CN110941737B - Single-machine voice storage method, device and equipment and readable storage medium - Google Patents

Abstract

The application discloses a stand-alone voice storage method, device, equipment, and readable storage medium. The method includes collecting voice information and judging whether the uploading condition is satisfied; if the uploading condition is not satisfied, obtaining dimension information of the voice information; Store to the target storage partition pointed to by the dimension information in the collection terminal storage partition, and add the index mark of the voice information to the target storage partition; when it is detected that the voice information meets the preset upload condition, determine the target storage partition based on the index mark , upload the voice information and corresponding dimension information in the target bucket. After the voice information is collected, judge whether the uploading condition is met or not. According to the dimension information, find the target storage partition in the collection terminal, store the voice information and create an index mark. If the uploading condition is met later, according to the index mark, quickly Determine the target bucket and upload voice and dimension information.

Description

Stand-alone voice storage method, device, equipment and readable storage medium

technical field

The invention relates to the technical field of data storage, in particular to a stand-alone voice storage method, device, equipment and readable medium.

Background technique

After the public security department collects the voice information, it needs to upload the voice information to the public security voiceprint database for voiceprint comparison, but sometimes it is not possible to directly upload the voiceprint due to the current conditions. Store the voiceprint information, and then upload the stored voiceprint information to the public security voiceprint database for comparison.

The existing storage method is to randomly store the collected voice information in the local memory, and when the upload condition is met, upload the collected voice information to the public security voiceprint database again. Uploading voice information is cumbersome, or directly uploading all voice information will take a long time.

Contents of the invention

The main purpose of this application is to provide a stand-alone voice storage method, device, equipment and readable storage medium, aiming at solving the problem of inconvenient uploading after storing and collecting voice information.

In order to achieve the above object, the application provides a stand-alone voice storage method, the incremental data clustering method includes the following steps:

Collect voice information and judge whether the uploading conditions are met;

If the uploading condition is not satisfied, acquiring dimension information of the voice information;

storing the voice information in the target storage partition pointed to by the dimension information in the collection terminal storage partition, and adding an index mark of the voice information to the storage partition;

When it is detected that the voice information satisfies the preset upload condition, the target storage partition is determined based on the index mark, and the voice information and the corresponding dimension information in the target storage partition are uploaded.

Optionally, the step of collecting voice information includes:

Collect voice information;

analyzing the number of speakers of the voice information;

According to the number of speakers, the voice information is separated to obtain the voice information of each speaker.

Optionally, the step of judging whether the upload condition can be met includes:

Establish a connection with the public security voiceprint database;

Obtain the connection result;

If the connection is successful, the upload condition is met;

If the connection fails, the upload condition is not met.

Optionally, the step of acquiring dimension information of the voice information includes:

determining voice feature information of the voice information;

Determining the collection location information of the voice information;

determining the collection time information of the voice information;

The dimension information is formed according to the voice feature information, the collection location information and the collection time information.

Optionally, the step of storing the voice information in the target storage partition pointed to by the dimension information in the collection terminal storage partition, and adding an index mark of the voice information to the target storage partition includes:

Find the target storage partition pointed to by the collection terminal according to the collection location information;

performing a similarity comparison between the voice information and the stored information in the target storage partition according to the voice feature information;

If the similarity is greater than a preset value, storing the voice information in the target storage partition;

Add the index mark to the target storage partition according to the collection time information.

Optionally, after the step of comparing the similarity between the voice information and the stored information in the target storage partition includes:

If the similarity is not greater than a preset value, a temporary storage partition is established according to the collection location information;

The voice information is stored in the temporary storage partition according to the collection location information.

When the amount of voice information in the temporary storage partition exceeds a preset number, then change the temporary storage partition into a fixed storage partition;

An index mark is added to the fixed storage partition according to the collection time information of the voice information in the fixed storage partition.

Optionally, the step of determining the target storage partition based on the index mark, and uploading the voice information and the corresponding dimension information in the target storage partition includes:

Obtain the upload time of the last uploaded voice message;

Obtain the index mark of each storage partition, and determine the target storage partition according to the upload time;

Upload the voice information in the target storage partition and the corresponding dimension information according to the collection time information of the voice information in the target storage partition.

The present application also provides a stand-alone voice storage device, the stand-alone voice storage device comprising:

Judging module, used for collecting voice information, judging whether the uploading condition is satisfied;

An acquisition module, configured to acquire dimension information of the voice information if the uploading condition is not met;

A storage module, configured to store the voice information in a target storage partition pointed to by the dimension information in the collection terminal storage partition, and add an index mark of the voice information to the target storage partition;

An upload module, configured to determine the target storage partition based on the index mark when it is detected that the voice information satisfies a preset upload condition, and upload the voice information and the corresponding dimension information in the target storage partition .

The present application also provides a stand-alone voice storage device. The stand-alone voice storage device includes: a memory, a processor, and a stand-alone voice storage program stored in the memory and operable on the processor. The stand-alone voice storage When the program is executed by the processor, the steps of the above-mentioned stand-alone voice storage method are realized.

The present application also provides a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned stand-alone voice storage method are implemented.

This application collects the voice information to determine whether the uploading condition is met; if the uploading condition is not met, obtain the dimension information of the voice information; store the voice information in the target pointed to by the dimension information in the storage partition of the collection terminal storage partition, and add an index mark of the voice information for the target storage partition; when it is detected that the voice information satisfies a preset upload condition, determine the target storage partition based on the index mark, and store the target The voice information in the partition and the corresponding dimension information are uploaded. After the voice information is collected, determine whether it can be directly uploaded to the public security voiceprint database. If the voice information cannot be uploaded, according to the dimension information of the voice information, find the target storage partition in the collection terminal, store the voice information in the target storage partition and Create an index mark, and then when the uploading conditions are met, quickly determine the target storage partition according to the index mark and upload the voice information and dimension information, which is convenient for comparison with the voiceprint information in the public security voiceprint database.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description serve to explain the principles of the application.

In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, In other words, other drawings can also be obtained from these drawings without paying creative labor.

FIG. 1 is a schematic diagram of the device structure of the hardware operating environment involved in the solution of the embodiment of the present application;

Fig. 2 is the schematic flow chart of the first embodiment of the stand-alone voice storage method of the present application;

Fig. 3 is the refinement flowchart of step S10 in Fig. 2 in the second embodiment of the stand-alone voice storage method of the present application;

Fig. 4 is the refinement flowchart of step S20 in Fig. 2 in the third embodiment of the stand-alone voice storage method of the present application;

FIG. 5 is a detailed flow chart of step S30 in FIG. 2 in the fourth embodiment of the stand-alone voice storage method of the present application;

FIG. 6 is a detailed flow chart of step S40 in FIG. 2 in the fourth embodiment of the stand-alone voice storage method of the present application;

FIG. 7 is a schematic diagram of the system structure of an embodiment of the stand-alone voice storage device of the present application.

The realization, functional features and advantages of the present application will be further described in conjunction with the embodiments and with reference to the accompanying drawings.

Detailed ways

It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

In the following description, use of suffixes such as 'module', 'part' or 'unit' for denoting elements is only for facilitating description of the present invention and has no specific meaning by itself. Therefore, 'module', 'part' or 'unit' may be used in combination.

As shown in FIG. 1 , FIG. 1 is a schematic diagram of a terminal structure of a hardware operating environment involved in the solution of the embodiment of the present application.

The terminal in the embodiment of the present application is a stand-alone voice storage device.

As shown in FIG. 1 , the terminal may include: a processor 1001 , such as a CPU, a network interface 1004 , a user interface 1003 , a memory 1005 , and a communication bus 1002 . Wherein, the communication bus 1002 is used to realize connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. Optionally, the network interface 1004 may include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 can be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001 .

Optionally, the terminal may further include a camera, an RF (Radio Frequency, radio frequency) circuit, a sensor, an audio circuit, a WiFi module, and the like. Among them, sensors such as light sensors, motion sensors and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, where the ambient light sensor may adjust the brightness of the display screen according to the brightness of the ambient light, and the proximity sensor may turn off the display screen and/or backlight. Of course, the terminal device may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which will not be repeated here.

Those skilled in the art can understand that the terminal structure shown in FIG. 1 does not constitute a limitation on the terminal, and may include more or less components than those shown in the figure, or combine some components, or arrange different components.

As shown in FIG. 1 , the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a stand-alone voice storage program.

In the terminal shown in Figure 1, the network interface 1004 is mainly used to connect to the background server and perform data communication with the background server; the user interface 1003 is mainly used to connect to the client (client) and perform data communication with the client; and the processor 1001 can be used to call the stand-alone voice storage program stored in memory 1005, and perform the following operations:

Collect voice information and judge whether the uploading conditions are met;

If the uploading condition is not satisfied, acquiring dimension information of the voice information;

storing the voice information in the target storage partition pointed to by the dimension information in the collection terminal storage partition, and adding an index mark of the voice information to the target storage partition;

When it is detected that the voice information satisfies the preset upload condition, the target storage partition is determined based on the index mark, and the voice information and the corresponding dimension information in the target storage partition are uploaded.

Based on the foregoing terminal hardware structure, various embodiments of the present application are proposed.

This application provides a stand-alone voice storage method.

Referring to Fig. 2, in the first embodiment of stand-alone voice storage method, the method includes:

Step S10, collecting voice information, and judging whether the uploading condition is satisfied;

When the public security department conducts a case investigation, it needs to collect voice information, upload the collected voice information to the public security voiceprint database and compare it with the voiceprint information in the voiceprint database. If similar voiceprint information is matched, it means that the collection The source of voice information may be suspected of crime. However, in order to ensure the information security of the public security voiceprint database, the uploading conditions are relatively strict. Uploading information needs to undergo strict security assessment. Uploading voice information needs to detect the uploading environment, such as the uploading location and network traffic conditions. If the connection is established with the voiceprint database, the voice information will be uploaded. If the connection with the public security voiceprint database cannot be established, the voice information needs to be saved in the local memory.

Step S20, if the uploading condition is not satisfied, then obtain dimension information of the voice information;

When the uploading conditions are not met, the dimensional information of the voice information is obtained. The dimensional information of the voice information includes voice feature information, collection location information, and collection time information. The voice feature information includes voice pitch, timbre, etc., which can be analyzed and compared with the voice. The feature information of the collection location information is the place where the voice information is collected, and the collection time information is the time when the voice information is collected.

Step S30, according to the dimension information, store the voice information in the target storage partition pointed to by the dimension information in the storage partition corresponding to the collection terminal, and add the voice information to the target storage partition index mark;

The terminal itself stores part of the voice information derived from the public security voiceprint database. The voice information derived from the public security voiceprint database is classified according to the location information at the time of collection, and sorted according to the time sequence of collection. For newly collected Voice information, according to the collection location information in the dimension information, first determine the possible target storage partitions, and then use the voice feature information to match the voice information in the collection terminal that has been stored before. If there is voice information with a high degree of similarity, then Store the collected voice information in the corresponding target storage partition, and add index marks to the target storage partition according to the dimension information. If no suitable existing storage partition is found, create a new temporary one according to the collection time information of the voice information The storage partition stores the collected voice information into a new temporary storage partition.

Step S40, when it is detected that the voice information satisfies the preset upload condition, based on the index, from the target storage partition determined by the mark, according to the dimension information, upload all the voice information in the target storage partition Upload the above voice information and the corresponding dimension information;

When it is detected that the current environment satisfies the preset upload condition again, according to the index mark of the storage partition, it is determined that there is a target storage partition that has undergone data update, and according to the collection time information in the dimension information of the voice information, the newly collected voice information And the corresponding dimension information is uploaded to the public security voiceprint database.

In this embodiment, by collecting voice information, it is judged whether the uploading condition is satisfied; if the uploading condition is not satisfied, the dimension information of the voice information is obtained; the voice information is stored in the dimension information in the storage partition of the collection terminal The target storage partition pointed to, and add the index mark of the voice information for the target storage partition; when it is detected that the voice information meets the preset upload condition, determine the target storage partition based on the index mark, and add The voice information and the corresponding dimension information in the target storage partition are uploaded. After the voice information is collected, determine whether it can be directly uploaded to the public security voiceprint database. If the voice information cannot be uploaded, according to the dimension information of the voice information, find the target storage partition in the collection terminal, store the voice information in the target storage partition and Create an index mark, and then when the uploading conditions are met, quickly determine the target storage partition according to the index mark and upload the voice information and dimension information, which is convenient for comparison with the voiceprint information in the public security voiceprint database.

Further, referring to FIG. 2 and FIG. 3 , on the basis of the first embodiment of the stand-alone voice storage method of the present application, a second embodiment of the stand-alone voice storage method is provided. In the second embodiment,

Step S10 includes:

Step S11, collecting voice information;

The on-site voice information is collected through the designated certified voice collection equipment, so that the voice information collected by the certified collection equipment can be uploaded to the public security voiceprint database, and the collection equipment number, collection personnel number, collection location and other information are recorded during collection. .

Step S12, analyzing the number of speakers of the voice information;

Because the environment for collecting voice information is relatively complicated, it usually collects voice information mixed with multiple speakers. Through the voice recognition function of the collection device, the collected voice information is recognized, and the collected voice information is processed according to the voice feature information. Clustering, the clustering number of clustering is the number of speakers.

Step S13, according to the number of the speakers, separate the voice information to obtain the voice information of each speaker;

According to the number of identified speakers, the collected voice information is separated, the voice information corresponding to each speaker is extracted separately, and information such as collection time and collection location is added to each separated voice information.

Step S14, establishing a connection with the public security voiceprint database;

The public security voiceprint database stores the voiceprint information of criminal suspects collected by the public security department, which is relatively confidential information. The connection to the public security voiceprint database requires security verification. The information in the tattoo database is compared to determine whether there is similar suspect data.

Step S15, obtaining the connection result;

Because the information stored in the public security voiceprint database is relatively confidential, there are stricter requirements for the environment connected to the public security voiceprint database, such as in an environment where the network is not good and transmission is limited, or in a network environment where information may be stolen, such as overseas In this case, in order to ensure the information security in the public security voiceprint database, when the environmental conditions cannot meet the connection requirements, the public security voiceprint database cannot be connected, so after trying to connect to the public security voiceprint database, the connection result is obtained.

Step S16, if the connection is successful, the upload condition is met;

Step S17, if the connection fails, the upload condition is not satisfied;

When the connection is successful, the voice information will be automatically uploaded, and when the connection fails, the voice information cannot be uploaded, and the voice information needs to be stored in the local storage and uploaded later.

In this embodiment, the voice information is collected, the number of speakers contained in the voice information is identified, the voice information of each speaker is separated, and at the same time, an attempt is made to connect to the public security voiceprint database, and the connection result with the public security voiceprint database is judged , to determine the next operation, if the connection is successful, the voice information will be automatically uploaded to the public security voiceprint database; if the connection fails, the voice information will be stored in the local memory.

Further, referring to FIG. 2 and FIG. 4 , on the basis of the second embodiment of the stand-alone voice storage method of the present application, a third embodiment of the stand-alone voice storage method is provided. In the third embodiment,

Step S20 includes:

Step S21, determining the voice characteristic information of the voice information;

Step S22, determining the collection location information of the voice information;

Step S23, determining the collection time information of the voice information;

Step S24, forming the dimension information according to the voice feature information, the collection location information and the collection time information;

The voice feature information is obtained by analyzing the voice information. The voice feature information includes the pitch, amplitude, frequency and other information of the voice. The collection location refers to the place where the voice information is collected, and the collection time refers to the time when the voice information is collected. The purpose of collecting voice information is to determine whether there is a suspect at the scene, and compare the collected voice information with the information in the public security voiceprint database. Usually, the range of activities of suspects is relatively fixed, and they tend to appear in some fixed places. The collection location information and collection time information can constitute the case dimension of voice information, that is, the existing cases that may be similar to the case are judged by time and place. Then, compare the voice feature information with the voice information collected from possibly similar cases in the public security voiceprint database to confirm whether it is the same person.

In this embodiment, the collected voice information is analyzed to obtain dimension information of the voice information. The dimension information can be used to match the voice information in the public security voiceprint database, and can also be used to store the voice information in a local memory later.

Further, referring to FIG. 2 and FIG. 5 , on the basis of the third embodiment of the stand-alone voice storage method of the present application, a fourth embodiment of the stand-alone voice storage method is provided. In the fourth embodiment,

Step S30 includes:

Step S31, according to the collection location information, find the target storage partition pointed to by the collection terminal;

The terminal itself stores part of the voice information that has been exported from the public security voiceprint database. The voice information derived from the public security voiceprint database is stored in partitions according to the location information where the voice information was collected. The collection location can be divided into cities as The scope of division can also be divided into provinces, that is, the division of storage partitions can be adjusted according to the actual situation. After new voice information is collected, the target storage partition is initially determined according to the location information of the voice information.

Step S32, comparing the similarity between the voice information and the stored information in the target storage partition according to the voice feature information;

According to the collection location information, after preliminarily determining the possible target storage partition of the voice information, according to the voice feature information, determine whether there is existing voice information similar to the collected voice information, if there is similar existing voice information, the voice information Store in the corresponding target storage partition, and then upload the voice information to the corresponding storage partition in the public security voiceprint database according to the current storage partition where the voice information is located when uploading.

Step S33, if the similarity is greater than a preset value, storing the voice information in the target storage partition;

By comparing the similarity between the collected voice information and the stored voice information, if the similarity is high, it is stored in the corresponding target storage partition.

Step S34, adding the index mark to the target storage partition according to the collection time information;

For the storage partition that has undergone data update, according to the collection time information of the voice information stored in the storage partition, an index mark is added to the storage partition, and the index mark can record the collection time of the last updated voice information in the storage partition.

Step S35, if the similarity is not greater than a preset value, then according to the collection location information, a temporary storage partition is established;

If the similarity is small, it means that the voice information is less related to the currently stored voice information and cannot be directly put into the corresponding storage partition. Then, according to the collection location information, a new temporary storage partition is established again to store the voice information. For the new temporary In the storage partition, the collection time information of the voice information is different from the existing voice information in the storage partition.

Step S36, storing the voice information in the temporary storage partition according to the collection location information;

If the collection location information of the collected voice information does not have a corresponding temporary storage partition, then create a new temporary storage partition and store the voice information in the new temporary storage partition, if there is already a temporary storage partition with the same collection location information, then directly The voice information is stored in a corresponding existing storage partition.

Step S37, when the number of voice information in the temporary storage partition exceeds the preset number, then change the temporary storage partition into a fixed storage partition;

When there is a lot of voice information in the temporary storage partition, it means that the voice information in the temporary storage partition may have constituted the relevant voice information of the new case, and the temporary storage partition becomes a fixed storage partition. If the voice information collected later meets the conditions, can be stored into this new pinned bucket.

Step S38, adding an index mark to the fixed storage partition according to the collection time information of the voice information in the fixed storage partition;

Similarly, an index mark will also be added to the new fixed storage partition. Like the previous index mark, the index mark of the new fixed storage partition contains the collection time information of the last updated voice information of the storage partition.

In this embodiment, if the voice information collected can be stored in an existing target storage partition, then it is stored in the target storage partition and an index mark is added; if it cannot be stored in an existing storage partition, a new one is created. and store the collected voice information in the temporary storage partition.

Further, referring to FIG. 2 and FIG. 6 , on the basis of the fourth embodiment of the stand-alone voice storage method of the present application, a fifth embodiment of the stand-alone voice storage method is provided. In the fifth embodiment,

Step S40 includes:

Step S41, obtaining the upload time of the last uploaded voice message;

The collection terminal will automatically record each upload operation. When uploading voice information each time, it will upload the newly collected voice information in the interval between two uploads to the public security voiceprint database. Therefore, each upload needs to obtain the last upload. The upload time of the audio message.

Step S42, obtaining the index mark of each storage partition, and determining the target storage partition according to the upload time;

When the update time of the data in the index mark of the storage partition is later than the last upload time, it is determined that the target storage partition needs to upload voice information.

Step S43, uploading the voice information in the target storage partition and the corresponding dimension information according to the collection time information of the voice information in the target storage partition;

After the target storage partition is determined, the collection time information of each voice information in the target storage partition is obtained. If the collection time is later than the upload time of the last uploaded data, the voice information and the corresponding dimension information are uploaded to the public security voiceprint database, and at the same time According to the dimension information, the voice information is stored in the corresponding area of the public security voiceprint database.

In this embodiment, the target storage partition is quickly determined according to the index mark of the storage partition, and the corresponding uploaded voice information is determined according to the dimension information of the voice information, and the voice information and the corresponding dimension information are uploaded.

In addition, referring to FIG. 7, the embodiment of the present application also proposes a stand-alone voice storage device, the stand-alone voice storage device includes:

Judging module, used for collecting voice information, judging whether the uploading condition is satisfied;

An acquisition module, configured to acquire dimension information of the voice information if the uploading condition is not met;

A storage module, configured to store the voice information in a target storage partition pointed to by the dimension information in the collection terminal storage partition, and add an index mark of the voice information to the target storage partition;

An upload module, configured to determine the target storage partition based on the index mark when it is detected that the voice information satisfies a preset upload condition, and upload the voice information and the corresponding dimension information in the target storage partition .

Optionally, the judging module is also used for:

Collect voice information;

analyzing the number of speakers of the voice information;

According to the number of speakers, the voice information is separated to obtain the voice information of each speaker.

Optionally, the judging module is also used for:

Establish a connection with the public security voiceprint database;

Obtain the connection result;

If the connection is successful, the upload condition is met;

If the connection fails, the upload condition is not met.

Optionally, the acquisition module is also used for:

determining voice feature information of the voice information;

Determining the collection location information of the voice information;

determining the collection time information of the voice information;

The dimension information is formed according to the voice feature information, the collection location information and the collection time information.

Optionally, the storage module is also used for:

Find the target storage partition pointed to by the collection terminal according to the collection location information;

performing a similarity comparison between the voice information and the stored information in the target storage partition according to the voice feature information;

If the similarity is greater than a preset value, storing the voice information in the target storage partition;

Add the index mark to the target storage partition according to the collection time information.

Optionally, the storage module is also used for:

If the similarity is not greater than a preset value, a temporary storage partition is established according to the collection location information;

storing the voice information in the temporary storage partition according to the collection location information;

When the amount of voice information in the temporary storage partition exceeds a preset number, then change the temporary storage partition into a fixed storage partition;

An index mark is added to the fixed storage partition according to the collection time information of the voice information in the fixed storage partition.

Optionally, the upload module is also used for:

Obtain the upload time of the last uploaded voice message;

Obtain the index mark of each storage partition, and determine the target storage partition according to the upload time;

Upload the voice information in the target storage partition and the corresponding dimension information according to the collection time information of the voice information in the target storage partition.

The extended content of the specific implementation of the device and the readable storage medium (that is, the computer-readable storage medium) of the present application is basically the same as the above-mentioned embodiments of the stand-alone voice storage method, and will not be repeated here.

It should be noted that, in this document, the term "comprising", "comprising" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or device. Without further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising that element.

The serial numbers of the above embodiments of the present invention are for description only, and do not represent the advantages and disadvantages of the embodiments.

Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation. Based on such an understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art can be embodied in the form of software products, and the computer software products are stored in a storage medium (such as ROM/RAM, disk, CD) contains several instructions to make a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in various embodiments of the present invention.

Embodiments of the present invention have been described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementations, and the above-mentioned specific implementations are only illustrative, rather than restrictive, and those of ordinary skill in the art will Under the enlightenment of the present invention, many forms can also be made without departing from the gist of the present invention and the protection scope of the claims, and these all belong to the protection of the present invention.

Claims (9)

1. a stand-alone voice storage method is characterized in that, the stand-alone voice storage method comprises the following steps: Collect voice information and judge whether the uploading conditions are met; If the uploading condition is not satisfied, acquiring dimension information of the voice information; storing the voice information in the target storage partition pointed to by the dimension information in the collection terminal storage partition, and adding an index mark of the voice information to the target storage partition; When it is detected that the voice information satisfies the preset upload condition, determine the target storage partition based on the index mark, and upload the voice information and the corresponding dimension information in the target storage partition; Wherein, the step of acquiring dimension information of the voice information includes: determining voice feature information of the voice information; Determining the collection location information of the voice information; determining the collection time information of the voice information; The dimension information is formed according to the voice feature information, the collection location information and the collection time information. 2. stand-alone voice storage method as claimed in claim 1, is characterized in that, the step of described collection voice information comprises: Collect voice information; analyzing the number of speakers of the voice information; According to the number of speakers, the voice information is separated to obtain the voice information of each speaker. 3. stand-alone voice storage method as claimed in claim 2, is characterized in that, the step of described judgment whether satisfies upload condition comprises: Establish a connection with the public security voiceprint database; Get the connection result; If the connection is successful, the upload condition is met; If the connection fails, the upload condition is not met. 4. The stand-alone voice storage method according to claim 1, wherein the voice information is stored in the target storage partition pointed to by the dimension information in the collection terminal storage partition, and stored for the target The step of adding the index mark of the voice information to the partition comprises: Find the target storage partition pointed to by the collection terminal according to the collection location information; performing a similarity comparison between the voice information and the stored information in the target storage partition according to the voice feature information; If the similarity is greater than a preset value, storing the voice information in the target storage partition; Add the index mark to the target storage partition according to the collection time information. 5. stand-alone voice storage method as claimed in claim 4, is characterized in that, described voice information and the storage information in the described target storage partition are carried out after the step of similarity comparison comprising: If the similarity is not greater than a preset value, a temporary storage partition is established according to the collection location information; storing the voice information in the temporary storage partition according to the collection location information; When the amount of voice information in the temporary storage partition exceeds a preset number, then change the temporary storage partition into a fixed storage partition; An index mark is added to the fixed storage partition according to the collection time information of the voice information in the fixed storage partition. 6. The stand-alone voice storage method according to claim 5, wherein the target storage partition is determined based on the index mark, and the voice information in the target storage partition and the corresponding dimension information The upload steps include: Obtain the upload time of the last uploaded voice message; Obtain the index mark of each storage partition, and determine the target storage partition according to the upload time; Upload the voice information and the corresponding dimension information in the target storage partition according to the collection time information of the voice information in the target storage partition. 7. A stand-alone voice storage device, characterized in that, the stand-alone voice storage device comprises: Judging module, used for collecting voice information, judging whether the uploading condition is satisfied; An acquisition module, configured to acquire dimension information of the voice information if the uploading condition is not met; A storage module, configured to store the voice information in a target storage partition pointed to by the dimension information in the collection terminal storage partition, and add an index mark of the voice information to the target storage partition; An upload module, configured to determine the target storage partition based on the index mark when it is detected that the voice information satisfies a preset upload condition, and upload the voice information and the corresponding dimension information in the target storage partition ; The acquisition module is also used to determine the voice feature information of the voice information; determine the collection location information of the voice information; determine the collection time information of the voice information; according to the voice feature information, the collection location information and the collection time information to form the dimension information. 8. A stand-alone voice storage device, characterized in that the device comprises: a memory, a processor and a stand-alone voice storage program stored on the memory and operable on the processor, the stand-alone voice storage program When being executed by the processor, the steps of realizing the stand-alone voice storage method according to any one of claims 1 to 6 are realized. 9. A readable storage medium, characterized in that a computer program is stored on the readable storage medium, and when the computer program is executed by a processor, the stand-alone voice according to any one of claims 1 to 6 is realized The steps of the storage method.

Images