An intelligent virtual public announcement method and public announcement system

Abstract

The present invention belongs to the technical field of information disclosure, and discloses an intelligent virtual disclosure method and disclosure system. The virtual disclosure method comprises: receiving first text data sent by a server; identifying the first text data and converting it into first audio data; identifying the first audio data and converting it into second text data; judging whether the first text data is the same as the second text data, and when the two are the same, loading the first audio data into a virtual character and making a virtual disclosure. The virtual disclosure system comprises a server, several clients and software, and the server is connected to each client through a network. The server is used to store and send the first text data, and the software is loaded in the client to execute the method. The present invention no longer requires manual participation when updating the content of the virtual disclosure, and has good real-time performance when updating the content.

Description

Technical Field

[0001] The present invention relates to the technical field of information disclosure, and in particular to an intelligent virtual disclosure method and disclosure system. Background Art

[0002] With the advent of the information age, various information disclosure devices have gradually entered people's daily lives, such as rolling posters on bus stations, rolling LED screens on taxis, information display stands at the stairwells of shopping malls, business disclosure boards in banks, etc. They provide great convenience for people to obtain external information.

[0003] And with the gradual development of informatization, the disclosure methods of various information disclosure devices have gradually changed from single text disclosure to audio disclosure, video disclosure, and then to virtual disclosure combined with virtual characters. Among them, the virtual disclosure, as a novel disclosure method, not only transmits the disclosure information to people through itself, but also helps to mobilize people's subjective willingness to obtain the disclosure information. Thereby further improving the effectiveness of information disclosure and transmission.

[0004] Currently, due to technical limitations, when the content of a virtual announcement needs to be updated, technicians are generally required to go to the information announcement device site, input the original text information into the information announcement device, and then confirm that the content played by the virtual character is consistent with the text information before the content update of the virtual announcement is confirmed to be complete. This method has the following defects in actual use: on the one hand, it consumes a lot of manpower, which will reduce the subjectivity of technicians in updating information, thereby reducing the frequency of information updates during virtual announcements; on the other hand, it reduces the real-time nature of content updates, which is not conducive to the popularization and application of this type of announcement method. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent virtual public announcement method and public announcement system, which solves the technical problems that the existing virtual public announcement not only consumes a lot of manpower but also has poor real-time performance when updating content.

[0006] To achieve the above object, the present invention proposes the following technical solutions:

[0007] An intelligent virtual public announcement method, comprising:

[0008] Receiving first text data sent by a server; the first text data includes information to be publicized, and the first text data is stored in the server;

[0009] recognizing the first text data and converting it into first audio data;

[0010] Recognizing the first audio data and converting it into second text data;

[0011] Determine whether the first text data and the second text data are the same, and if they are the same, load the first audio data into the virtual character and store it;

[0012] The first audio data is virtually publicized through the virtual character.

[0013] Furthermore, the determining whether the first text data is the same as the second text data further includes:

[0014] When the two are different, locating different positions of the first text data and the second text data in the first text data, and generating third text data from the characters at the different positions in the first text data;

[0015] recognizing the third text data and converting it into second audio data;

[0016] recognizing the second audio data and converting it into fourth text data;

[0017] It is determined whether the third text data is identical to the fourth text data. If they are identical, the audio at the corresponding position of the first audio data is replaced with the second audio data and then loaded into the virtual character and stored.

[0018] Furthermore, the determining whether the third text data is the same as the fourth text data further includes:

[0019] When the two are different, sending the third text data and a first request to the server; the first request is used to request the server to convert the third text data into audio;

[0020] Receiving third audio data sent by the server, where the third audio data is audio obtained after the server converts the third text data;

[0021] The audio at the corresponding position of the first audio data is replaced with the third audio data and then loaded into the virtual character and stored.

[0022] Furthermore, the determining whether the first text data is the same as the second text data further includes:

[0023] When the two are the same, the audio data previously virtually announced is overwritten with the first audio data.

[0024] Furthermore, the determining whether the first text data is the same as the second text data further includes:

[0025] When the two are the same, the text data corresponding to the previously virtually publicized audio data is stored.

[0026] Furthermore, before receiving the first text data sent by the server, the method further includes:

[0027] A publicity period is set, and virtual publicity is performed through the virtual character in each publicity period; the publicity period is negatively correlated with the flow of people.

[0028] An intelligent virtual public announcement system includes a server, several clients and software, wherein the server is connected to any of the clients via a network;

[0029] The server is used to store first text data and send the first text data to the client, wherein the first text data includes information to be publicized;

[0030] The client includes a first converter, a second converter, a virtual synthesizer and a display;

[0031] The first converter is used to convert the first text data into the first audio data, or convert the third text data into the second audio data;

[0032] The second converter is used to convert the first audio data into second text data, or convert the second audio data into fourth text data;

[0033] The virtual synthesizer is used to realize virtual public display of the first audio data through a virtual character;

[0034] The display is used to display virtual announcements;

[0035] The software is used to execute the described method.

[0036] Furthermore, the server includes a third converter, and the third converter is used to convert the text data into audio data.

[0037] Furthermore, the client includes a memory, and the memory is used to store text data corresponding to the audio data during the virtual announcement.

[0038] Furthermore, the client includes a clock module, and the clock module is used to set a publicity period.

[0039] Beneficial effects:

[0040] It can be seen from the above technical solutions that in order to solve the defects of updating content in the existing virtual public announcement, the technical solution of the present invention provides an intelligent virtual public announcement method and public announcement system.

[0041] The virtual public announcement method comprises: first, receiving first text data sent by a server, wherein the first text data includes information to be announced. Since the information to be announced is transmitted in the form of text, it is beneficial to reduce the amount of data when the information is transmitted and the amount of storage when the client stores the information; thus, it is beneficial to improve the data processing efficiency and the real-time performance of the final virtual public announcement.

[0042] Secondly, the first text data is identified and converted into first audio data. The first audio data is the content that needs to be loaded into the virtual character later. In order to ensure whether the first audio data is accurate, the existing technology is that personnel go to the site to load it directly into the virtual character for virtual public display and make a manual judgment.

[0043] According to common knowledge, the number of clients is generally large and relatively scattered. Therefore, in order to improve the intelligence of the judgment process and reduce manpower consumption, the following contents are continued: the first audio data is identified and reversely converted into the second text data; then the first text data and the second text data are judged to be the same. If they are the same, it indicates that the first audio data is the result of correct recognition and conversion. At this time, the first audio data can be loaded into the virtual character for virtual public display.

[0044] From the above steps, it can be seen that in order to reduce the problem of high manpower consumption and poor real-time performance when updating content in virtual public notices: on the one hand, during data transmission, text form is used to reduce the pressure of data transmission, thereby improving the efficiency of data transmission. On the other hand, the reverse conversion method is used to achieve self-confirmation of the accuracy of the public notice content. Since this process can be completed by the server and the client itself, there is no corresponding manpower consumption, and the content update has good real-time performance. In addition, the content update frequency during virtual public notices is increased, which facilitates the popularization and application of this type of public notice method.

[0045] The present invention also provides an intelligent virtual public announcement system. The virtual public announcement system includes a server, a plurality of clients and software, wherein the server is connected to each client via a network. The server is used to store and send first text data, and the software is loaded in the client to execute the method. The public announcement system no longer requires manual participation when updating the content of the virtual public announcement, and has good real-time performance when updating the content.

[0046] It should be appreciated that all combinations of the foregoing concepts, as well as additional concepts described in greater detail below, may be considered to be part of the inventive subject matter of the present disclosure, provided such concepts are not mutually inconsistent.

[0047] The foregoing and other aspects, embodiments and features of the present invention can be more fully understood from the following description in conjunction with the accompanying drawings. Other additional aspects of the present invention, such as the features and / or beneficial effects of the exemplary embodiments, will be apparent from the following description or learned from the practice of the specific embodiments according to the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The drawings are not intended to be drawn to scale. In the drawings, each identical or nearly identical component shown in various figures may be represented by the same reference numeral. For clarity, not every component is labeled in every figure. Embodiments of various aspects of the present invention will now be described by way of example and with reference to the accompanying drawings, in which:

[0049] Figure 1 It is a flow chart of the intelligent virtual public announcement method described in an embodiment of the present invention;

[0050] Figure 2 for Figure 1 A processing flow chart when the first text data and the second text data are different;

[0051] Figure 3 for Figure 2 A processing flow chart when the third text data is different from the fourth text data;

[0052] Figure 4 for Figure 1 A flowchart of the processing of previously publicized content;

[0053] Figure 5 for Figure 1 Another processing flow chart of the previously publicized content;

[0054] Figure 6 for Figure 1 A flowchart of a specific implementation method for performing virtual publicity in;

[0055] Figure 7 for Figure 1 A flowchart of another specific implementation method when performing virtual publicity;

[0056] Figure 8 It is a structural diagram of the intelligent virtual public announcement system described in an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Unless otherwise defined, the technical terms or scientific terms used herein should be the common meanings understood by people with ordinary skills in the field to which the present invention belongs.

[0058] The words "first", "second" and similar words used in the patent application specification and claims of the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, unless the context clearly indicates otherwise, the singular form of "a", "an" or "the" and other similar words do not indicate a quantitative limitation, but indicate the existence of at least one. "Include" or "comprise" and other similar words mean that the elements or objects appearing before "include" or "comprise" include the features, wholes, steps, operations, elements and / or components listed after "include" or "comprise", and do not exclude the existence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0059] The embodiment of the present invention provides an intelligent virtual public announcement method. The virtual public announcement method includes: receiving first text data; identifying the first text data and converting it into first audio data; identifying the first audio data and converting it into second text data; and performing a virtual public announcement when the first text data is consistent with the second text data. Since the received data type is in text form, the pressure of data transmission is greatly reduced; and the accuracy of the content of the final virtual public announcement is self-confirmed by reverse conversion, thereby eliminating the manual consumption in the existing process and greatly improving the real-time update.

[0060] The embodiment of the present invention also provides an intelligent virtual public announcement system. The virtual public announcement system is built based on the virtual public announcement method, so that human participation is no longer required when updating the content of the virtual public announcement, and the content is updated in real time.

[0061] Example 1

[0062] The disclosed intelligent virtual public announcement method is further specifically introduced below in conjunction with the embodiments shown in the accompanying drawings.

[0063] like Figure 1As shown, the virtual publicity method includes:

[0064] Step S102: receiving first text data sent by a server; the first text data includes information to be publicized, and the first text data is stored in the server.

[0065] In this step, the information contained in the first text data is the content of the final virtual announcement. The main form of virtual announcement is to announce the information in the form of voice broadcast by a virtual character. The purpose of transmitting in text format in this step is that the distance between the server and the client is large, and the number of clients is large and scattered. For example, the business announcement boards of bank branches are scattered in various locations in towns and cities, and the number is very large. Therefore, using text format to transmit the announcement information greatly improves the data transmission efficiency and ensures the stability of data transmission.

[0066] Step S104: Identify the first text data and convert it into first audio data.

[0067] In this step, the first audio data is the information that needs to be loaded into the virtual character later. In order to confirm the accuracy of the first audio data, the existing method is to manually audition and confirm it on site. However, from the above analysis, it can be seen that manual confirmation requires a lot of manpower and material resources, and will reduce the real-time nature of the announcement. As for the content of the announcement, the reduction in real-time nature will reduce the value and effectiveness of the announcement information itself.

[0068] Therefore, this embodiment adopts the following method:

[0069] Step S106: Identify the first audio data and convert it into second text data.

[0070] This step is the reverse conversion process of the first audio data, that is, the audio data is reconverted into text data. Since the two conversion processes are performed by different converters, when the reversely converted text data is consistent with the original text data, it indicates that the audio data is accurate.

[0071] Step S108: determine whether the first text data is identical to the second text data; if they are identical, load the first audio data into the virtual character and store it.

[0072] Step S110: virtually publicizing the first audio data through the virtual character.

[0073] Based on step S106, when the first text data is consistent with the second text data, it indicates that the public information in the first audio data is accurate. Therefore, it is sufficient to load it into the virtual character and perform virtual public announcement through steps S108 to S110.

[0074] like Figure 2 As shown, for step S108, when the first text data is different from the second text data, it indicates that the public information in the first audio data is incorrect. Therefore, the following steps are continued:

[0075] Step S109.2: when the two are different, locate the different positions of the first text data and the second text data in the first text data, and generate third text data from the characters in the different positions in the first text data;

[0076] Step S109.4, identifying the third text data and converting it into second audio data;

[0077] Step S109.6, identifying the second audio data and converting it into fourth text data;

[0078] Step S109.8: Determine whether the third text data is identical to the fourth text data. If they are identical, replace the audio at the corresponding position of the first audio data with the second audio data and then load it into the virtual character and store it.

[0079] Since the converted first audio data is only partially abnormal, in order to reduce the amount of data processing, reduce the difficulty of data processing, and thus improve data processing efficiency, only the abnormal content is reprocessed. That is, through steps S109.2-S109.6, the abnormal position is located, reconverted, and re-converted for self-confirmation. When the third text data is the same as the fourth text data, it indicates that the abnormal position has been resolved. At this time, the audio data after the corresponding position of the first audio data is replaced by the second audio data contains the correct public announcement information, which can be loaded into the virtual character for virtual announcement.

[0080] like Figure 3 As shown, for step S109.8, when the third text data is still different from the fourth text data, it indicates that the client has difficulty recognizing the characters in the third text data. At this time, the success rate of repeated recognition is extremely low. Therefore, continue to perform the following steps:

[0081] Step S109.8.2: When the two are different, sending the third text data and a first request to the server; the first request is used to request the server to convert the third text data into audio;

[0082] Step S109.8.4, receiving third audio data sent by the server, wherein the third audio data is audio obtained after the server converts the third text data;

[0083] Step S109.8.6: Replace the audio at the corresponding position of the first audio data with the third audio data, and then load it into the virtual character and store it.

[0084] Steps S109.8.2 to S109.8.4 are used to send the third text data corresponding to the abnormal position to the server and send the first request. At this time, the server can directly transmit the accurate third audio data corresponding to the third text data to the corresponding client. At this time, the corresponding position of the first audio data is replaced with the third audio data and then loaded into the virtual character for virtual public display.

[0085] Since the third audio data received from the server is only related to the abnormal position, it will not have an adverse impact on the overall transmission volume and transmission efficiency during data transmission.

[0086] like Figure 4 As shown, since the update frequency of the publicized content is generally high, in order to reduce the storage pressure of the client. When performing step S108, the following operations are also performed:

[0087] Step S108': when the two are the same, the first audio data is used to overwrite the audio data of the previous virtual public announcement.

[0088] like Figure 5 As shown, in order to archive the publicized content for future viewing when needed, after performing step S108', the following operations are also performed:

[0089] Step S108”: when the two are the same, the text data corresponding to the previously virtually publicized audio data is stored.

[0090] Since the audio data of the previous virtual announcement is stored here as text data, the storage volume is small, which will not increase the storage pressure and will not have an adverse impact on the normal virtual announcement.

[0091] like Figure 6 As shown, in order to improve the effectiveness of the announcement, it is generally necessary to adjust the announcement frequency according to the flow of people. Based on this, before step S102, it also includes:

[0092] S101, setting a publicity period, and performing virtual publicity through the virtual character in each publicity period; the publicity period is negatively correlated with the flow of people.

[0093] Virtual public disclosure is information disclosure conducted with virtual characters as the main body. Virtual characters not only have anthropomorphic language, but also have certain appearance characteristics based on image design.

[0094] Therefore, Figure 7As shown, as an optional implementation, when performing step S108, the following is also included:

[0095] Step S108.2: Match the first audio data to a corresponding virtual character based on a preset public announcement item; the appearance characteristics of the virtual character are associated with the public announcement item, and the public announcement item is a classified statistical result of the public announcement information.

[0096] Through this step, the virtual public announcement method can automatically match virtual characters according to the public announcement information on the basis of correct voice broadcasting. For example, in the specific implementation, the public announcement items include safety publicity items and business publicity items. At this time, the virtual characters corresponding to the safety publicity items are security personnel images, and the virtual characters corresponding to the business publicity items are professional images. This not only further improves the intelligence of the virtual public announcement method, but also gives full play to the characteristics of the virtual characters themselves, achieving the effect of improving the public announcement effect.

[0097] Specifically, in order to improve the efficiency and accuracy of matching the first audio data, identification and matching are performed through keywords. Therefore, as an optional implementation, before step S108.2, the following is also included:

[0098] Step S108.1: extract keywords from the first audio data, where the keywords are associated with preset public announcement items.

[0099] At this time, based on the steps S108.1-S108.2, the first audio data can be quickly loaded into the adapted virtual character image, and this process also does not require human participation and can be completed by the client itself. In addition, the keyword matching method also has the advantage of high virtual character matching accuracy.

[0100] The above program can be run in the processor, or it can be stored in the memory (or computer-readable medium), which includes permanent and non-permanent, removable and non-removable media. Information storage can be achieved by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined in this article, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0101] These computer programs can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in one or more blocks can be implemented by different modules corresponding to different steps.

[0102] Example 2

[0103] The following is a further detailed introduction to the disclosed intelligent virtual public announcement system in conjunction with the embodiments shown in the accompanying drawings.

[0104] like Figure 8 As shown, the intelligent virtual public announcement system is built based on the virtual public announcement method described in Example 1, including a server, several clients and software, and the server is connected to each client through a network.

[0105] The server is used to store the first text data and send the first text data to the client.

[0106] The client includes a first converter, a second converter, a virtual synthesizer and a display.

[0107] The first converter is used to convert any text data into corresponding audio data, such as converting the first text data in Example 1 into the first audio data. The second converter is used to convert audio data into text data, and its purpose is to confirm the accuracy of the audio data by inverse conversion from audio data to text data.

[0108] The virtual synthesizer is used to model a virtual character and load accurate audio data into the virtual character to realize virtual publicity through it. In this embodiment, there are several virtual characters, and they have different appearance characteristics based on the publicity items. The purpose is that when the virtual publicity is performed, virtual characters with different appearance characteristics can be automatically selected according to the publicity information, thereby further improving the intelligence of the virtual publicity device.

[0109] The display is a medium for direct interaction between the client and the personnel, and is used to display virtual announcements. In this embodiment, the client can be a business announcement board of a bank, an information display stand of a shopping mall, etc.

[0110] The software is used to execute the virtual announcement method described in Example 1.

[0111] When virtual publicity is performed through this embodiment, not only does it no longer require human participation when updating content, but it also has good real-time performance when updating content.

[0112] In order to solve the problem that the client still cannot convert the abnormally converted text data after repeated attempts, the server is configured to include a third converter. The third converter is used to convert the text data into audio data. At this time, the position of the abnormal conversion can be transmitted with accurate audio data.

[0113] In order to store the text data corresponding to the audio data during the previous virtual announcement for archiving and viewing, the client is also configured to include a memory.

[0114] In order to set the publicity period of the client for virtual publicity to improve the publicity validity, the client is configured to further include a clock module. In this case, the clock module is used to set the publicity period.

[0115] Although the present invention has been disclosed as above with preferred embodiments, it is not intended to limit the present invention. A person with ordinary knowledge in the technical field to which the present invention belongs may make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention shall be determined by the definition of the claims.

Claims

1. An intelligent virtual public announcement method, characterized in that: include: Receiving first text data sent by a server; the first text data includes information to be publicized, and the first text data is stored in the server; recognizing the first text data and converting it into first audio data; Recognizing the first audio data and converting it into second text data; Determine whether the first text data and the second text data are the same, and when the two are the same, load the first audio data into the virtual character and store it; when the two are different, firstly, locate the different positions of the first text data and the second text data in the first text data, and generate third text data from the text at the different positions in the first text data; secondly, identify the third text data and convert it into second audio data; then, identify the second audio data and convert it into fourth text data; finally, determine whether the third text data and the fourth text data are the same, and when the two are the same, replace the audio at the corresponding position of the first audio data with the second audio data, and then load it into the virtual character and store it; The first audio data is virtually publicized through the virtual character.

2. The intelligent virtual public announcement method according to claim 1, characterized in that: The determining whether the third text data is the same as the fourth text data further includes: When the two are different, sending the third text data and a first request to the server; the first request is used to request the server to convert the third text data into audio; Receiving third audio data sent by the server; the third audio data is the audio obtained after the server converts the third text data; The audio at the corresponding position of the first audio data is replaced with the third audio data and then loaded into the virtual character and stored.

3. The intelligent virtual public announcement method according to claim 1 is characterized in that: The determining whether the first text data is the same as the second text data further includes: When the two are the same, the audio data previously virtually announced is overwritten with the first audio data.

4. The intelligent virtual public announcement method according to claim 3 is characterized in that: The determining whether the first text data is the same as the second text data further includes: When the two are the same, the text data corresponding to the previously virtually publicized audio data is stored.

5. The intelligent virtual public announcement method according to claim 1, characterized in that: Before receiving the first text data sent by the server, the method further includes: A publicity period is set, and virtual publicity is performed through the virtual character in each publicity period, and the publicity period is negatively correlated with the flow of people.

6. An intelligent virtual public announcement system, characterized in that: It includes a server, several clients and software, wherein the server is connected to any of the clients via a network; The server is used to store first text data and send the first text data to the client, wherein the first text data includes information to be publicized; The client includes a first converter, a second converter, a virtual synthesizer and a display; The first converter is used to convert the first text data into the first audio data, or convert the third text data into the second audio data; The second converter is used to convert the first audio data into second text data, or convert the second audio data into fourth text data; The virtual synthesizer is used to realize virtual public display of the first audio data through a virtual character; The display is used to display virtual announcements; The software is used to execute the method according to any one of claims 1 to 5.

7. The intelligent virtual public announcement system according to claim 6, characterized in that: The server includes a third converter for converting text data into audio data.

8. The intelligent virtual public announcement system according to claim 6, characterized in that: The client includes a memory, and the memory is used to store text data corresponding to the audio data during virtual public announcement.

9. The intelligent virtual public announcement system according to claim 6, characterized in that: The client comprises a clock module, and the clock module is used to set a publicity period.

Images