CN111931821A - Vector database partitioning method, device, equipment and storage medium - Google Patents
Vector database partitioning method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN111931821A CN111931821A CN202010682732.9A CN202010682732A CN111931821A CN 111931821 A CN111931821 A CN 111931821A CN 202010682732 A CN202010682732 A CN 202010682732A CN 111931821 A CN111931821 A CN 111931821A
- Authority
- CN
- China
- Prior art keywords
- vector
- sub
- registration
- base
- vectors
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a vector library dividing method, a device, equipment and a storage medium, wherein the method comprises the steps of establishing anchor points for all registered vectors in a training model; performing sub-base according to the registration vector with the anchor point relative identity degree within a preset range, and performing sub-base numbering on each sub-base to obtain a plurality of first sub-base numbers; and obtaining a second sub-base number of the input vector, judging the sub-base corresponding to the first sub-base number with the input vector being the same as the second sub-base number as a target sub-base, and then calculating the degree of identity between the input vector and the registration vector in the target sub-base. According to the vector database partitioning method, only one target database with few registered vectors needs to be calculated during calculation, and the calculation speed is improved.
Description
Technical Field
The invention relates to the technical field of intelligent identification, in particular to a vector library dividing method, a vector library dividing device, vector library dividing equipment and a storage medium.
Background
The existing face recognition, voiceprint recognition and the like mainly use a neural network for model training, and the final output is in a vector form. The similarity of two faces or voiceprints is calculated by similarity between the characterized vectors.
The existing calculation methods include euclidean distance, cosine, and plda, and when the 1: N search is performed, i.e., when the similarity calculation is performed by using vectors in a vector library, the similarity calculation is very time-consuming when the data amount in the library is very large (more than tens of thousands).
Disclosure of Invention
The invention aims to provide a vector library dividing method, a vector library dividing device, vector library dividing equipment and a storage medium, so as to solve the problem that the conventional calculation mode of the similarity of human faces or voiceprints is time-consuming and realize the beneficial effect of quick calculation.
The invention provides a vector database partitioning method, which comprises the following steps: establishing anchor points for all the registration vectors in the training model; performing sub-base according to the registration vector with the anchor point relative identity degree within a preset range, and performing sub-base numbering on each sub-base to obtain a plurality of first sub-base numbers; and obtaining a second sub-base number of the input vector, judging the sub-base corresponding to the first sub-base number with the input vector being the same as the second sub-base number as a target sub-base, and then calculating the degree of identity between the input vector and the registration vector in the target sub-base.
Further, the step of establishing an anchor point for all registered vectors in the training model comprises:
and calculating N central points by using a clustering algorithm, and forming a matrix N by the registration vectors at the N central points, wherein the range of N is between 10 and 10000.
Further, the step of performing bank splitting on the registration vector with the identification degree within a preset range according to the anchor point, and performing bank splitting numbering on each bank includes:
and calculating the registration vectors and the matrix N, and taking the sequence numbers of one or more most similar registration vectors as the sub-base numbers of the registration vectors to obtain a plurality of first sub-base numbers.
Further, the clustering algorithm is a k-means algorithm.
Further, the step of computing the registration vector and a matrix N comprises:
according to the formula
And calculating the degree of identity between the registration vector on the anchor point and other registration vectors, wherein a matrix N is formed by the registration vectors on a plurality of anchor points, m is the registration vector on one anchor point, and x is any registration vector.
The invention also provides a vector database dividing device, which comprises: the anchor point establishing module is used for establishing anchor points for all the registration vectors in the training model; the database dividing module is used for dividing the registration vector with the anchor point relative identity degree within a preset range and dividing and numbering each database to obtain a plurality of first database dividing numbers; and the retrieval calculation module is used for obtaining a second sub-library number of the input vector, judging the sub-library corresponding to the first sub-library number with the same input vector and second sub-library number as a target sub-library, and then calculating the degree of identity between the input vector and the registration vector in the target sub-library.
Further, the library dividing module further comprises a clustering algorithm sub-module, which is used for calculating N central points and forming a matrix N by the registration vectors at the N central points.
Further, the library dividing module further comprises: the calculation submodule is used for calculating the registration vector and the matrix N; and the numbering submodule is used for taking the sequence numbers of one or more most similar registration vectors as the sub-base numbers of the registration vectors so as to obtain a plurality of first sub-base numbers.
The invention also provides a vector banking device which comprises a memory, a processor and a program which is stored on the memory and can run on the processor, and is characterized in that the processor executes the program to realize the vector banking method.
The present invention also provides a storage medium comprising a storage data area storing data created according to use of a blockchain node and a storage program area storing a computer program, wherein the computer program realizes the vector banking method as described in any one of the above items when executed by a processor.
The invention provides a vector library dividing method, which comprises the steps of establishing anchor points for all registered vectors in a training model; performing sub-base on the registration vectors within a preset range according to the relative identification degree of the anchor points, and performing sub-base numbering on each sub-base to obtain a plurality of first sub-base numbers; the method comprises the steps of obtaining a second sub-base number of an input vector, judging a sub-base corresponding to a first sub-base number with the input vector being the same as the second sub-base number as a target sub-base, and then carrying out identity calculation on the input vector and the registration vector in the target sub-base, so that only one target sub-base with few registration vectors needs to be calculated during calculation, and the calculation speed is improved.
Drawings
FIG. 1 is a flowchart of a vector binning method according to a first embodiment of the present invention;
FIG. 2 is a block diagram of a vector library apparatus according to a second embodiment of the present invention;
FIG. 3 is a schematic block diagram of a binning module in the vector binning apparatus in FIG. 2;
fig. 4 is a schematic structural diagram of a vector binning device in a third embodiment of the present invention.
The following detailed description will further illustrate the invention in conjunction with the above-described figures.
Detailed Description
To facilitate an understanding of the invention, the invention will now be described more fully with reference to the accompanying drawings. Several embodiments of the invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like as used herein are for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
Referring to fig. 1, a vector binning method according to a first embodiment of the present invention includes steps S01 through S03.
Step S01, establishing anchor points for all the registration vectors in the training model; it should be noted that, because the feature vectors generated by the model are not uniformly distributed in the vector space, a large amount (tens of thousands to millions) of data is required for the identification of the anchor point, and specifically, the step of establishing the anchor point for all the registration vectors in the training model includes: calculating N central points by using a clustering algorithm, and forming a matrix N by the registration vectors at the N central points, wherein the range of N is between 10 and 10000, the clustering algorithm can be a K-means algorithm, the K-means algorithm is also called a K-means clustering algorithm (K-means clustering algorithm) is an iterative solution clustering analysis algorithm, and the method comprises the steps of dividing data into K groups in advance, randomly selecting K objects as initial clustering centers, then calculating the distance between each object and each seed clustering center, and allocating each object to the nearest clustering center. The cluster centers and the objects assigned to them represent a cluster. The cluster center of a cluster is recalculated for each sample assigned based on the objects existing in the cluster. This process will be repeated until some termination condition is met. The termination condition may be that no (or minimum number) objects are reassigned to different clusters, no (or minimum number) cluster centers are changed again, and the sum of squared errors is locally minimal.
Step S02, performing database partitioning according to the registration vector with the anchor point identification degree in a preset range, and performing database partitioning numbering on each database to obtain a plurality of first database partitioning numbers; for example, 100 adjacent registration vectors have a higher degree of identity and are divided into one sub-pool, so that 1000 registration vectors can be divided into sub-pools with the numbers 1,2,3,4,5, 6, 7, 8, 9 and 10, which are the first sub-pool numbers.
The step of performing bank splitting on the registration vectors with the relative identity degrees of the anchor points within a preset range and performing bank splitting numbering on each bank comprises the following steps: and calculating the registration vectors and the matrix N to calculate the degree of identity between the registration vectors on the anchor points and other registration vectors, and taking the sequence numbers of one or more most similar registration vectors as the sub-library numbers of the registration vectors to obtain a plurality of first sub-library numbers.
Specifically, the step of calculating the registration vector and the matrix N includes:
according to the formula
Calculating the degree of identity between the registration vector on the anchor point and other registration vectors, wherein a matrix N is composed of the registration vectors on a plurality of anchor points, m is the registration vector on one anchor point, and x is any registration vector, so as to calculate the degree of identity between the registration vector on the anchor point and other registration vectors.
Step S03, obtaining a second sub-library number of an input vector, judging the sub-library corresponding to the first sub-library number with the input vector being the same as the second sub-library number as a target sub-library, and then calculating the degree of identity between the input vector and the registration vector in the target sub-library, wherein the input vector is the face or the voiceprint to be identified. Assume that there are 5 anchor point vectors m1, m2, m3, m4, m5, given the numbers 1,2,3,4,5, respectively.
A vector x is registered, which has the greatest similarity to m1, and x is labeled with a sequence number of 1.
Inputting a vector y which has the maximum similarity with m1, recalling the vector with the label serial number of 1, namely recalling the vector x, then performing similarity calculation on the vector x and the vector y to identify whether the recognition degree of the vector y and the vector x is within a preset range, if so, indicating that the vector y is a face or a voiceprint in the training model, and passing verification, otherwise, indicating that the vector y is not the face or the voiceprint in the training model, and failing verification.
In the vector library partitioning method, anchor points are established for all the registered vectors in the training model; performing sub-base on the registration vectors within a preset range according to the relative identification degree of the anchor points, and performing sub-base numbering on each sub-base to obtain a plurality of first sub-base numbers; the method comprises the steps of obtaining a second sub-base number of an input vector, judging a sub-base corresponding to a first sub-base number with the input vector being the same as the second sub-base number as a target sub-base, and then carrying out identity calculation on the input vector and the registration vector in the target sub-base, so that only one target sub-base with few registration vectors needs to be calculated during calculation, and the calculation speed is improved.
Referring to fig. 2 and fig. 3, the present invention further provides a vector binning apparatus, including: an anchor point establishing module 10, configured to establish anchor points for all the registration vectors in the training model; a database partitioning module 20, configured to perform database partitioning on the registration vectors with the anchor point identification degrees within a preset range, and perform database partitioning numbering on each database to obtain a plurality of first database partitioning numbers; and the retrieval calculation module 30 is configured to obtain a second library number of the input vector, determine a library corresponding to the first library number with the same input vector and the second library number as a target library, and then calculate the degree of identity between the input vector and the registration vector in the target library.
Specifically, in this embodiment, the library dividing module 20 further includes a clustering algorithm sub-module 21, which is configured to calculate N central points, and form the registration vectors at the N central points into a matrix N.
Specifically, in this embodiment, the library dividing module 20 further includes: a calculation submodule 22, configured to calculate the registration vector and the matrix N; and the numbering submodule 3 is used for taking the sequence numbers of one or more most similar registration vectors as the sub-base numbers of the registration vectors so as to obtain a plurality of first sub-base numbers.
In the vector library dividing device, the anchor point establishing module 10 establishes anchor points for all registered vectors in the training model; so that the database partitioning module 20 performs database partitioning on the registration vectors with the anchor point identification degrees within a preset range, and performs database partitioning numbering on each database to obtain a plurality of first database partitioning numbers; and then, a second sub-library number of the input vector is obtained through the retrieval calculation module 30, the sub-library corresponding to the first sub-library number with the input vector being the same as the second sub-library number is judged as a target sub-library, and then the input vector and the registration vector in the target sub-library are subjected to identity degree calculation, so that only one target sub-library with few registration vectors needs to be calculated during calculation, and the calculation speed is improved.
The present invention also provides a storage medium comprising a storage data area storing data created according to use of a blockchain node and a storage program area storing a computer program, wherein the computer program realizes the vector banking method as described in any one of the above items when executed by a processor.
In an embodiment of the present invention, there is also provided a vector banking apparatus, including a memory, a processor, and a program stored on the memory and executable on the processor, the processor implementing the method as described above when executing the program. Fig. 4 is a schematic structural diagram of a vector binning device according to an embodiment of the present invention. Referring to fig. 4, the vector banking apparatus 90 includes: a Radio Frequency (RF) circuit 910, a memory 920, an input unit 930, a display unit 940, a sensor 950, an audio circuit 960, a Wireless Fidelity (WiFi) module 970, a processor 980, and a power supply 990. Those skilled in the art will appreciate that the vector binning apparatus configuration shown in fig. 4 does not constitute a limitation on the vector binning apparatus and may include more or fewer components than shown, or some components in combination, or a different arrangement of components. The following describes each component of the vector library splitting device of this embodiment in detail with reference to fig. 4:
the RF circuit 910 may be used for receiving and transmitting signals during information transceiving, and in particular, for processing the downlink information of the base station to the processor 980 after receiving the downlink information; in addition, the data for designing uplink is transmitted to the base station. In general, the RF circuit 910 includes, but is not limited to, an antenna, at least one Amplifier, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like. In addition, the RF circuit 910 may also communicate with networks and other devices via wireless communication. The wireless communication may use any communication standard or protocol, including but not limited to Global System for Mobile communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), and the like.
The memory 920 may be used to store user software and modules, and the processor 980 may execute various functional applications and data processing of the vector banking apparatus by operating the user software and modules stored in the memory 920. The memory 920 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating device, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. Further, the memory 920 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
The input unit 930 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the vector banking apparatus. Specifically, the input unit 930 may include a touch panel 931 and other input devices 932. The touch panel 931, also referred to as a touch screen, may collect a touch operation performed by a user on or near the touch panel 931 (e.g., a user's operation on or near the touch panel 931 using a finger, a stylus, or any other suitable object or accessory), and drive a corresponding connection device according to a preset program. Alternatively, the touch panel 931 may include two parts, a touch detection device and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts the touch information into touch point coordinates, sends the touch point coordinates to the processor 980, and can receive and execute commands sent by the processor 980. In addition, the touch panel 931 may be implemented by various types, such as a resistive type, a capacitive type, an infrared ray, and a surface acoustic wave. The input unit 930 may include other input devices 932 in addition to the touch panel 931. In particular, other input devices 932 may include, but are not limited to, one or more of a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.
The display unit 940 may be used to display information input by a user or information provided to the user and various menus of the vector banking apparatus. The Display unit 940 may include a Display panel 941, and optionally, the Display panel 941 may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like. Further, the touch panel 931 may cover the display panel 941, and when the touch panel 931 detects a touch operation on or near the touch panel 931, the touch panel transmits the touch operation to the processor 980 to determine the type of the touch event, and then the processor 980 provides a corresponding visual output on the display panel 941 according to the type of the touch event. Although in fig. 4, the touch panel 931 and the display panel 941 are two independent components to implement the input and output functions of the mobile phone, in some embodiments, the touch panel 931 and the display panel 941 may be integrated to implement the input and output functions of the mobile phone.
The vector banking apparatus may further include at least one sensor 950, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 941 according to the brightness of ambient light. Audio circuitry 960, speaker 961, microphone 962 may provide an audio interface between a user and the vector banking apparatus. The audio circuit 960 may transmit the electrical signal converted from the received audio data to the speaker 961, and convert the electrical signal into a sound signal for output by the speaker 961; microphone 962, on the other hand, converts the collected sound signals into electrical signals, which are received by audio circuit 960 and converted into audio data, which are processed by audio data output processor 980, either via RF circuit 910 for transmission to another vector banking device, for example, or output to memory 920 for further processing.
WiFi belongs to short-distance wireless transmission technology, and the vector banking equipment can provide wireless broadband internet access for users through a WiFi module 970. Although fig. 4 shows the WiFi module 970, it is understood that it does not belong to the essential constitution of the vector banking apparatus and can be omitted entirely as needed within the scope not changing the essence of the invention.
The processor 980 is a control center of the vector library apparatus, connects various parts of the entire cellular phone using various interfaces and lines, and performs various functions of the vector library apparatus and processes data by operating or executing user software and/or modules stored in the memory 920 and calling data stored in the memory 920, thereby integrally monitoring the vector library apparatus. Alternatively, processor 980 may include one or more processing units; preferably, the processor 980 may be integrated with an application processor, which mainly handles operating devices, user interfaces, applications, and the like. Processor 980 may or may not be integrated with modem processor(s) 980.
The vector banking apparatus further includes a power supply 990 (e.g., a battery) for supplying power to the various components, and preferably, the power supply may be logically connected to the processor 980 via a power management device, thereby performing functions of managing charging, discharging, and power consumption via the power management device. Although not shown, the vector banking device may further include a camera, a bluetooth module, and the like, which are not described herein again.
The identification method and device for an automatic identification device and the application program product of the storage medium provided by the embodiment of the invention comprise the storage medium storing the program code, the instructions included in the program code can be used for executing the method described in the previous method embodiment, and specific implementation can refer to the method embodiment and is not described herein again.
The functions, if implemented in the form of software functional units and sold or used as independent products, may be stored in a vector banking apparatus readable storage medium. Based on such understanding, the technical solution of the present invention, or portions thereof that contribute to the prior art in essence, may be embodied in the form of a software product, where the vector banking apparatus application program is stored in a storage medium and includes several instructions for enabling a vector banking apparatus (which may be a mobile phone, a tablet computer, a vehicle-mounted computer, or a PDA, etc.) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A vector banking method, comprising:
establishing anchor points for all the registration vectors in the training model;
performing sub-base according to the registration vector with the anchor point relative identity degree within a preset range, and performing sub-base numbering on each sub-base to obtain a plurality of first sub-base numbers;
and obtaining a second sub-base number of the input vector, judging the sub-base corresponding to the first sub-base number with the input vector being the same as the second sub-base number as a target sub-base, and then calculating the degree of identity between the input vector and the registration vector in the target sub-base.
2. The vector banking method of claim 1 wherein the step of establishing anchor points for all registered vectors within the training model comprises:
and calculating N central points by using a clustering algorithm, and forming a matrix N by the registration vectors at the N central points, wherein the range of N is between 10 and 10000.
3. The vector banking method according to claim 2, wherein the step of banking the registration vectors within a preset range according to the relative identity of the anchor points, and numbering each of the banked vectors includes:
and calculating the registration vectors and the matrix N, and taking the sequence numbers of one or more most similar registration vectors as the sub-base numbers of the registration vectors to obtain a plurality of first sub-base numbers.
4. The vector banking method of claim 2, wherein the clustering algorithm is a k-means algorithm.
5. The vector banking method of claim 1, wherein the step of computing the registration vector and a matrix N comprises:
according to the formula
And calculating the degree of identity between the registration vector on the anchor point and other registration vectors, wherein a matrix N is formed by the registration vectors on a plurality of anchor points, m is the registration vector on one anchor point, and x is any registration vector.
6. A vector banking apparatus, comprising:
the anchor point establishing module is used for establishing anchor points for all the registration vectors in the training model;
the database dividing module is used for dividing the registration vector with the anchor point relative identity degree within a preset range and dividing and numbering each database to obtain a plurality of first database dividing numbers;
and the retrieval calculation module is used for obtaining a second sub-library number of the input vector, judging the sub-library corresponding to the first sub-library number with the same input vector and second sub-library number as a target sub-library, and then calculating the degree of identity between the input vector and the registration vector in the target sub-library.
7. The vector banking device according to claim 6, wherein the banking module further comprises a clustering algorithm sub-module for calculating N central points and forming the registration vectors at the N central points into a matrix N.
8. The vector binning apparatus of claim 6, wherein said binning module further comprises:
the calculation submodule is used for calculating the registration vector and the matrix N;
and the numbering submodule is used for taking the sequence numbers of one or more most similar registration vectors as the sub-base numbers of the registration vectors so as to obtain a plurality of first sub-base numbers.
9. A vector banking apparatus comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor implements the vector banking method of any one of claims 1 to 5 when executing the program.
10. A storage medium comprising a stored data area storing data created according to use of blockchain nodes and a stored program area storing a computer program, wherein the computer program when executed by a processor implements the vector banking method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010682732.9A CN111931821A (en) | 2020-07-15 | 2020-07-15 | Vector database partitioning method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010682732.9A CN111931821A (en) | 2020-07-15 | 2020-07-15 | Vector database partitioning method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111931821A true CN111931821A (en) | 2020-11-13 |
Family
ID=73313476
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010682732.9A Pending CN111931821A (en) | 2020-07-15 | 2020-07-15 | Vector database partitioning method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111931821A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117573655A (en) * | 2024-01-15 | 2024-02-20 | 中国标准化研究院 | Data management optimization method and system based on convolutional neural network |
-
2020
- 2020-07-15 CN CN202010682732.9A patent/CN111931821A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117573655A (en) * | 2024-01-15 | 2024-02-20 | 中国标准化研究院 | Data management optimization method and system based on convolutional neural network |
| CN117573655B (en) * | 2024-01-15 | 2024-03-12 | 中国标准化研究院 | Data management optimization method and system based on convolutional neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110009052B (en) | Image recognition method, image recognition model training method and device | |
| CN111368934B (en) | Image recognition model training method, image recognition method and related device | |
| CN110321965B (en) | Training method of object re-recognition model, and object re-recognition method and device | |
| CN110163367B (en) | Terminal deployment method and device | |
| CN108334539B (en) | Object recommendation method, mobile terminal and computer-readable storage medium | |
| CN104699973A (en) | Method and device for controlling logic of questionnaires | |
| CN106096359A (en) | A kind of solution lock control method and mobile terminal | |
| CN109376781B (en) | Training method of image recognition model, image recognition method and related device | |
| CN114444579B (en) | General disturbance acquisition method and device, storage medium and computer equipment | |
| CN114694226B (en) | Face recognition method, system and storage medium | |
| CN112820299A (en) | Voiceprint recognition model training method and device and related equipment | |
| CN107609533B (en) | Fingerprint unlocking method and related product | |
| CN113268572A (en) | Question answering method and device | |
| CN114973351A (en) | Face recognition method, device, equipment and storage medium | |
| CN110597957B (en) | Text information retrieval method and related device | |
| CN111931821A (en) | Vector database partitioning method, device, equipment and storage medium | |
| CN108256466B (en) | Data processing method and device, electronic equipment and computer readable storage medium | |
| CN112351441B (en) | Data processing method and device and electronic equipment | |
| CN114821751B (en) | Image recognition method, device, system and storage medium | |
| CN116383680A (en) | Clustering method, clustering device, electronic equipment and computer readable storage medium | |
| CN108352173B (en) | Method for controlling audio file playing and audio playing device | |
| CN115270163A (en) | Data processing method, related device and storage medium | |
| CN110809234A (en) | Figure category identification method and terminal equipment | |
| CN116257657B (en) | Data processing method, data query method, related device and storage medium | |
| CN115909186B (en) | Image information identification method, device, computer 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 |