CN113556431A - AI (Artificial intelligence) director assistant system capable of implementing intelligent interaction - Google Patents
AI (Artificial intelligence) director assistant system capable of implementing intelligent interaction Download PDFInfo
- Publication number
- CN113556431A CN113556431A CN202110663880.0A CN202110663880A CN113556431A CN 113556431 A CN113556431 A CN 113556431A CN 202110663880 A CN202110663880 A CN 202110663880A CN 113556431 A CN113556431 A CN 113556431A
- Authority
- CN
- China
- Prior art keywords
- call
- module
- live broadcast
- broadcast room
- equipment
- 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.)
- Withdrawn
Links
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
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/5166—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing in combination with interactive voice response systems or voice portals, e.g. as front-ends
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
- G06F16/90344—Query processing by using string matching techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/22—Arrangements for supervision, monitoring or testing
- H04M3/2281—Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/22—Arrangements for supervision, monitoring or testing
- H04M3/24—Arrangements for supervision, monitoring or testing with provision for checking the normal operation
-
- 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
- H04M3/436—Arrangements for screening incoming calls, i.e. evaluating the characteristics of a call before deciding whether to answer it
-
- 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
- H04M3/54—Arrangements for diverting calls for one subscriber to another predetermined subscriber
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44204—Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
- H04N21/4756—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for rating content, e.g. scoring a recommended movie
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Telephonic Communication Services (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Computer Security & Cryptography (AREA)
- Technology Law (AREA)
- Human Computer Interaction (AREA)
- Geometry (AREA)
- Evolutionary Biology (AREA)
Abstract
The invention discloses an AI (artificial intelligence) broadcasting guide assistant system capable of implementing intelligent interaction, belonging to the technical field of broadcasting guide assistants. The method adopts a multiple management mode to manage the incoming calls of the live broadcast room, greatly improves the working efficiency of a host in the live broadcast room, can realize more accurate screening, and simultaneously reduces the occurrence probability of conditions of screen missing, screen missing and the like in manual screening; the appearance state of the equipment is judged by adopting an area ratio judgment mode, so that the maintenance suggestions of each equipment are obtained, the judgment mode is simple, the calculated amount is small, the hardware requirement is low, and the equipment maintenance requirements can be met; the weighted average value of the multiple types of scores is adopted to represent the program quality, so that the evaluation of the program is more reasonable, the comprehensive level of the program in a live broadcast room can be reflected, and the method is worthy of being popularized and used.
Description
Technical Field
The invention relates to the technical field of broadcasting guide assistants, in particular to an AI broadcasting guide assistant system capable of implementing intelligent interaction.
Background
The broadcasting guide assistant is an assistant of a radio head-man, helps the radio head-man to answer the telephone of the audience, selects the telephone to access the live broadcast room, helps the radio head-man to dial the honored telephone, accesses the telephone to the live broadcast room, helps the radio head-man to filter out the telephone, harassing telephone and telephone which is contrary to national laws and regulations and irrelevant to programs, and helps the radio head-man to extract the short message platform lucky audience; the help radio station host records the telephone of the audience, reminds the radio station host to receive and hang up the telephone, and the help radio station host contacts with the technical department when the program goes wrong, and the help radio station host processes other things outside the live broadcast room. While the director assistant should also have the ability to assist in maintaining live room equipment. The above functions mainly adopt a manual processing mode, and with the rapid development of the AI technology, an intelligent broadcasting assistant system, namely an AI broadcasting assistant system, also comes up.
The existing intelligent broadcasting assistant system is not powerful enough in functionality, for example, call management cannot be realized better, and the phenomenon of mistakenly filtering calls often occurs, so that listeners who really need to reflect problems or complain about emotion through a live broadcasting room obtain poor experience, and adverse effects are brought to public praise of the live broadcasting room; meanwhile, the capability of assisting the maintenance of the equipment in the live broadcast room is difficult to realize, and the product use experience is difficult to improve.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: how to solve the problems that the intelligent broadcasting assistant system can not realize the call management better and is difficult to realize the auxiliary maintenance capability of the equipment of the live broadcast room, and the like, and provides the AI broadcasting assistant system capable of realizing intelligent interaction.
The invention solves the technical problems through the following technical scheme, and the system comprises an incoming call management module, an equipment auxiliary maintenance module, a program quality scoring module, an interaction module, an incoming call switching module, a database module, an early warning module and a central control module;
the call management module is used for managing calls in the live broadcast room and screening the calls with high matching degree with the topics in the live broadcast room;
the device auxiliary maintenance module is used for judging the state of each device in the live broadcast room through image detection, identification and analysis to obtain a maintenance suggestion of each device;
the program quality scoring module is used for comprehensively scoring the live program after the live broadcast is finished to obtain program quality comprehensive scoring data;
the interaction module is used for answering simple questions of a live room audience;
the call forwarding module is used for forwarding the call screened by the call management module to a live broadcast room host, and hanging up and suspending the call;
the database module is used for storing harassing call data, data of each device in a normal state, program quality comprehensive scoring data and the like;
the early warning module is used for selecting whether to early warn maintainers according to the equipment maintenance suggestions obtained by the equipment auxiliary maintenance module;
the central control module is in communication connection with each module and controls each module to execute corresponding instructions.
Furthermore, the call management module comprises a harassing call judgment screening unit, a live broadcast room theme similarity matching unit and an abnormal call judgment unit; the harassing call judging and screening unit is used for comparing the number characteristics contained in the harassing call data stored in the database module with the current incoming call number so as to determine whether to answer the call; the live broadcast room theme similarity matching unit is used for converting voice data of caller in the conversation process into text data in real time, calculating similarity between a character string in the obtained text data and a live broadcast room theme character string, and judging that the call is a call with high matching degree with the live broadcast room theme when the similarity reaches a set value; the abnormal incoming call judging unit is used for recording the incoming call number of which the call duration is less than the set threshold, and sending an abnormal incoming call prompt to the background management center when the incoming call number carries out incoming calls exceeding the set times within the set duration, and the background staff get in contact with the incoming call number.
Furthermore, the working process of the call management module is as follows:
s11: when a call comes from a live broadcast room, comparing the number characteristics contained in the harassing call data stored in the database module with the current incoming call number, judging the call as a harassing call if the number characteristics contained in the harassing call data are met, and not answering the call;
s12: when the incoming call number judges that the incoming call is not a harassing call, the incoming call is connected, voice data of caller in the call process is converted into text data in real time, similarity calculation is carried out on a character string in the obtained text data and a theme character string in a live broadcast room, and when the similarity reaches a set value, the incoming call is judged to be an incoming call with high matching degree with the theme in the live broadcast room;
s13: and recording the incoming call number with the call duration less than the set threshold, and sending an abnormal incoming call prompt to a background management center when the incoming call number carries out incoming calls exceeding the set times within the set duration, so that background workers can contact the incoming call number.
Furthermore, the auxiliary equipment maintenance module comprises an equipment image acquisition unit, an equipment image processing unit and a state judgment unit; the equipment image acquisition unit is used for acquiring images of each piece of equipment at regular time and transmitting the images to the equipment image processing unit; the device image processing unit is used for identifying target devices in the image, reconstructing a blank picture, covering the identified target device image part into the blank picture to form a recombined picture, and performing gray processing and contour detection processing on the recombined picture to acquire contour information of the target devices and dust particles; the state judging unit is used for calculating the area ratio of the dust particles in the recombined picture at the current angle, judging whether the area ratio reaches a set area ratio threshold value, if so, suggesting that the equipment needs to be maintained and cleaned, and if not, suggesting that the equipment does not need to be maintained and cleaned.
Further, the working process of the equipment auxiliary maintenance module is as follows:
s21: regularly collecting images of each device;
s22: identifying target equipment in the image, reconstructing a blank picture, covering the identified image part of the target equipment into the blank picture to form a recombined picture, and performing gray processing and contour detection processing on the recombined picture to obtain contour information of the target equipment and each dust particle;
s23: and calculating the area ratio of the dust particles in the recombined picture at the current angle, and judging whether the area ratio reaches a set area ratio threshold value, wherein if the area ratio reaches the set area ratio threshold value, the equipment is recommended to be maintained and cleaned, and if the area ratio does not reach the set area ratio threshold value, the equipment is recommended not to be maintained and cleaned.
Further, in step S22, contour information of each dust particle, that is, area outline information formed of a plurality of dust particles.
Furthermore, the program quality scoring module comprises a hearing rate scoring unit, an audience independent scoring unit and a staff scoring unit; the listening rate scoring unit is used for scoring the program quality according to the listening rate scoring of the current live broadcast room; the audience autonomous scoring unit is used for scoring the program quality according to the autonomous scoring of the audience; and the staff scoring unit is used for scoring the program quality according to the autonomous scoring of the staff in the live broadcast room.
Further, the formula for calculating the program quality score is as follows:
Z=w1*S+w2*T+w3*M
wherein Z represents the final program quality score, S represents the listening rate score of a live broadcast room, T represents the autonomous score of an audience, and M represents the autonomous score of staff in the live broadcast room; w1, w2 and w3 respectively represent the weights of all types of scores and are specifically set according to practical application.
Compared with the prior art, the invention has the following advantages: the AI director assistant system capable of implementing intelligent interaction manages the incoming calls of the live broadcast room in a multiple management mode, greatly improves the working efficiency of a host in the live broadcast room, can realize more accurate screening, and simultaneously reduces the occurrence probability of conditions of screen missing, screen missing and the like in manual screening; the appearance state of the equipment is judged by adopting an area ratio judgment mode, so that the maintenance suggestions of each equipment are obtained, the judgment mode is simple, the calculated amount is small, the hardware requirement is low, and the equipment maintenance requirements can be met; the weighted average value of the multiple types of scores is adopted to represent the program quality, so that the evaluation of the program is more reasonable, the comprehensive level of the program in a live broadcast room can be reflected, and the method is worthy of being popularized and used.
Drawings
Fig. 1 is a block diagram of an AI director assistant system capable of implementing intelligent interaction in an embodiment of the present invention.
Detailed Description
The following examples are given for the detailed implementation and specific operation of the present invention, but the scope of the present invention is not limited to the following examples.
The embodiment provides a technical scheme: an AI (Artificial intelligence) director assistant system capable of implementing intelligent interaction comprises an incoming call management module, an equipment auxiliary maintenance module, a program quality scoring module, an interaction module, an incoming call switching module, a database module, an early warning module and a central control module;
the call management module is used for managing calls in the live broadcast room and screening calls with high matching degree with the topics in the live broadcast room;
the device auxiliary maintenance module is used for judging the state of each device in the live broadcast room through image detection, identification and analysis to obtain a maintenance suggestion of each device;
the program quality scoring module is used for comprehensively scoring the live program at the end of live broadcast to obtain program quality comprehensive scoring data for subsequent analysis;
the interaction module is used for answering simple questions of a live room audience, such as providing simple information of the live program end time, the host name, the carrier and the like;
the call forwarding module is used for forwarding the call screened by the call management module to a live broadcast room host, and performing hanging-up, suspension and other operations on the call;
the database module is used for storing harassing call data, data of each device in a normal state, program quality comprehensive scoring data and the like;
the early warning module is used for selecting whether to early warn maintainers according to the equipment maintenance suggestions obtained by the equipment auxiliary maintenance module; the early warning mode can be realized by adopting an instant messaging mode, and provides a selection reply item of maintenance personnel, such as 'temporary maintenance' and 'immediate maintenance';
the central control module is in communication connection with the modules and controls the modules to execute corresponding instructions.
In this embodiment, the call management module includes a harassing call judgment and screening unit, a live broadcast room theme similarity matching unit, and an abnormal call judgment unit; the harassing call judging and screening unit is used for comparing the number characteristics contained in the harassing call data stored in the database module with the current incoming call number, and judging that the harassing call is a harassing call if the current incoming call number conforms to the number characteristics contained in the harassing call data, and not answering; the live broadcast room theme similarity matching unit is used for converting voice data of caller in the conversation process into text data in real time, calculating similarity between a character string in the obtained text data and a live broadcast room theme character string, and judging that the call is a call with high matching degree with the live broadcast room theme when the similarity reaches a set value; the abnormal incoming call judging unit is used for recording the incoming call number of which the call duration is less than a set threshold (3 s), and when the incoming call number carries out incoming calls exceeding a set number of times within the set duration (abnormal dangerous conditions may occur to listeners at the incoming call number end), an abnormal incoming call prompt is sent to the background management center, and background workers are in contact with the incoming call number, so that accidents are avoided as much as possible.
In this embodiment, the working process of the incoming call management module is as follows:
s11: when a call comes from a live broadcast room, comparing the number characteristics contained in the harassing call data stored in the database module with the current incoming call number, judging the call as a harassing call if the number characteristics contained in the harassing call data are met, and not answering the call;
s12: when the incoming call number judges that the incoming call is not a harassing call, the incoming call is connected, voice data of caller in the call process is converted into text data in real time, similarity calculation is carried out on a character string in the obtained text data and a theme character string in a live broadcast room, and when the similarity reaches a set value, the incoming call is judged to be an incoming call with high matching degree with the theme in the live broadcast room;
s13: and recording the incoming call number with the call duration less than the set threshold, and sending an abnormal incoming call prompt to a background management center when the incoming call number carries out incoming calls exceeding the set times within the set duration, wherein the background staff contact the incoming call number to inquire the reason.
In the present embodiment, in step S12, the similarity calculation method employs a cosine similarity calculation method.
In this embodiment, the device auxiliary maintenance module includes a device image acquisition unit, a device image processing unit, and a state determination unit; the equipment image acquisition unit is used for acquiring images of each piece of equipment at regular time and transmitting the images to the equipment image processing unit; the device image processing unit is used for identifying target devices in the image, reconstructing a blank picture, covering the identified target device image part into the blank picture to form a recombined picture, and performing gray processing and contour detection processing on the recombined picture to acquire contour information (coordinates in the recombined picture) of the target devices and dust particles; the state judging unit is used for calculating the area ratio of the dust particles in the recombined picture at the current angle, judging whether the area ratio reaches a set area ratio threshold value, if so, suggesting that the equipment needs to be maintained and cleaned, and if not, suggesting that the equipment does not need to be maintained and cleaned. The area ratio judgment mode is adopted to judge the appearance state of the equipment, and then maintenance suggestions of each equipment are obtained, the judgment mode is simple, the calculated amount is small, the hardware requirement is low, and the equipment maintenance requirements can be met.
In this embodiment, the working process of the device auxiliary maintenance module is as follows:
s21: regularly collecting images of each device;
s22: identifying target equipment in the image, reconstructing a blank picture, covering the identified image part of the target equipment into the blank picture to form a recombined picture, and performing gray processing and contour detection processing on the recombined picture to obtain contour information of the target equipment and each dust particle;
s23: and calculating the area ratio of the dust particles in the recombined picture at the current angle, and judging whether the area ratio reaches a set area ratio threshold value, wherein if the area ratio reaches the set area ratio threshold value, the equipment is recommended to be maintained and cleaned, and if the area ratio does not reach the set area ratio threshold value, the equipment is recommended not to be maintained and cleaned.
In this embodiment, in step S22, the target device is identified by using the target detection network trained by a large number of data sets.
In the present embodiment, in step S22, contour information of each dust particle, that is, area outline information formed of a plurality of dust particles.
In this embodiment, the program quality scoring module includes a listening rate scoring unit, an audience independent scoring unit, and a staff scoring unit; the listening rate scoring unit is used for scoring the program quality according to the listening rate scoring of the current live broadcast room; the audience autonomous scoring unit is used for scoring the program quality according to the autonomous scoring of the audience; and the staff scoring unit is used for scoring the program quality according to the autonomous scoring of the staff in the live broadcast room.
In this embodiment, the formula for calculating the program quality score is as follows:
Z=w1*S+w2*T+w3*M
wherein Z represents the final program quality score, S represents the listening rate score of a live broadcast room, T represents the autonomous score of an audience, and M represents the autonomous score of staff in the live broadcast room; w1, w2 and w3 respectively represent the weights of all types of scores and are specifically set according to practical application. The weighted average value of the multiple types of scores is adopted to represent the program quality, so that the evaluation of the program is more reasonable, and the comprehensive level of the program in a live broadcast room can be reflected better.
To sum up, the AI director assistant system capable of implementing intelligent interaction of the embodiment manages the incoming call of the live broadcast room in a multiple management mode, greatly improves the working efficiency of a host in the live broadcast room, can realize more accurate screening, and simultaneously reduces the occurrence probability of conditions of screen missing, screen missing and the like in manual screening; the appearance state of the equipment is judged by adopting an area ratio judgment mode, so that the maintenance suggestions of each equipment are obtained, the judgment mode is simple, the calculated amount is small, the hardware requirement is low, and the equipment maintenance requirements can be met; the weighted average value of the multiple types of scores is adopted to represent the program quality, so that the evaluation of the program is more reasonable, the comprehensive level of the program in a live broadcast room can be reflected, and the method is worthy of being popularized and used.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (9)
1. An AI director assistant system capable of implementing intelligent interaction, characterized in that: the system comprises an incoming call management module, an equipment auxiliary maintenance module, a program quality scoring module, an interaction module, an incoming call switching module, a database module, an early warning module and a central control module;
the call management module is used for managing calls in the live broadcast room and screening the calls with high matching degree with the topics in the live broadcast room;
the device auxiliary maintenance module is used for judging the state of each device in the live broadcast room through image detection, identification and analysis to obtain a maintenance suggestion of each device;
the program quality scoring module is used for comprehensively scoring the live program after the live broadcast is finished to obtain program quality comprehensive scoring data;
the interaction module is used for answering questions of a live room audience;
the call forwarding module is used for forwarding the call screened by the call management module to a live broadcast room host, and hanging up and suspending the call;
the database module is used for storing harassing call data, data of each device in a normal state, program quality comprehensive scoring data and the like;
the early warning module is used for selecting whether to early warn maintainers according to the equipment maintenance suggestions obtained by the equipment auxiliary maintenance module;
the central control module is in communication connection with each module and controls each module to execute corresponding instructions.
2. The AI director assistant system according to claim 1, wherein: the incoming call management module comprises a harassing call judgment screening unit, a live broadcast room theme similarity matching unit and an abnormal incoming call judgment unit; the harassing call judging and screening unit is used for comparing the number characteristics contained in the harassing call data stored in the database module with the current incoming call number so as to determine whether to answer the call; the live broadcast room theme similarity matching unit is used for converting voice data of caller in the conversation process into text data in real time, calculating similarity between a character string in the obtained text data and a live broadcast room theme character string, and judging that the call is a call with high matching degree with the live broadcast room theme when the similarity reaches a set value; the abnormal incoming call judging unit is used for recording the incoming call number of which the call duration is less than the set threshold, and sending an abnormal incoming call prompt to the background management center when the incoming call number carries out incoming calls exceeding the set times within the set duration, and the background staff get in contact with the incoming call number.
3. The AI director assistant system according to claim 2, wherein: the working process of the call management module is as follows:
s11: when a call comes from a live broadcast room, comparing the number characteristics contained in the harassing call data stored in the database module with the current incoming call number, judging the call as a harassing call if the number characteristics contained in the harassing call data are met, and not answering the call;
s12: when the incoming call number judges that the incoming call is not a harassing call, the incoming call is connected, voice data of caller in the call process is converted into text data in real time, similarity calculation is carried out on a character string in the obtained text data and a theme character string in a live broadcast room, and when the similarity reaches a set value, the incoming call is judged to be an incoming call with high matching degree with the theme in the live broadcast room;
s13: and recording the incoming call number with the call duration less than the set threshold, and sending an abnormal incoming call prompt to a background management center when the incoming call number carries out incoming calls exceeding the set times within the set duration, so that background workers can contact the incoming call number.
4. An AI director assistant system according to claim 1 or 3, capable of implementing intelligent interaction, characterized in that: the equipment auxiliary maintenance module comprises an equipment image acquisition unit, an equipment image processing unit and a state judgment unit; the equipment image acquisition unit is used for acquiring images of each piece of equipment at regular time and transmitting the images to the equipment image processing unit; the device image processing unit is used for identifying target devices in the image, reconstructing a blank picture, covering the identified target device image part into the blank picture to form a recombined picture, and performing gray processing and contour detection processing on the recombined picture to acquire contour information of the target devices and dust particles; the state judging unit is used for calculating the area ratio of the dust particles in the recombined picture at the current angle, judging whether the area ratio reaches a set area ratio threshold value, if so, suggesting that the equipment needs to be maintained and cleaned, and if not, suggesting that the equipment does not need to be maintained and cleaned.
5. The AI director assistant system according to claim 4, wherein: the working process of the equipment auxiliary maintenance module is as follows:
s21: regularly collecting images of each device;
s22: identifying target equipment in the image, reconstructing a blank picture, covering the identified image part of the target equipment into the blank picture to form a recombined picture, and performing gray processing and contour detection processing on the recombined picture to obtain contour information of the target equipment and each dust particle;
s23: and calculating the area ratio of the dust particles in the recombined picture at the current angle, and judging whether the area ratio reaches a set area ratio threshold value, wherein if the area ratio reaches the set area ratio threshold value, the equipment is recommended to be maintained and cleaned, and if the area ratio does not reach the set area ratio threshold value, the equipment is recommended not to be maintained and cleaned.
6. The AI director assistant system of claim 5 wherein said AI director assistant system is further configured to: in step S22, contour information of each dust particle, that is, area outline information formed of a plurality of dust particles.
7. The AI director assistant system according to claim 1, wherein: the program quality scoring module comprises a listening rate scoring unit, an audience independent scoring unit and a staff scoring unit; the listening rate scoring unit is used for scoring the program quality according to the listening rate scoring of the current live broadcast room; the audience autonomous scoring unit is used for scoring the program quality according to the autonomous scoring of the audience; and the staff scoring unit is used for scoring the program quality according to the autonomous scoring of the staff in the live broadcast room.
8. The AI director assistant system of claim 7 wherein: the formula for calculating the program quality score is as follows:
Z=w1*S+w2*T+w3*M
wherein Z represents the final program quality score, S represents the listening rate score of a live broadcast room, T represents the autonomous score of an audience, and M represents the autonomous score of staff in the live broadcast room; w1, w2 and w3 respectively represent the weights of all types of scores and are specifically set according to practical application.
9. The weighted average value of the multiple types of scores is adopted to represent the program quality, so that the evaluation of the program is more reasonable, and the comprehensive level of the program in a live broadcast room can be reflected better.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110663880.0A CN113556431A (en) | 2021-06-16 | 2021-06-16 | AI (Artificial intelligence) director assistant system capable of implementing intelligent interaction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110663880.0A CN113556431A (en) | 2021-06-16 | 2021-06-16 | AI (Artificial intelligence) director assistant system capable of implementing intelligent interaction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113556431A true CN113556431A (en) | 2021-10-26 |
Family
ID=78102147
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110663880.0A Withdrawn CN113556431A (en) | 2021-06-16 | 2021-06-16 | AI (Artificial intelligence) director assistant system capable of implementing intelligent interaction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113556431A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114745560A (en) * | 2022-02-23 | 2022-07-12 | 南京小灿灿网络科技有限公司 | AI (Artificial intelligence) director assistant system for implementing intelligent interactive effect |
-
2021
- 2021-06-16 CN CN202110663880.0A patent/CN113556431A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114745560A (en) * | 2022-02-23 | 2022-07-12 | 南京小灿灿网络科技有限公司 | AI (Artificial intelligence) director assistant system for implementing intelligent interactive effect |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105808694B (en) | Online customer service answering system and method | |
| CN101433072B (en) | Call centers with image or video based priority | |
| CN104936182B (en) | A kind of method and system of intelligence management and control fraudulent call | |
| CN105100521A (en) | Method and server for realizing ordered speech in teleconference | |
| EP3731519B1 (en) | Method for identifying identity in video conference and related apparatus | |
| CN110035187A (en) | A method of realizing AI and operator attendance seamless switching in the phone | |
| CN110445942A (en) | A kind of outer paging system of intelligence and intelligent calling-out method | |
| CN110705482A (en) | Personnel behavior alarm prompt system based on video AI intelligent analysis | |
| CN109119084B (en) | Dispatching communication method and system based on voice recognition | |
| CN111815297A (en) | Intelligent conference management system based on big data | |
| CN108989587A (en) | Application method of the IVR voice in the work of bank's post-loan management | |
| CN109714491B (en) | Intelligent voice outbound detection system based on voice mailbox | |
| CN113556431A (en) | AI (Artificial intelligence) director assistant system capable of implementing intelligent interaction | |
| CN103634448A (en) | Method for intelligently responding to incoming calls by voice | |
| US20230078210A1 (en) | Method and system for asynchronous reporting of emergency incidents | |
| CN113269039A (en) | On-duty personnel behavior identification method and system | |
| CN105262916A (en) | Help-seeking method and device for wearable equipment | |
| CN111787164B (en) | Incoming call prompting method and device, electronic equipment and computer readable medium | |
| CN113518156B (en) | Telephone switching method and device and electronic equipment | |
| CN110798379B (en) | VoIP signaling gateway identification method, device and readable storage medium | |
| CN109348164A (en) | A kind of self-service guarantee control system of teleconference | |
| CN114227702A (en) | Intelligent conference guiding method and device based on robot and robot | |
| CN210091231U (en) | Wisdom garden management system | |
| CN110958355A (en) | Multi-party communication system and method based on public network talkback and alarm telephone voice system | |
| CN113963476A (en) | Integrated intelligent management system |
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 | ||
| CB02 | Change of applicant information |
Address after: 518000 room 304, building A5, Tongle Road, Nanlian community, Nantou street, Nanshan District, Shenzhen, Guangdong Applicant after: Shenzhen Chenyuan Wangxin Technology Co.,Ltd. Address before: 518000 room 304, building A5, Tongle Road, Nanlian community, Nantou street, Nanshan District, Shenzhen, Guangdong Applicant before: Shenzhen Shengli New Technology Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20211026 |
|
| WW01 | Invention patent application withdrawn after publication |