step S41: when the conversation voice uploaded by the client 5 stops for a specified time, the conversation voice acquired before the automatic voice reply stops and the conversation voice acquired again after the automatic voice reply stops are combined to form complete conversation voice.

Step S42: and continuing to analyze the call voice. When the voice automatic reply is simultaneously carried out with the voice call of the client terminal 5, the automatic reply is immediately stopped, and the contents of the client and the contents to be answered last time are uniformly replied to the client.

Fig. 5 shows a flow chart of repeatedly acquiring call voice in an intelligent voice call method according to an embodiment of the present invention, where the intelligent voice call method further includes:

step S50: when the call voice uploaded by the client 5 has noise or the voice content is not consistent, the obtained call voice is a bad call voice, and a prompt voice with a bad communication condition is fed back to the client 5.

Step S51: and acquiring the call voice repeatedly uploaded again after the client 5 receives the prompt voice.

Step S52: and covering the bad call voice acquired last time with the call voice acquired again.

Step S53: and continuing to analyze the call voice acquired again. When the client 5 has noise or the signal is not good and the reception is poor, the client is reminded of the poor communication condition, and the conversation content is repeated.

Fig. 6 is a schematic diagram illustrating an internal structure of an intelligent voice call device according to an embodiment of the present invention, where the intelligent voice call device 1 includes:

and the code acquiring module 100 is used for acquiring the drive line code of the execution device and the execution device code.

And the trigger word adding module 200 is configured to add a trigger word to each execution device code, and store the trigger word, the execution device code, and the corresponding drive line code in a trigger index list in a group.

And the voice obtaining module 300 is used for obtaining the call voice uploaded by the client 5.

The voice analysis module 400 is configured to analyze the call voice to obtain a problem requirement of the user of the client 5.

And the problem judging module 500 is used for judging whether the problem requirement is a pre-reserve problem.

And a reply information obtaining module 600, configured to drive the execution device 4 to obtain the reply information according to the question requirement when the question requirement is not a pre-reserve question.

And the reply information feedback module 700 is configured to feed back the acquired reply information to the client 5 in real time.

In order to load the above method and apparatus to operate successfully, the apparatus may include more or less components than those described above, or combine some components, or different components, in addition to the various modules described above, for example, an input/output device, a network access device, a bus, a processor, a memory, and the like.

The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like that is the control center for the device and that connects the various parts of the overall system using various interfaces and lines.

The memory may be used to store a computer and system programs and/or modules, and the processor may implement various functions of the client 5 by running or executing the computer programs and/or modules stored in the memory and calling data stored in the memory. The memory mainly comprises a storage program area and a storage data area, wherein the storage program area can store an operating system, application programs (such as an information acquisition template display function, a product information publishing function and the like) required by at least one function and the like; the storage data area may store data created according to the use of the berth-state display system (e.g., product information acquisition templates corresponding to different product types, product information that needs to be issued by different product providers, etc.), and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.

It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in sequence as indicated by the arrows, the steps are not necessarily executed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in various embodiments may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.

The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.