CN114330369A - Local production marketing management method, device and equipment based on intelligent voice analysis - Google Patents
Local production marketing management method, device and equipment based on intelligent voice analysis Download PDFInfo
- Publication number
- CN114330369A CN114330369A CN202210251946.XA CN202210251946A CN114330369A CN 114330369 A CN114330369 A CN 114330369A CN 202210251946 A CN202210251946 A CN 202210251946A CN 114330369 A CN114330369 A CN 114330369A
- Authority
- CN
- China
- Prior art keywords
- information
- voice
- speaker
- identity
- speaking
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a local production marketing management method, a local production marketing management device and local production marketing management equipment based on intelligent voice analysis, wherein the method comprises the following steps: acquiring original voice data of a case scene; acquiring one or more sound characteristics and speaking information in the original voice data; obtaining an authorization record of a speaker, determining the identity of the speaker related to the voice characteristics, and associating the speaking information with the identity of the speaker one by one; carrying out voice recognition on the speaking information, and converting the speaking information into character information; carrying out calculation inference based on a knowledge graph on the character information, and extracting key information in the character information; and carrying out intelligent analysis based on the key information to support the business requirements of the real estate marketing management. The invention can solve the problem that the quality of the marketing skill in the existing real estate selling process can not be evaluated and effectively monitored, thereby more accurately obtaining the attention points and the real requirements of the customers, supporting the decision of managers and improving the marketing quality and effect.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method, a device and equipment for local production marketing management based on intelligent voice analysis.
Background
With the progress of neural networks and deep learning, speech technologies in various fields including speech recognition, semantic recognition, speaker recognition, etc. are increasingly widely used.
Customer reception and tracking are important links in the real estate marketing process. In the current reception process, client information is mainly manually input through a placement consultant, and due to various reasons, the phenomena of untimely, uncertain, unreal and the like of client visiting data may exist, and even more, the phenomena of no input and missing of important information can also occur, so that data distortion is caused, and support cannot be made for subsequent service development and management decision. And a few existing basic recording products in the market are weakened in function, and complex business functions such as extracting client multi-dimensional portrait labels, fuzzy semantic analysis, distinguishing conversation roles and accurately extracting keywords cannot be really achieved.
In conclusion, based on the latest intelligent voice technology, the problems that the quality of the sales call cannot be evaluated in the current real estate sales process, the whole visit process is not tracked by touch in the whole process, and the presence or absence of the promised promise of a business consultant cannot be effectively supervised can be solved. Therefore, the attention points and the real requirements of the customers can be more accurately acquired, and the marketing quality and effect are improved.
Disclosure of Invention
In view of the above technical problems, the present invention provides a method, an apparatus, and a device for local production marketing management based on intelligent voice analysis, so as to provide a technical solution that can solve the problems of reception and customer tracking distortion and inefficiency in the existing local production marketing.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of the disclosure.
According to an aspect of the present invention, a local delivery marketing management method based on intelligent voice analysis is provided, the method comprising: acquiring original voice data of a case scene; performing voiceprint recognition on the original voice data to obtain one or more voice characteristics in the original voice data and speaking information corresponding to the one or more voice characteristics; obtaining an authorization record of a speaker, determining the identity of the speaker associated with the voice characteristics according to one or more voice characteristics in the original voice data and the authorization record, associating the speaking information with the identity of the speaker one by one, deleting the original voice data, and deleting the voice characteristics and the associated speaking information which can not determine the identity of the speaker; carrying out voice recognition on the speaking information, and converting the speaking information into character information; carrying out calculation inference based on a knowledge graph on the character information, and extracting key information in the character information; and carrying out intelligent analysis based on the key information to support the business requirements of the real estate marketing management.
Further, after acquiring the original voice data of the scene of the case, the method further includes: and carrying out environmental noise elimination of the non-human voice frequency band signal based on hardware on the original voice data, and further eliminating the noise in the signal field by a voiceprint technology based on software.
Further, the determining the identity of the speaker associated with the voice feature according to the voice feature and the authorization record in the original voice data includes: after one or more sound features are obtained, comparing the similarity of the one or more sound features with feature data in an authorization database, and confirming the feature data with the similarity higher than a threshold value with the sound features in the authorization database one by one; and associating the identity of the speaker stored in the authorization database according to the feature data with the voice feature similarity higher than the threshold value in the authorization database.
Further, the characteristic data and the identity of the speaker in the authorization database are derived from an authorization record of the speaker, the authorization record occurs before the original voice data is obtained, and when the authorization record is obtained, the speaker is authorized to acquire and process the original voice data generated in the process of accessing the case by the speaker.
Further, the converting the speaking information into text information includes: converting the file of the speaking information into a frequency spectrum image by adopting a natural language processing technology based on a neural network; adopting an RNN (radio network-based) encoder to convert the spectrum image into an advanced feature identifier; and inputting the advanced feature identifier into another RNN to obtain the text information.
Further, the performing knowledge-graph-based computational inference on the text information to extract key information therein includes: according to the characteristics of the real estate marketing industry, the knowledge graph which meets the industry requirements is constructed, and entities such as real estate agents, clients and real estate and the like and the associated relations of the entities are constructed in a key way; updating information in the knowledge graph in real time, wherein the information comprises semantic relations among different entities and relations among different scenes; and when new character information is input, using a semantic matching network to perform computational reasoning based on the knowledge graph, and extracting the key information in the character information.
Further, the using a semantic matching network to perform computation inference based on the knowledge graph and extract the key information in the text information specifically includes: presetting a keyword list for real estate marketing; performing word segmentation on the character information; filtering interference words of non-key information according to a preset deactivation word list; converting words in the keyword list and the text information into a feature vector space through a neural network, and measuring the similarity between a feature vector corresponding to each word in the text information and a feature vector corresponding to the keyword list; if the similarity is higher than a preset threshold value, extracting a corresponding word in the text information as the key information; and performing computational reasoning based on the extracted key information and by combining the knowledge graph to obtain more associated key information.
Further, the performing intelligent analysis based on the key information includes: when the identity of the speaker corresponding to the key information is a client, performing client portrait tracing based on the key information to complete analysis of information such as client intention, focus, resistance and the like; and when the identity of the speaker corresponding to the key information is a employment consultant, analyzing the illegal call operation and the reception flow based on the key information.
According to a second aspect of the present disclosure, there is provided a local product marketing management device based on intelligent voice analysis, including: the audio acquisition module is used for acquiring original voice data of a case scene; the voice print recognition module is used for carrying out voice print recognition on the original voice data to obtain one or more voice characteristics in the original voice data and speaking information corresponding to the one or more voice characteristics; the identity matching module is used for acquiring an authorization record of a speaker, determining the identity of the speaker related to the voice characteristics according to one or more voice characteristics in the original voice data and the authorization record, associating the speaking information with the identity of the speaker one by one, deleting the original voice data, and deleting the voice characteristics and the related speaking information which can not confirm the identity of the speaker; the voice recognition module is used for carrying out voice recognition on the speaking information and converting the speaking information into character information; the semantic recognition module is used for carrying out calculation inference based on a knowledge graph on the character information and extracting key information in the character information; and the intelligent information analysis module is used for carrying out intelligent analysis based on the key information so as to support the business requirements of real estate marketing management.
According to a third aspect of the present disclosure, there is provided a local production marketing management device based on intelligent voice analysis, comprising: the local server, the local server is made up of memorizer, processor and computer program stored on the memorizer and can be run on the processor, also include: case audio data acquisition sub-equipment: for acquiring and recording audio data within the arena; the client authorizes the sub-device: the system is used for acquiring the authorization authentication of the speaker and generating an authorization record; wherein the processor executes the computer program with the steps of the method described above.
The technical scheme of the disclosure has the following beneficial effects:
according to the method, the device and the equipment for the marketing management of the real estate based on the intelligent voice analysis, the problem that the marketing skill quality cannot be evaluated and effectively supervised in the existing real estate marketing process can be solved, so that the attention points and the real requirements of customers can be more accurately acquired, the decision of managers is supported, and the marketing quality and effect are improved.
Drawings
Fig. 1 is a flowchart of a method for marketing management of local production based on intelligent voice analysis according to an embodiment of the present disclosure;
fig. 2 is a block diagram of a local production marketing management device based on intelligent voice analysis in an embodiment of the present specification;
fig. 3 is a terminal device for implementing a real estate marketing management method based on intelligent voice analysis in an embodiment of the present specification.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and the like. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.
Furthermore, the drawings are only schematic illustrations of the present disclosure. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
As shown in fig. 1, an embodiment of the present specification provides a local product marketing management method based on intelligent voice analysis, where an execution subject of the method may be a terminal device, where the terminal device may be a mobile phone, a tablet computer, a personal computer, and the like. The method specifically comprises the following steps S101-S106:
in step S101, raw voice data of a scene is acquired.
The original voice data can be collected through general monitoring equipment or special recording equipment, and the collected original voice data is stored in a local memory before being processed, so that privacy information is prevented from being leaked.
In step S102, voiceprint recognition is performed on the original voice data, and one or more voice features and speaking information corresponding to the one or more voice features in the original voice data are obtained.
In which voiceprint recognition can be used to perform sound feature-based classification of different human voices, putting all voices of the same feature in a group.
In step S103, obtaining an authorization record of a speaker, determining an identity of the speaker associated with the voice feature according to the one or more voice features in the original voice data and the authorization record, associating the speaking information with the identity of the speaker one by one, deleting the original voice data, and deleting the voice feature and the associated speaking information that cannot confirm the identity of the speaker.
The method comprises the steps of obtaining an authorization record of a speaker, obtaining voice characteristics of the speaker, comparing the voice characteristics in original voice data with the voice characteristics of the speaker after obtaining the voice characteristics of the speaker, if the voice characteristics can be compared, indicating that speaking information managed by the voice characteristics is authorized and can be processed, and if the voice characteristics cannot be compared, indicating that the speaking information is not authorized and cannot be processed, so that the privacy of the speaker is fully protected.
In step S104, the speaking information is subjected to speech recognition, and the speaking information is converted into text information.
Exemplarily, a natural language processing technology based on a neural network can be adopted to convert a file of the speaking information into a frequency spectrum image, then, an RNN network-based encoder is adopted to convert the frequency spectrum image into a high-level feature identifier, and the high-level feature identifier is input into another RNN network to obtain the text information.
In step S105, a computation inference based on a knowledge graph is performed on the text information, and key information in the text information is extracted.
The knowledge graph meeting the industry requirements can be constructed according to the characteristics of the real estate marketing industry, and entities such as real estate agents, clients and real estate and the like and the associated relation of the entities are constructed in a key way; in practical application, the information in the knowledge graph can be updated in real time, wherein the information comprises semantic relations between different entities and relations between different scenes; when new character information is input, a semantic matching network is used for carrying out calculation inference based on a knowledge graph and extracting key information in the character information.
And additionally, a semantic matching network is used to perform a knowledge graph-based computational inference process, specifically, a keyword list of the knowledge graph for real estate marketing is preset, then, segmenting words of the obtained text information, filtering interference words of non-key information in the text information according to a preset disabled word list, such as some words "or" and kayama ", and then, the unfiltered words in the keyword list and the text information are converted into the feature vector space through the neural network, and measure the similarity between the feature vector corresponding to each word in the text message and the feature vector corresponding to the keyword list, if the similarity is higher than the preset threshold value, and extracting words with similarity higher than a threshold value from the character information as key information, and performing computational reasoning by combining a formulated knowledge graph based on the extracted key information to obtain more associated key information.
In step S106, intelligent analysis is performed based on the key information to support business needs of the real estate marketing management.
Specifically, when the identity of the speaker corresponding to the key information is the client, the client profile is traced based on the key information, and the analysis of information such as the intention, the focus, and the resistance point of the client is completed.
And when the identity of the speaker corresponding to the key information is the employment advisor, analyzing the illegal call operation and the reception flow based on the key information, thereby carrying out assessment and scoring on the employment advisor.
After the intelligent analysis, the analysis results are stored in a database and may be presented to the administrator in the form of a web page or a terminal application.
In one embodiment, after step S101, the method further includes: and carrying out environmental noise elimination of the non-human voice frequency band signal based on hardware on the original voice data, and further eliminating the noise in the signal field by a voiceprint technology based on software.
Wherein, the purpose of the noise elimination is to eliminate other environmental noises except the voice information of the target task in the recorded data. Since the noise cancellation alone cannot achieve the optimal effect, a method of combining hardware and software is adopted. The hardware noise elimination eliminates the environmental noise by filtering out the signals of the non-human voice frequency band, and then further eliminates the noise in the signal field by adopting the voiceprint technology. Specifically, because the frequency range of the voice of the human speaking is mainly concentrated on 20-3KHz, the hardware analog band-pass filter covering the frequency band can be adopted to firstly weaken the voice outside the range; meanwhile, after converting the sound into a digital signal, a digital filtering technique may be further employed to filter out signals outside the frequency range of a given voiceprint in the frequency domain.
In one embodiment, step S103 specifically includes: after one or more sound features are obtained, comparing the similarity of the one or more sound features with feature data in an authorization database, and confirming the feature data with the similarity higher than a threshold value with the sound features in the authorization database one by one; and associating the identity of the speaker stored in the authorization database according to the feature data with the voice feature similarity higher than the threshold value in the authorization database.
In addition, speakers in the case field are mainly marketing personnel and clients, the number of the marketing personnel is substantially fixed, and the number of the clients changes every day, so that in the design of the database, an independent database can be set for all the marketing personnel, information in the database corresponding to the clients is classified according to dates, after one or more sound characteristics are obtained, similarity comparison is carried out on the information in the database corresponding to the marketing personnel, whether the sound characteristics belong to the marketing personnel is determined, and if not, comparison is carried out on the information in the database corresponding to the clients on the dates. Thus, the running speed can be greatly improved.
Additionally, the characteristic data and the identity of the speaker in the authorization database are derived from an authorization record of the speaker, the authorization record occurring prior to obtaining the raw speech data, and upon obtaining the authorization record, authorization is obtained for the speaker to capture and process the raw speech data generated during the speaker's visit to the case.
The speaker authorization process may exemplarily include reading a certificate of the speaker by using a certificate reading device to obtain related identity information, such as name, gender, and the like, or confirming the identity information by using third software through face recognition, recording the voice of the speaker by using the certificate reading device, a professional recording device, a field monitoring device, a mobile phone terminal, and the like, analyzing the voice characteristics, and storing the acquired voice characteristics, identity information, and authorization mode of the speaker as authorization records in a database.
In addition, for ease of understanding, the present disclosure, according to the above-described embodiments, makes a simple exemplary application description of the method of the present disclosure, but the description should not be taken as a limitation of the disclosure, as the marketer customer comes to the real estate arena, the marketer comes to the reception, and requests authorization from the customer. If the client accepts the authorization, the related identity information and the voice characteristics of the client are recorded. Subsequently, in the conversation between the marketer and the client, the voice generated by the client in the case is recorded by the monitoring device or the professional recording device on the case and stored as the original voice data in the local server. Then, the executing subject starts to process the original voice data, including noise elimination and voiceprint recognition, so as to obtain one or more voice characteristics and corresponding speaking information in the original voice data. And then obtaining authorization records in the database, namely obtaining the identity information and the corresponding sound characteristics in the data, inputting the sound characteristics and the corresponding speaking information in the original voice data into the data, comparing the sound characteristics and the corresponding speaking information one by one, and associating the speaking information with the identity information stored in the authorization database. If the client refuses the authorization, the voice data generated by the client in the case is recorded, so that the voice characteristic corresponding to the client cannot be associated in the database, and all the information belonging to the client is deleted. The associated spoken information is then analyzed for identity, and the analysis results can be used to support business needs of the property marketing management, as described in the embodiments above.
Based on the same idea, an exemplary embodiment of the present disclosure further provides a local product marketing management device based on intelligent voice analysis, as shown in fig. 2, the local product marketing management device 200 based on intelligent voice analysis includes: the audio acquisition module 201 is used for acquiring original voice data of a case scene; a voiceprint recognition module 202, configured to perform voiceprint recognition on the original voice data to obtain one or more voice features in the original voice data and speaking information corresponding to the one or more voice features; the identity matching module 203 is used for acquiring an authorization record of a speaker, determining the identity of the speaker related to the voice characteristics according to one or more voice characteristics in the original voice data and the authorization record, associating the speaking information with the identity of the speaker one by one, deleting the original voice data, and deleting the voice characteristics and the related speaking information which can not confirm the identity of the speaker; the voice recognition module 204 is used for carrying out voice recognition on the speaking information and converting the speaking information into character information; the semantic recognition module 205 is used for performing computation inference based on a knowledge graph on the character information and extracting key information in the character information; and the intelligent information analysis module 206 carries out intelligent analysis based on the key information so as to support the business requirements of the real estate marketing management.
The specific details of each module/unit in the above-mentioned apparatus have been described in detail in the method section, and the details that are not disclosed may refer to the contents of the method section, and thus are not described again.
Based on the same idea, the embodiment of the present specification further provides a local production marketing management device based on intelligent voice analysis, as shown in fig. 3.
The smart voice analysis based local production management device may have a large difference due to different configurations or performances, and may include one or more than one customer authorization sub-device 301, such as a tablet computer, a certificate reading device, and the like. An audio acquisition sub-device 302, such as a standard or custom sound recording device. Also included is a local server sub-device 303, where the local server sub-device 303 includes a processor 3031 and a memory 3032, and the memory 3032 may store one or more stored applications or data. The memory 3032 may include readable media in the form of volatile memory units, such as Random Access Memory (RAM) and/or cache memory units, and may further include read-only memory units, among others. The application programs stored in memory 3032 may include one or more program modules (not shown), including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment. Further, the processor 3031 may be arranged in communication with the memory 3032 to execute a series of computer-executable instructions in the memory 3032 on the device. The smart voice analytics-based location management device may also include one or more power supplies 304, one or more wired or wireless network interfaces 305, one or more I/O interfaces (input output interfaces) 306, one or more external devices 307 (e.g., keyboard, pointing device, bluetooth device, etc.), may also communicate with one or more devices that enable a user to interact with the device, and/or communicate with any device (e.g., router, modem, etc.) that enables the device to communicate with one or more other computing devices. Such communication may occur via the I/O interface 306.
In particular, in the embodiment, the intelligent voice analysis-based local production marketing management device includes a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the intelligent voice analysis-based local production marketing management device, and the one or more programs configured to be executed by the one or more processors include computer-executable instructions for:
acquiring original voice data of a case scene; performing voiceprint recognition on the original voice data to obtain one or more voice characteristics in the original voice data and speaking information corresponding to the one or more voice characteristics; obtaining an authorization record of a speaker, determining the identity of the speaker associated with the voice characteristics according to one or more voice characteristics in the original voice data and the authorization record, associating the speaking information with the identity of the speaker one by one, deleting the original voice data, and deleting the voice characteristics and the associated speaking information which can not determine the identity of the speaker; carrying out voice recognition on the speaking information, and converting the speaking information into character information; carrying out calculation inference based on a knowledge graph on the character information, and extracting key information in the character information; and carrying out intelligent analysis based on the key information to support the business requirements of the real estate marketing management.
Based on the same idea, the exemplary embodiments of the present disclosure also provide a computer-readable storage medium on which a program product capable of implementing the above-described method of the present specification is stored. In some possible embodiments, various aspects of the disclosure may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps according to various exemplary embodiments of the disclosure described in the above-mentioned "exemplary methods" section of this specification, when the program product is run on the terminal device.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the exemplary embodiments of the present disclosure.
Furthermore, the above-described figures are merely schematic illustrations of processes included in methods according to exemplary embodiments of the present disclosure, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.
It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functions of two or more of the modules described above may be embodied in one module or unit according to exemplary embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. A local production marketing management method based on intelligent voice analysis is characterized by comprising the following steps:
acquiring original voice data of a case scene;
performing voiceprint recognition on the original voice data to obtain one or more voice characteristics in the original voice data and speaking information corresponding to the one or more voice characteristics;
obtaining an authorization record of a speaker, determining the identity of the speaker associated with the voice characteristics according to one or more voice characteristics in the original voice data and the authorization record, associating the speaking information with the identity of the speaker one by one, deleting the original voice data, and deleting the voice characteristics and the associated speaking information which can not determine the identity of the speaker;
carrying out voice recognition on the speaking information, and converting the speaking information into character information;
carrying out calculation inference based on a knowledge graph on the character information, and extracting key information in the character information;
and carrying out intelligent analysis based on the key information to support the business requirements of the real estate marketing management.
2. The intelligent voice analysis-based local production marketing management method according to claim 1, further comprising, after acquiring the raw voice data of a scene of a case, the steps of:
and carrying out environmental noise elimination of the non-human voice frequency band signal based on hardware on the original voice data, and further eliminating the noise in the signal field by a voiceprint technology based on software.
3. The intelligent voice analysis-based local productivity marketing management method according to claim 1, wherein the determining the identity of the speaker associated with the voice feature according to the voice feature or features in the raw voice data and the authorization record comprises:
after one or more sound features are obtained, comparing the similarity of the one or more sound features with feature data in an authorization database, and confirming the feature data with the similarity higher than a threshold value with the sound features in the authorization database one by one;
and associating the identity of the speaker stored in the authorization database according to the feature data with the voice feature similarity higher than the threshold value in the authorization database.
4. The intelligent voice analysis-based local productivity marketing management method according to claim 3, wherein the characteristic data in the authorization database and the identity of the speaker are derived from an authorization record of the speaker, the authorization record occurring before the original voice data is obtained, and when the authorization record is obtained, the speaker is authorized to acquire and process the original voice data generated during the visit to a case.
5. The intelligent speech analysis-based local productivity marketing management method according to claim 1, wherein the converting the speaking information into text information comprises:
converting the file of the speaking information into a frequency spectrum image by adopting a natural language processing technology based on a neural network;
adopting an RNN (radio network-based) encoder to convert the spectrum image into an advanced feature identifier;
and inputting the advanced feature identifier into another RNN to obtain the text information.
6. The intelligent voice analysis-based local production marketing management method according to claim 1, wherein the performing knowledge-graph-based computational inference on the text information to extract key information therein comprises:
according to the characteristics of the real estate marketing industry, the knowledge graph which meets the industry requirements is constructed, and the real estate agency, the client and the real estate entity and the associated relation of the client and the real estate agency are constructed in a key mode;
updating information in the knowledge graph in real time, wherein the information comprises semantic relations among different entities and relations among different scenes;
and when new character information is input, using a semantic matching network to perform computational reasoning based on the knowledge graph, and extracting the key information in the character information.
7. The intelligent voice analysis-based local production marketing management method according to claim 6, wherein the using of the semantic matching network to perform the computation inference based on the knowledge graph to extract the key information in the text information specifically comprises:
presetting a keyword list for real estate marketing;
performing word segmentation on the character information;
filtering interference words of non-key information according to a preset deactivation word list;
converting words in the keyword list and the text information into a feature vector space through a neural network, and measuring the similarity between a feature vector corresponding to each word in the text information and a feature vector corresponding to the keyword list;
if the similarity is higher than a preset threshold value, extracting a corresponding word in the text information as the key information;
and performing computational reasoning based on the extracted key information and by combining the knowledge graph to obtain more associated key information.
8. The intelligent voice analysis-based local production marketing management method according to claim 1, wherein the intelligent analysis based on the key information comprises:
when the identity of the speaker corresponding to the key information is a client, performing client portrait tracing based on the key information to complete analysis of information of intention, focus and resistance of the client;
and when the identity of the speaker corresponding to the key information is a employment consultant, analyzing the illegal call operation and the reception flow based on the key information.
9. An intelligent voice analysis-based local production marketing management device, comprising:
the audio acquisition module is used for acquiring original voice data of a case scene;
the voice print recognition module is used for carrying out voice print recognition on the original voice data to obtain one or more voice characteristics in the original voice data and speaking information corresponding to the one or more voice characteristics;
the identity matching module is used for acquiring an authorization record of a speaker, determining the identity of the speaker related to the voice characteristics according to one or more voice characteristics in the original voice data and the authorization record, associating the speaking information with the identity of the speaker one by one, deleting the original voice data, and deleting the voice characteristics and the related speaking information which can not confirm the identity of the speaker;
the voice recognition module is used for carrying out voice recognition on the speaking information and converting the speaking information into character information;
the semantic recognition module is used for carrying out calculation inference based on a knowledge graph on the character information and extracting key information in the character information;
and the intelligent information analysis module is used for carrying out intelligent analysis based on the key information so as to support the business requirements of real estate marketing management.
10. A local production marketing management device based on intelligent voice analysis is characterized by comprising: the local server, the local server is made up of memorizer, processor and computer program stored on the memorizer and can be run on the processor, also include:
case audio data acquisition sub-equipment: for acquiring and recording audio data within the arena;
the client authorizes the sub-device: the system is used for acquiring the authorization authentication of the speaker and generating an authorization record;
wherein the steps of the method of any one of claims 1 to 8 are implemented by the processor when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210251946.XA CN114330369A (en) | 2022-03-15 | 2022-03-15 | Local production marketing management method, device and equipment based on intelligent voice analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210251946.XA CN114330369A (en) | 2022-03-15 | 2022-03-15 | Local production marketing management method, device and equipment based on intelligent voice analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114330369A true CN114330369A (en) | 2022-04-12 |
Family
ID=81033420
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210251946.XA Pending CN114330369A (en) | 2022-03-15 | 2022-03-15 | Local production marketing management method, device and equipment based on intelligent voice analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114330369A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117391822A (en) * | 2023-12-11 | 2024-01-12 | 中汽传媒(天津)有限公司 | VR virtual reality digital display method and system for automobile marketing |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106328122A (en) * | 2016-08-19 | 2017-01-11 | 深圳市唯特视科技有限公司 | Voice identification method using long-short term memory model recurrent neural network |
| CN109145123A (en) * | 2018-09-30 | 2019-01-04 | 国信优易数据有限公司 | Construction method, intelligent interactive method, system and the electronic equipment of knowledge mapping model |
| CN110335612A (en) * | 2019-07-11 | 2019-10-15 | 招商局金融科技有限公司 | Minutes generation method, device and storage medium based on speech recognition |
| CN112712393A (en) * | 2021-01-04 | 2021-04-27 | 上海明略人工智能(集团)有限公司 | Method and device for adjusting house source price |
-
2022
- 2022-03-15 CN CN202210251946.XA patent/CN114330369A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106328122A (en) * | 2016-08-19 | 2017-01-11 | 深圳市唯特视科技有限公司 | Voice identification method using long-short term memory model recurrent neural network |
| CN109145123A (en) * | 2018-09-30 | 2019-01-04 | 国信优易数据有限公司 | Construction method, intelligent interactive method, system and the electronic equipment of knowledge mapping model |
| CN110335612A (en) * | 2019-07-11 | 2019-10-15 | 招商局金融科技有限公司 | Minutes generation method, device and storage medium based on speech recognition |
| CN112712393A (en) * | 2021-01-04 | 2021-04-27 | 上海明略人工智能(集团)有限公司 | Method and device for adjusting house source price |
Non-Patent Citations (3)
| Title |
|---|
| 全国计算机职业技能教材编写委员会: "《计算机程序设计员（高级）》", 31 May 2009, pages: 70 * |
| 袁鹏飞 等: "《专利战略与企业发展》", 30 November 2017, 天津人民出版社, pages: 287 - 288 * |
| 黄勇: "《智慧养老》", 31 July 2016, 中国社会出版社, pages: 173 - 177 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117391822A (en) * | 2023-12-11 | 2024-01-12 | 中汽传媒(天津)有限公司 | VR virtual reality digital display method and system for automobile marketing |
| CN117391822B (en) * | 2023-12-11 | 2024-03-15 | 中汽传媒(天津)有限公司 | VR virtual reality digital display method and system for automobile marketing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20100211551A1 (en) | Method, system, and computer readable recording medium for filtering obscene contents | |
| CN112949708B (en) | Emotion recognition method, emotion recognition device, computer equipment and storage medium | |
| CN113011889B (en) | Account anomaly identification method, system, device, equipment and medium | |
| TWI807172B (en) | Active risk control method and system based on intelligent interaction | |
| CN107977678A (en) | Method and apparatus for output information | |
| CN107515852A (en) | Particular type of information recognition methods and device | |
| JPH11161670A (en) | Method, device, and system for information filtering | |
| CN114330369A (en) | Local production marketing management method, device and equipment based on intelligent voice analysis | |
| US10446138B2 (en) | System and method for assessing audio files for transcription services | |
| CN113850077A (en) | Topic identification method, device, server and medium based on artificial intelligence | |
| Altalbe | RETRACTED ARTICLE: Audio fingerprint analysis for speech processing using deep learning method | |
| CN112287111A (en) | Text processing method and related device | |
| CN113746780A (en) | Abnormal host detection method, device, medium and equipment based on host image | |
| Vasconcellos et al. | Analyzing polarization and toxicity on political debate in brazilian TikTok videos transcriptions | |
| CN114119037B (en) | Marketing anti-cheating system based on big data | |
| CN113421590B (en) | Abnormal behavior detection method, device, equipment and storage medium | |
| CN112783799B (en) | Software daemon testing method and device | |
| Medikonda et al. | Higher order information set based features for text-independent speaker identification | |
| CN115329173A (en) | Method and device for determining enterprise credit based on public opinion monitoring | |
| Wang et al. | Fault diagnosis using improved pattern spectrum and fruit fly optimization algorithm–support vector machine | |
| CN109409127B (en) | Method and device for generating network data security policy and storage medium | |
| Arcos et al. | Ideal neighbourhood mask for speech enhancement | |
| CN113963440A (en) | Customer purchase intention analysis method and device | |
| ALI et al. | A Novel Leader Election Algorithm for Honeycomb Mesh Networks | |
| CN113918941A (en) | Abnormal behavior detection method and device, computing equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220412 |
|
| RJ01 | Rejection of invention patent application after publication |