CN111143703A - Intelligent line recommendation method and related product - Google Patents

Intelligent line recommendation method and related product Download PDF

Info

Publication number
CN111143703A
CN111143703A CN201911320923.4A CN201911320923A CN111143703A CN 111143703 A CN111143703 A CN 111143703A CN 201911320923 A CN201911320923 A CN 201911320923A CN 111143703 A CN111143703 A CN 111143703A
Authority
CN
China
Prior art keywords
artificial intelligence
objects
preset
action
video image
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.)
Granted
Application number
CN201911320923.4A
Other languages
Chinese (zh)
Other versions
CN111143703B (en
Inventor
不公告发明人
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Cambricon Information Technology Co Ltd
Original Assignee
Shanghai Cambricon Information Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Cambricon Information Technology Co Ltd filed Critical Shanghai Cambricon Information Technology Co Ltd
Priority to CN201911320923.4A priority Critical patent/CN111143703B/en
Publication of CN111143703A publication Critical patent/CN111143703A/en
Application granted granted Critical
Publication of CN111143703B publication Critical patent/CN111143703B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9536—Search customisation based on social or collaborative filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/01—Social networking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

The embodiment of the invention discloses an intelligent line recommendation method and a related product, which are applied to an intelligent line recommendation device, wherein the method comprises the following steps: the method comprises the steps that a processor conducts video analysis on a plurality of acquired shot videos to obtain a plurality of video image sets, an artificial intelligence chip conducts operation on video images in the plurality of video image sets in sequence according to a preset artificial intelligence algorithm to obtain a first position where a first object is located currently and m other positions where m other objects are located in a cell, a predictor predicts m reference action tracks of the m other objects according to the m other positions of the m other objects and a plurality of action tracks stored in a memory in advance, and the processor recommends a target action line for the first object according to the m reference action tracks and the first position.

Description

Intelligent line recommendation method and related product
Technical Field
The invention relates to the technical field of video processing, in particular to an intelligent line recommendation method and a related product.
Background
At present, urban districts are more and more modern, the activities of people in the districts are more and more diversified, the activity connection in the districts is more and more compact, in order to make the district service more intelligent and improve the activity experience of residents in the districts, more individual and more intimate service needs to be provided for the residents, so that the problems that the relationship between people is more compact, and the relationship between people, pets and pets is more harmonious need to be solved.
Disclosure of Invention
The embodiment of the invention provides an intelligent line recommendation method and a related product, which improve the activity experience of a user in a cell by pushing a target action line for a first object which is active in the cell.
In a first aspect, an embodiment of the present invention provides an intelligent line recommendation method, which is applied to an intelligent line recommendation apparatus, where the apparatus includes a processor, an artificial intelligence chip, a predictor, and a memory, and the method includes:
the processor performs video analysis on the obtained shooting videos to obtain a plurality of video image sets, wherein the shooting videos are shooting videos of different areas of a cell in a first preset time period;
the artificial intelligence chip sequentially operates the video images in the plurality of video image sets according to a preset artificial intelligence algorithm to obtain a first position where a first object is located currently in the cell and m other positions where m other objects are located, wherein m is a positive integer, each other object corresponds to one other position, and the first position and the m other positions are located in different areas in the cell;
the predictor predicts m reference action tracks of the m other objects according to m other positions of the m other objects and a plurality of action tracks stored in the memory in advance;
and the processor recommends a target action line for the first object according to the m reference action tracks and the first position.
In a second aspect, an embodiment of the present invention provides an intelligent line recommendation apparatus, which includes a processor, an artificial intelligence chip, a predictor, and a memory, wherein,
the processor is used for performing video analysis on the obtained shooting videos to obtain a plurality of video image sets, wherein the shooting videos are shooting videos of different areas of a cell in a first preset time period;
the artificial intelligence chip is used for sequentially operating the video images in the plurality of video image sets according to a preset artificial intelligence algorithm to obtain a first position where a first object is located currently in the cell and m other positions where m other objects are located, wherein m is a positive integer, each other object corresponds to one other position, and the first position and the m other positions are located in different areas in the cell;
the predictor is used for predicting m reference action tracks of the m other objects according to m other positions of the m other objects and a plurality of action tracks stored in the memory in advance;
the processor is further configured to recommend a target action line for the first object according to the m reference action tracks and the first position.
In a third aspect, an embodiment of the present invention provides an intelligent line recommendation apparatus, including a processor, an artificial intelligence chip, a predictor, a memory, and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the processor, the artificial intelligence chip, and the predictor, and the programs include instructions for executing the steps in the first aspect of the embodiment of the present invention.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program for electronic data exchange, where the computer program makes a computer perform part or all of the steps described in the first aspect of the embodiment of the present invention.
In a fifth aspect, embodiments of the present invention provide a computer program product, where the computer program product comprises a non-transitory computer-readable storage medium storing a computer program, where the computer program is operable to cause a computer to perform some or all of the steps as described in the first aspect of embodiments of the present invention. The computer program product may be a software installation package.
The embodiment of the invention has the following beneficial effects:
it can be seen that, in the intelligent line recommendation method and the related product described in the embodiments of the present invention, the processor performs video analysis on the obtained multiple captured videos to obtain multiple video image sets, the artificial intelligence chip sequentially performs operations on the video images in the multiple video image sets according to a preset artificial intelligence algorithm to obtain a current first position of the first object in the cell and m other positions of the m other objects, the predictor predicts m reference action tracks of the m other objects according to the m other positions of the m other objects and the multiple action tracks pre-stored in the memory, and the processor recommends the target action line for the first object according to the m reference action tracks and the first position, so that the target action line can be pushed for the first object according to the m reference action tracks of the other objects in the cell to improve the processing speed of the video images, therefore, the route recommendation can be rapidly and effectively carried out, the recommended traveling route of the first object can be reasonably planned and adjusted according to the other m objects, and the activity experience of the user in the cell is further improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1A is a system diagram of a pet monitoring system according to an embodiment of the present invention;
fig. 1B is a schematic structural diagram of an intelligent line recommendation device according to an embodiment of the present invention;
FIG. 1C is a schematic structural diagram of an artificial intelligence chip according to an embodiment of the present invention;
fig. 2A is a schematic flowchart of an intelligent route recommendation method according to an embodiment of the present invention;
fig. 2B is a schematic illustration of an electronic map according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of another intelligent route recommendation method according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of another intelligent route recommendation device provided in the embodiment of the present invention;
fig. 5 is a schematic structural diagram of an intelligent line recommendation device according to an embodiment of the present invention.
Detailed Description
The terms "first," "second," and the like in the description and claims of the present invention and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
The terminal device related to the embodiments of the present application may include various handheld devices, vehicle-mounted devices, wearable devices (smart watches, smart bracelets, wireless headsets, augmented reality/virtual reality devices, smart glasses), computing devices or other processing devices connected to wireless modems, and various forms of User Equipment (UE), Mobile Stations (MS), control platforms, terminal devices (terminal device), and the like, which have wireless communication functions. For convenience of description, the above-mentioned devices are collectively referred to as terminal devices. The intelligent transportation system is applied to the terminal equipment.
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1A, fig. 1A provides a system diagram of an intelligent route recommendation system implementing the intelligent route recommendation method. The pet monitoring system can include a plurality of cameras, intelligent line recommendation devices and user's terminal equipment which are arranged in each region in the cell, wherein the plurality of cameras can be connected with the intelligent line recommendation devices, the intelligent line recommendation devices can be in communication connection with the user's terminal equipment, videos of each region in the cell can be shot through the plurality of cameras, and therefore the intelligent line recommendation devices can obtain a plurality of shooting videos shot by the plurality of cameras.
Optionally, the intelligent line recommendation device may include a plurality of cameras disposed in each area in the cell, so that the videos of each area in the cell may be captured by the plurality of cameras to obtain a plurality of captured videos.
Further, when the first object is going to go out, the intelligent route recommendation device can recommend the target action route for the first object according to the obtained multiple shot videos, and then the target action route is pushed to the user.
Referring to fig. 1B, fig. 1B provides an intelligent route recommendation device, which may be implemented to perform intelligent route recommendation for a user, and as shown in fig. 1B, the intelligent route recommendation device includes: the system comprises a processor 110, an artificial intelligence chip 111, a predictor 112 and a memory 113, wherein the artificial intelligence chip comprises a data converter, a data access circuit, a register circuit and an arithmetic circuit.
The Processor 110 may be a general-purpose Processor, such as a Central Processing Unit (CPU), a Digital Signal Processor (DSP), a Graphics Processing Unit (GPU), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, a discrete hardware component, and so on. Optionally, the processor 110 may be an artificial intelligence processor.
Referring to fig. 1C, fig. 1C is a schematic structural diagram of an artificial intelligence chip applied to an intelligent line recommendation device, where the intelligent line recommendation device may further include a processor, a predictor, and a memory in addition to the artificial intelligence chip, the artificial intelligence chip may be configured to perform an image recognition operation, and the artificial intelligence chip may include: data converter, data access circuit, register circuit, arithmetic circuit, wherein, arithmetic circuit can include: two or more of an addition calculator, a multiplication calculator, a comparator and an activation calculator. In practical applications, the arithmetic circuit may include a plurality of addition calculators or a plurality of multiplication calculators, and the number of addition calculators, multiplication calculators, comparators, and activation calculators included in the arithmetic circuit may be unlimited in practical applications. The register circuit is used for storing an operation instruction, an address of a data block in a storage medium and a calculation topological structure corresponding to the operation instruction.
In a specific implementation, in an intelligent line recommendation scene, the data converter converts a first video image in the plurality of video image sets into first input data and transmits the first input data to the data access circuit; the data access circuit sends the first input data to the arithmetic circuit; the data access circuit reads an operation instruction from the register circuit and sends the operation instruction to the operation circuit; the arithmetic circuit carries out pixel gradient calculation according to the arithmetic instruction and the first input data to obtain gradient amplitudes and gradient directions of all pixel points in the first video image; and counting the gradient amplitudes and gradient directions of all the pixel points to obtain a feature vector set of the first object in the first video image, and determining a first position where the first object is located currently according to the feature vector set. Through the artificial intelligence chip, the video images in the plurality of video image sets can be sequentially operated according to a preset artificial intelligence algorithm to obtain m other positions where m other objects in the cell are located, further, the data access circuit can transmit the current first position where the first object is located to the processor and transmit the m other positions where the m other objects are located to the predictor, the predictor predicts m reference action tracks of the m other objects according to the m other positions of the m other objects and a plurality of action tracks prestored in the memory, and finally, the processor recommends a target action line for the first object according to the m reference action tracks and the first position.
Fig. 2A is a schematic flow chart of an intelligent line recommendation method according to an embodiment of the present invention. The intelligent line recommendation method described in this embodiment is applied to an intelligent line recommendation device shown in fig. 1B, where the device includes a processor, an artificial intelligence chip, a predictor, and a memory, and the method includes the following steps:
201. the processor performs video analysis on the obtained shooting videos to obtain a plurality of video image sets, wherein the shooting videos are shooting videos of different areas of a cell in a first preset time period.
The first preset time period may be set by the user or default by the system, for example, the first preset time period may be the last 1 minute, or the last 3 minutes, the last 5 minutes, and the like, which is not limited herein.
In the embodiment of the invention, a plurality of cameras can be arranged in each area in the cell, the cameras can be single cameras or multiple cameras, and the single cameras can be infrared cameras, visible light cameras, wide-angle cameras and double cameras. Personnel activities and animal activities in each area in the cell can be shot through the camera, so that the processor can acquire a plurality of shooting videos shot by the camera in a preset time period.
202. And the artificial intelligence chip sequentially operates the video images in the plurality of video image sets according to a preset artificial intelligence algorithm to obtain a first position where a first object is located currently in the cell and m other positions where m other objects are located, wherein m is a positive integer, each other object corresponds to one other position, and the first position and the m other positions are located in different areas in the cell.
Wherein the first object may be a person or an animal, and the m other objects may include a person or an animal.
The preset artificial intelligence algorithm may include any one of the following: histogram of Oriented Gradients (HOG) algorithm, hough transform method, Haar feature cascade classifier algorithm or Local Binary Pattern (LBP) algorithm, etc., without limitation.
In specific implementation, the artificial intelligence chip can perform object identification on the video images in the plurality of video image sets, determine whether people or animals exist in the video images, identify the people or the animals, and further determine the positions of the people or the animals.
The following is a detailed description of the histogram algorithm with directional gradient.
Optionally, the preset artificial intelligence algorithm includes a direction gradient histogram algorithm, the artificial intelligence chip includes a data converter, a data access circuit, a register circuit, and an arithmetic circuit, and in step 202, the sequentially performing, by the artificial intelligence chip, an operation on the video images in the plurality of video image sets according to the preset artificial intelligence algorithm to obtain a current first position of the first object in the cell may include the following steps:
21. the data converter converts a first video image of the plurality of sets of video images into first input data and transmits the first input data to a data access circuit;
22. the data access circuit sends the first input data to the arithmetic circuit; the data access circuit reads an operation instruction from the register circuit and sends the operation instruction to the operation circuit;
23. the arithmetic circuit carries out pixel gradient calculation according to the arithmetic instruction and the first input data to obtain gradient amplitudes and gradient directions of all pixel points in the first video image; and counting the gradient amplitudes and gradient directions of all the pixel points to obtain a feature vector set of the first object in the first video image, and determining a first position where the first object is located currently according to the feature vector set.
In the specific implementation, the arithmetic circuit can perform pixel gradient calculation according to the first input data to obtain gradient amplitudes and gradient directions of all pixel points in the first video image, count the gradient amplitudes and the gradient directions of all the pixel points to obtain a feature vector set belonging to the first object in the first video image, wherein the feature vector set can comprise a plurality of HOG features of the first object, and then can determine a first position where the first object is located currently according to the feature vector set.
According to the mode, the artificial intelligence chip can also sequentially operate the video images in the plurality of video image sets according to a preset artificial intelligence algorithm to obtain m other positions where m other objects are located in the cell.
Optionally, before the artificial intelligence chip sequentially operates the video images in the plurality of video image sets according to a preset artificial intelligence algorithm, the method may further include the following steps:
24. the processor determines the similarity among a plurality of video images in each video image set within a first preset time length to obtain at least one similarity set;
25. taking a plurality of video images with the similarity greater than a preset threshold in each similarity set in the at least one similarity set as a group of repeated video images to obtain at least one group of repeated video images;
26. performing quality evaluation on each group of repeated video images in the at least one group of repeated video images to obtain at least one group of quality evaluation values;
27. selecting the maximum quality evaluation value in each group of quality evaluation values in the at least one group of quality evaluation values to obtain at least one maximum quality evaluation value;
28. and selecting the video images corresponding to each maximum quality evaluation value in the plurality of video image sets to obtain a plurality of screened video images.
The first preset time period may be set by a user or default by a system, for example, the first preset time period may be 5 seconds or 10 seconds, and the like, which is not limited herein.
Considering that the plurality of video images include repeated video images appearing at adjacent moments in the same shot video, in order to reduce the number of video images operated by the artificial intelligence chip on the video images, at least one group of repeated video images in the plurality of video images may be determined, for example, in one shot video, within a period from the fifth second to the seventh second, the same pet is shot to move in the same place, and the similarity between the video images within the fifth second to the seventh second obtained by analysis is greater than a preset threshold, at this time, the video images within the period may be determined as a group of repeated video images, wherein, for the video image in any shot video, the similarity between each video image and other video images adjacent thereto within a preset time period may be determined, and if the similarity is greater than the preset threshold, the two compared video images may be determined as the repeated video images, thus, at least one set of repeated video images may be obtained. Therefore, at least one group of repeated video images in the plurality of videos can be determined, then, each group of repeated video images in the at least one group of repeated video images is subjected to instruction evaluation to obtain a plurality of groups of quality evaluation values, so that the first video image with the best quality in each group of repeated video images in the at least one group of repeated video images can be selected, at least one first video image corresponding to the at least one group of repeated video images is reserved, and the at least one video image and other video images without repetition are taken as a plurality of target video images.
Therefore, by deleting part of the repeated video images in the plurality of video images, the number of images for subsequent processing can be reduced, the image processing efficiency can be improved, and the efficiency for subsequent processing of the first video image can be improved by reserving the first video image with the highest quality evaluation value in each group of repeated video images.
203. The predictor predicts m reference action tracks of the m other objects according to m other positions of the m other objects and a plurality of action tracks stored in the memory in advance.
In a specific implementation, a plurality of action tracks may be stored in the memory in advance, and the plurality of action tracks may be a plurality of action tracks in which a plurality of objects act frequently determined according to a plurality of historical videos of the plurality of objects in the cell. For example, if the first preset time period is within a time period range of 6: 00-7: 00, available in the last month often 6: 00-7: 00 a plurality of objects moving in the cell, and determining the action track of each object in the plurality of objects moving frequently, obtaining a plurality of action tracks, and storing the plurality of action tracks in the memory. Therefore, after the predictor acquires the m other positions of the m other objects in the first preset time period, the reference action track, in which each other object in the m other objects will move, can be predicted according to the pre-stored action tracks corresponding to the objects and the m other positions of the m other objects, so as to acquire the reference action tracks.
Optionally, in this embodiment of the present application, the following steps may also be included:
the processor acquires a plurality of historical videos of different areas of the cell in a second preset time period;
carrying out object identification according to the plurality of historical videos to obtain a plurality of historical identification results of a plurality of objects, wherein each historical identification result comprises a position corresponding to one object, and each historical identification result corresponds to one shooting time;
determining the action tracks according to the historical recognition results and shooting times corresponding to the historical recognition results one by one, wherein each action track is the action track of an object in the second preset time period;
storing the plurality of action trajectories to the memory.
The second preset time period may be set by the user or default by the system, for example, the second preset time period may be the last week, or the last month, the last three months, and the like, which is not limited herein.
In a specific implementation, a plurality of historical videos of different areas of the cell within a second preset time period, for example a plurality of historical videos of the last month, and performing object identification according to the plurality of historical videos to obtain a plurality of historical identification results of a plurality of objects, for example, an animal, such as a dog, or that a person is often present at multiple locations within a certain time period (e.g., 6: 00-7: 00, or, 20: 00-21: 00), then connecting the positions according to the time sequence of the appearance of the animal or the human in the time period to obtain the action track of the animal or the human in the time period, thus, a plurality of action tracks of a plurality of persons or animals who often move in a cell in each time period can be determined from a plurality of history videos, and the plurality of action tracks of a plurality of objects can be stored in a memory.
204. And the processor recommends a target action line for the first object according to the m reference action tracks and the first position.
In this embodiment, the first object may be a person or an animal, such as a pet of a user, for which a target action line is recommended, a walking action line for the user, or an activity line for the pet of the user. In a specific implementation, the action line can be pushed to the user according to the relationship between the first object and m other objects, for example, an acquaintance of the first object or an animal that the first object likes among the m other objects, and the target action line on the same way as the acquaintance can be pushed to the user, and for example, an animal that the first object is afraid of or a person that does not have a good relationship with the first object among the m other objects, the target action line that avoids the animal or the person can be pushed to the user. Therefore, the target action line can be pushed for the first object according to the m reference action tracks of other objects in the cell, so that the recommended travelling route of the first object can be reasonably planned and adjusted according to the m reference action tracks of the other objects, and the activity experience of the user in the cell is improved.
Optionally, the first object is a first animal, the m other objects are m animals, or the first object is a first person, the m other objects are m persons, and the processor recommends a target action route for the first object according to the m reference action tracks and the first position, and may include the following steps:
41. the processor acquires a preset cell map;
42. acquiring the intimacy between each other object in the m other objects and the first object to obtain m intimacy;
43. determining a maximum intimacy degree of the m intimacy degrees;
44. and generating a target action route overlapped with the selected reference action track according to the reference action track corresponding to the maximum intimacy degree in the m reference action tracks and the preset cell map.
The intimacy between each of the m other objects and the first object may be preset, specifically, the user may set the intimacy between the first person and the other persons in advance through the terminal device, or the intimacy between the first animal and the other animals in advance, and report the set intimacy to the intelligent line recommendation device, and then the intelligent line recommendation device may obtain the intimacy between the multiple objects in the cell in advance, so as to obtain multiple intimacy. Therefore, in the process of intelligently pushing the line to the first object, the processor can obtain the intimacy between each other object in the m other objects and the first object to obtain m intimacy.
Referring to fig. 2B, fig. 2B is a schematic diagram illustrating an intelligent route recommendation according to an embodiment of the present invention, where a first object is assumed to be a first person, and m other objects are m persons, an intimacy between the first person and each of the m other persons may be determined, m intimacy are obtained, a maximum intimacy among the m intimacy is determined, a target action route overlapping with a selected reference action track is generated according to a reference action track of the target other person corresponding to the maximum intimacy among the m reference action tracks, and a preset cell map is used, so that a close and personalized action route may be pushed to a user more intelligently.
Optionally, if the first object is a first person, the m other objects are m persons, the intimacy may also be intimacy between the first person and the m other persons in the social application, specifically, a friend relationship exists between the first person and some of the m other persons, and a friend relationship does not exist between the first person and another of the m other persons, then the intimacy between the first person and some of the m other persons is higher, and the intimacy in the social application may also be obtained to obtain the intimacy between the first person and the first person, and the intimacy between the first person and another of the m other persons may be set to 0.
In a specific implementation, if the first object is a first animal and m other objects are m animals, or the first object is a first person and m other objects are m persons, the intimacy between each of the m other objects and the first object can be obtained to obtain m intimacy, and further, according to a reference action track corresponding to the maximum intimacy in the m reference action tracks, and according to a preset cell map, a target action route overlapped with the selected reference action track is generated, so that when the first object is the first animal and the m other objects are m animals, an intelligent route which moves together with the other animals with the highest intimacy can be pushed for the first animal, and when the first object is the first person and the m other objects are m persons, an intelligent route which moves together with the other persons with the highest intimacy can be pushed for the first person, therefore, the activity experience of the user in the cell can be improved.
It can be seen that, with the intelligent line recommendation method described in the embodiment of the present invention, the obtained multiple captured videos are subjected to video analysis by the processor to obtain multiple video image sets, the artificial intelligence chip sequentially operates the video images in the multiple video image sets according to a preset artificial intelligence algorithm to obtain a current first position of the first object and m other positions of the m other objects in the cell, the predictor predicts m reference action tracks of the m other objects according to the m other positions of the m other objects and the multiple action tracks pre-stored in the memory, and the processor recommends the target action line for the first object according to the m reference action tracks and the first position, so that the target action line can be pushed for the first object according to the m reference action tracks of the other objects in the cell to improve the processing speed of the video images, therefore, the route recommendation can be rapidly and effectively carried out, the recommended traveling route of the first object can be reasonably planned and adjusted according to the other m objects, and the activity experience of the user in the cell is further improved.
Referring to fig. 3, a flowchart of an embodiment of an intelligent line recommendation method according to an embodiment of the present invention is shown, which is consistent with fig. 2A. The intelligent route recommendation method described in this embodiment is applied to the intelligent route recommendation apparatus shown in fig. 1B, and the method includes the following steps:
301. the processor performs video analysis on the obtained shooting videos to obtain a plurality of video image sets, wherein the shooting videos are shooting videos of different areas of a cell in a first preset time period.
302. The artificial intelligence chip sequentially operates the video images in the plurality of video image sets according to a preset artificial intelligence algorithm to obtain a first position where a first object is located currently in the cell and m other positions where m other objects are located, wherein m is a positive integer, each other object corresponds to one other position, and the first position and the m other positions are located in different areas in the cell.
303. The predictor predicts m reference action trajectories of the m other objects according to m other positions of the m other objects and a plurality of action trajectories stored in the memory in advance.
304. The first object is a first person, the m other objects are m animals, and the processor acquires a preset cell map; and acquiring a preset user label of the first person.
305. And if the preset user label meets a preset condition, generating a target action line with the minimum intersection with the m reference action tracks according to the preset cell map.
The user tag may be a user tag determined according to usage data of the terminal device used by the user, for example, the user tag may be determined according to the usage data of the mobile phone used by the user, and the user tag may also be a tag set by the user. The user tags may be, for example, favorite animals, disfavorite animals, fear of big dogs, and the like, without limitation. Therefore, when the preset user label is a dog with a large fear body, the target action line with the least animals can be pushed for the user.
The preset user tag satisfies a preset condition, for example, the preset user tag may be a favorite animal, a fear animal, or the like. In specific implementation, if the first object is a first person, the m other objects are m animals, the preset user tag is an animal which is not liked or afraid of the animal, and a target action line with the minimum intersection with the m reference action tracks can be generated according to the preset cell map, so that the activity experience of the user in the cell can be improved.
The detailed description of the steps 301-305 may refer to the corresponding description of the intelligent line recommendation method described in fig. 2A, and will not be described herein again.
It can be seen that, according to the intelligent line recommendation method described in the embodiment of the present invention, a processor performs video analysis on a plurality of acquired captured videos to obtain a plurality of video image sets, an artificial intelligence chip sequentially performs operations on video images in the plurality of video image sets according to a preset artificial intelligence algorithm to obtain a current first position of a first object in a cell and m other positions of m other objects, a predictor predicts m reference action tracks of the m other objects according to the m other positions of the m other objects and a plurality of action tracks pre-stored in a memory, and the processor acquires a preset cell map; acquiring a preset user label of a first person; if the preset user label meets the preset condition, a target action line with the minimum intersection with the m reference action tracks is generated according to the preset cell map, so that the target action line can be pushed for the first object according to the m reference action tracks of other objects in the cell, the processing speed of the video image is increased, the route recommendation can be rapidly and effectively carried out, the recommended travelling route of the first object can be reasonably planned and adjusted according to the m other objects, and the activity experience of the user in the cell is further improved.
The following is a device for implementing the intelligent route recommendation method, specifically as follows:
in accordance with the above, please refer to fig. 4, where fig. 4 is a schematic structural diagram of an intelligent line recommendation device according to an embodiment of the present invention, the intelligent line recommendation device described in this embodiment includes: a processor 410, a memory 420, an artificial intelligence chip 430 and a predictor 440; and one or more programs 421, the one or more programs 421 stored in the memory and configured to be executed by the processor, artificial intelligence chip, and predictor, the programs 421 including instructions for:
performing video analysis on the obtained shooting videos to obtain a plurality of video image sets, wherein the shooting videos are shooting videos of different areas of a cell in a first preset time period;
sequentially operating the video images in the plurality of video image sets according to a preset artificial intelligence algorithm to obtain a first position where a first object is located currently in the cell and m other positions where m other objects are located, wherein m is a positive integer, each other object corresponds to one other position, and the first position and the m other positions are located in different areas in the cell;
predicting m reference action trajectories of the m other objects according to m other positions of the m other objects and a plurality of action trajectories stored in the memory in advance;
recommending a target action line for the first object according to the m reference action tracks and the first position.
In one possible example, the preset artificial intelligence algorithm includes a direction gradient histogram algorithm, and in terms of the sequentially operating the video images in the plurality of video image sets according to the preset artificial intelligence algorithm to obtain the current first position of the first object in the cell, the program 421 includes instructions for performing the following steps:
converting a first video image of the plurality of sets of video images into first input data and transmitting the first input data to a data access circuit;
sending the first input data to an arithmetic circuit; the data access circuit reads an operation instruction from the register circuit and sends the operation instruction to the operation circuit;
performing pixel gradient calculation according to the operation instruction and the first input data to obtain gradient amplitudes and gradient directions of all pixel points in the first video image; and counting the gradient amplitudes and gradient directions of all the pixel points to obtain a feature vector set of the first object in the first video image, and determining a first position where the first object is located currently according to the feature vector set.
In one possible example, before the artificial intelligence chip sequentially operates the video images in the plurality of video image sets according to a preset artificial intelligence algorithm, the program 421 further includes instructions for performing the following steps:
determining the similarity among a plurality of video images in each video image set within a first preset time length to obtain at least one similarity set;
taking a plurality of video images with the similarity greater than a preset threshold in each similarity set in the at least one similarity set as a group of repeated video images to obtain at least one group of repeated video images;
performing quality evaluation on each group of repeated video images in the at least one group of repeated video images to obtain at least one group of quality evaluation values;
selecting the maximum quality evaluation value in each group of quality evaluation values in the at least one group of quality evaluation values to obtain at least one maximum quality evaluation value;
and selecting the video images corresponding to each maximum quality evaluation value in the plurality of video image sets to obtain a plurality of screened video images.
In one possible example, the program 421 further includes instructions for performing the steps of:
acquiring a plurality of historical videos of different areas of the cell within a second preset time period;
carrying out object identification according to the plurality of historical videos to obtain a plurality of historical identification results of a plurality of objects, wherein each historical identification result comprises a position corresponding to one object, and each historical identification result corresponds to one shooting time;
determining the action tracks according to the historical recognition results and shooting times corresponding to the historical recognition results one by one, wherein each action track is the action track of an object in the second preset time period;
storing the plurality of action trajectories to the memory.
In one possible example, the first object is a first animal and the m other objects are m animals, or the first object is a first person and the m other objects are m persons, the program 421 comprises instructions for performing the following steps in recommending a target course of action for the first object based on the m reference trajectories of action and the first position:
acquiring a preset cell map;
acquiring the intimacy between each other object in the m other objects and the first object to obtain m intimacy;
determining a maximum intimacy degree of the m intimacy degrees;
and generating a target action route overlapped with the selected reference action track according to the reference action track corresponding to the maximum intimacy degree in the m reference action tracks and the preset cell map.
In one possible example, the first object is a first person, the m other objects are m animals, and in said recommending a target course of action for the first object based on the m reference trajectories of action and the first position, the program 421 comprises instructions for:
acquiring a preset cell map; acquiring a preset user label of the first person;
and if the preset user label meets a preset condition, generating a target action line with the minimum intersection with the m reference action tracks according to the preset cell map.
Referring to fig. 5, fig. 5 is a schematic structural diagram of an intelligent line recommendation apparatus according to the present embodiment, where the intelligent line recommendation apparatus 500 described in the present embodiment includes a processor 501, an artificial intelligence chip 502, a predictor 503 and a memory 504, where,
the processor is used for performing video analysis on the obtained shooting videos to obtain a plurality of video image sets, wherein the shooting videos are shooting videos of different areas of a cell in a first preset time period;
the artificial intelligence chip is used for sequentially operating the video images in the plurality of video image sets according to a preset artificial intelligence algorithm to obtain a first position where a first object is located currently in the cell and m other positions where m other objects are located, wherein m is a positive integer, each other object corresponds to one other position, and the first position and the m other positions are located in different areas in the cell;
the predictor is used for predicting m reference action tracks of the m other objects according to m other positions of the m other objects and a plurality of action tracks stored in the memory in advance;
the processor is further configured to recommend a target action line for the first object according to the m reference action tracks and the first position.
Optionally, the preset artificial intelligence algorithm includes a direction gradient histogram algorithm, the artificial intelligence chip includes a data converter, a data access circuit, a register circuit, and an arithmetic circuit, wherein in the aspect that the artificial intelligence chip sequentially operates the video images in the plurality of video image sets according to the preset artificial intelligence algorithm to obtain a first position where the first object is currently located in the cell,
the data converter is used for converting a first video image in the plurality of video image sets into first input data and transmitting the first input data to the data access circuit;
the data access circuit is used for sending the first input data to the arithmetic circuit; the data access circuit reads an operation instruction from the register circuit and sends the operation instruction to the operation circuit;
the arithmetic circuit is used for carrying out pixel gradient calculation according to the arithmetic instruction and the first input data to obtain gradient amplitudes and gradient directions of all pixel points in the first video image; and counting the gradient amplitudes and gradient directions of all the pixel points to obtain a feature vector set of the first object in the first video image, and determining a first position where the first object is located currently according to the feature vector set.
Optionally, before the artificial intelligence chip sequentially operates the video images in the plurality of video image sets according to a preset artificial intelligence algorithm, the processor is further configured to:
determining the similarity among a plurality of video images in each video image set within a first preset time length to obtain at least one similarity set;
taking a plurality of video images with the similarity greater than a preset threshold in each similarity set in the at least one similarity set as a group of repeated video images to obtain at least one group of repeated video images;
performing quality evaluation on each group of repeated video images in the at least one group of repeated video images to obtain at least one group of quality evaluation values;
selecting the maximum quality evaluation value in each group of quality evaluation values in the at least one group of quality evaluation values to obtain at least one maximum quality evaluation value;
and selecting the video images corresponding to each maximum quality evaluation value in the plurality of video image sets to obtain a plurality of screened video images.
Optionally, the processor is further configured to:
acquiring a plurality of historical videos of different areas of the cell within a second preset time period;
carrying out object identification according to the plurality of historical videos to obtain a plurality of historical identification results of a plurality of objects, wherein each historical identification result comprises a position corresponding to one object, and each historical identification result corresponds to one shooting time;
determining the action tracks according to the historical recognition results and shooting times corresponding to the historical recognition results one by one, wherein each action track is the action track of an object in the second preset time period;
storing the plurality of action trajectories to the memory.
Optionally, the first object is a first animal, the m other objects are m animals, or the first object is a first person, the m other objects are m persons, and in terms of the processor recommending a target action route for the first object according to the m reference action tracks and the first position, the processor is specifically configured to:
acquiring a preset cell map;
acquiring the intimacy between each other object in the m other objects and the first object to obtain m intimacy;
determining a maximum intimacy degree of the m intimacy degrees;
and generating a target action route overlapped with the selected reference action track according to the reference action track corresponding to the maximum intimacy degree in the m reference action tracks and the preset cell map.
Optionally, the first object is a first person, the m other objects are m animals, and in the aspect that the processor recommends the target action route for the first object according to the m reference action tracks and the first position, the processor is specifically configured to:
acquiring a preset cell map; acquiring a preset user label of the first person;
and if the preset user label meets a preset condition, generating a target action line with the minimum intersection with the m reference action tracks according to the preset cell map.
It can be seen that, with the intelligent line recommendation apparatus described in the foregoing embodiment of the present invention, the processor performs video analysis on the obtained multiple captured videos to obtain multiple video image sets, the artificial intelligence chip sequentially performs operations on the video images in the multiple video image sets according to a preset artificial intelligence algorithm to obtain a current first position of the first object in the cell and m other positions of the m other objects, the predictor predicts m reference action trajectories of the m other objects according to the m other positions of the m other objects and the multiple action trajectories pre-stored in the memory, and the processor recommends the target action line for the first object according to the m reference action trajectories and the first position, so that the target action line can be pushed for the first object according to the m reference action trajectories of the other objects in the cell, and thus, the recommended travel route of the first object can be reasonably planned and adjusted according to the other m objects, and the activity experience of the user in the cell is further improved.
It can be understood that the functions of each program module of the intelligent line recommendation device in this embodiment may be specifically implemented according to the method in the foregoing method embodiment, and the specific implementation process may refer to the related description of the foregoing method embodiment, which is not described herein again.
An embodiment of the present invention further provides a computer storage medium, where the computer storage medium stores a computer program for electronic data exchange, the computer program enables a computer to execute part or all of the steps of any one of the methods described in the above method embodiments, and the computer includes an intelligent line recommendation device.
Embodiments of the present invention also provide a computer program product comprising a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods as described in the above method embodiments. The computer program product may be a software installation package, said computer comprising intelligent line recommendation means.
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus can be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the above-described division of the units is only one type of division of logical functions, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some interfaces, devices or units, and may be an electric or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit may be stored in a computer readable memory if it is implemented in the form of a software functional unit and sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a memory and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the above methods according to the embodiments of the present invention. And the aforementioned memory comprises: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable memory, which may include: flash Memory disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.
The above embodiments of the present invention are described in detail, and the principle and the implementation of the present invention are explained by applying specific embodiments, and the above description of the embodiments is only used to help understanding the method of the present invention and the core idea thereof; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims (10)

1. An intelligent line recommendation method applied to an intelligent line recommendation device, the device comprising a processor, an artificial intelligence chip, a predictor and a memory, the method comprising:
the processor performs video analysis on the obtained shooting videos to obtain a plurality of video image sets, wherein the shooting videos are shooting videos of different areas of a cell in a first preset time period;
the artificial intelligence chip sequentially operates the video images in the plurality of video image sets according to a preset artificial intelligence algorithm to obtain a first position where a first object is located currently in the cell and m other positions where m other objects are located, wherein m is a positive integer, each other object corresponds to one other position, and the first position and the m other positions are located in different areas in the cell;
the predictor predicts m reference action tracks of the m other objects according to m other positions of the m other objects and a plurality of action tracks stored in the memory in advance;
and the processor recommends a target action line for the first object according to the m reference action tracks and the first position.
2. The method of claim 1, wherein the artificial intelligence chip comprises a data converter, a data access circuit, a register circuit, and an arithmetic circuit, and the obtaining the current first position of the first object in the cell by sequentially performing operations on the video images in the plurality of video image sets by the artificial intelligence chip according to a preset artificial intelligence algorithm comprises:
the data converter converts a first video image of the plurality of sets of video images into first input data and transmits the first input data to a data access circuit;
the data access circuit sends the first input data to the arithmetic circuit; the data access circuit reads an operation instruction from the register circuit and sends the operation instruction to the operation circuit;
the arithmetic circuit carries out pixel gradient calculation according to the arithmetic instruction and the first input data to obtain gradient amplitudes and gradient directions of all pixel points in the first video image; and counting the gradient amplitudes and gradient directions of all the pixel points to obtain a feature vector set of the first object in the first video image, and determining a first position where the first object is located currently according to the feature vector set.
3. The method according to claim 1 or 2, wherein before the artificial intelligence chip sequentially operates the video images in the plurality of video image sets according to a preset artificial intelligence algorithm, the method further comprises:
the processor determines the similarity among a plurality of video images in each video image set within a first preset time length to obtain at least one similarity set;
taking a plurality of video images with the similarity greater than a preset threshold in each similarity set in the at least one similarity set as a group of repeated video images to obtain at least one group of repeated video images;
performing quality evaluation on each group of repeated video images in the at least one group of repeated video images to obtain at least one group of quality evaluation values;
selecting the maximum quality evaluation value in each group of quality evaluation values in the at least one group of quality evaluation values to obtain at least one maximum quality evaluation value;
and selecting the video images corresponding to each maximum quality evaluation value in the plurality of video image sets to obtain a plurality of screened video images.
4. The method according to any one of claims 1-3, further comprising:
the processor acquires a plurality of historical videos of different areas of the cell in a second preset time period;
carrying out object identification according to the plurality of historical videos to obtain a plurality of historical identification results of a plurality of objects, wherein each historical identification result comprises a position corresponding to one object, and each historical identification result corresponds to one shooting time;
determining the action tracks according to the historical recognition results and shooting times corresponding to the historical recognition results one by one, wherein each action track is the action track of an object in the second preset time period;
storing the plurality of action trajectories to the memory.
5. The method of any one of claims 1-4, wherein the first object is a first animal and the m other objects are m animals, or wherein the first object is a first person and the m other objects are m persons, and wherein the processor recommends a target course of action for the first object based on the m reference trajectories of action and the first location, comprising:
the processor acquires a preset cell map;
acquiring the intimacy between each other object in the m other objects and the first object to obtain m intimacy;
determining a maximum intimacy degree of the m intimacy degrees;
and generating a target action route overlapped with the selected reference action track according to the reference action track corresponding to the maximum intimacy degree in the m reference action tracks and the preset cell map.
6. The method of any one of claims 1-4, wherein the first object is a first person, the m other objects are m animals, and the processor recommends a target course of action for the first object based on the m reference trajectories of action and the first location, comprising:
the processor acquires a preset cell map; acquiring a preset user label of the first person;
and if the preset user label meets a preset condition, generating a target action line with the minimum intersection with the m reference action tracks according to the preset cell map.
7. An intelligent line recommendation apparatus comprising a processor, an artificial intelligence chip, a predictor, and a memory, wherein,
the processor is used for performing video analysis on the obtained shooting videos to obtain a plurality of video image sets, wherein the shooting videos are shooting videos of different areas of a cell in a first preset time period;
the artificial intelligence chip is used for sequentially operating the video images in the plurality of video image sets according to a preset artificial intelligence algorithm to obtain a first position where a first object is located currently in the cell and m other positions where m other objects are located, wherein m is a positive integer, each other object corresponds to one other position, and the first position and the m other positions are located in different areas in the cell;
the predictor is used for predicting m reference action tracks of the m other objects according to m other positions of the m other objects and a plurality of action tracks stored in the memory in advance;
the processor is further configured to recommend a target action line for the first object according to the m reference action tracks and the first position.
8. The apparatus of claim 7, wherein the artificial intelligence chip comprises a data converter, a data access circuit, a register circuit, and an arithmetic circuit, wherein in the aspect of obtaining the current first position of the first object in the cell by sequentially operating the video images in the plurality of video image sets by the artificial intelligence chip according to a preset artificial intelligence algorithm,
the data converter is used for converting a first video image in the plurality of video image sets into first input data and transmitting the first input data to the data access circuit;
the data access circuit is used for sending the first input data to the arithmetic circuit; the data access circuit reads an operation instruction from the register circuit and sends the operation instruction to the operation circuit;
the arithmetic circuit is used for carrying out pixel gradient calculation according to the arithmetic instruction and the first input data to obtain gradient amplitudes and gradient directions of all pixel points in the first video image; and counting the gradient amplitudes and gradient directions of all the pixel points to obtain a feature vector set of the first object in the first video image, and determining a first position where the first object is located currently according to the feature vector set.
9. An intelligent line recommendation apparatus comprising a processor, an artificial intelligence chip, a predictor and a memory for storing one or more programs configured for execution by the processor, artificial intelligence chip and predictor, the programs including instructions for performing the steps in the method of any one of claims 1-6.
10. A computer-readable storage medium, characterized in that a computer program for electronic data exchange is stored, wherein the computer program causes a computer to perform the method according to any one of claims 1-6.
CN201911320923.4A 2019-12-19 2019-12-19 Intelligent line recommendation method and related products Active CN111143703B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911320923.4A CN111143703B (en) 2019-12-19 2019-12-19 Intelligent line recommendation method and related products

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911320923.4A CN111143703B (en) 2019-12-19 2019-12-19 Intelligent line recommendation method and related products

Publications (2)

Publication Number Publication Date
CN111143703A true CN111143703A (en) 2020-05-12
CN111143703B CN111143703B (en) 2023-05-23

Family

ID=70519036

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911320923.4A Active CN111143703B (en) 2019-12-19 2019-12-19 Intelligent line recommendation method and related products

Country Status (1)

Country Link
CN (1) CN111143703B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107273510A (en) * 2017-06-20 2017-10-20 广东欧珀移动通信有限公司 Photo recommends method and Related product
WO2018192406A1 (en) * 2017-04-20 2018-10-25 腾讯科技（深圳）有限公司 Identity authentication method and apparatus, and storage medium
WO2018228168A1 (en) * 2017-06-14 2018-12-20 Oppo广东移动通信有限公司 Image processing method and related product

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018192406A1 (en) * 2017-04-20 2018-10-25 腾讯科技（深圳）有限公司 Identity authentication method and apparatus, and storage medium
WO2018228168A1 (en) * 2017-06-14 2018-12-20 Oppo广东移动通信有限公司 Image processing method and related product
CN107273510A (en) * 2017-06-20 2017-10-20 广东欧珀移动通信有限公司 Photo recommends method and Related product

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
许晓飞;米洁;陈雯柏;: "人工智能视域下协同过滤推荐系统的工程训练平台" *

Also Published As

Publication number Publication date
CN111143703B (en) 2023-05-23

Similar Documents

Publication Publication Date Title
EP3605394A1 (en) Method and apparatus for recognizing body movement
CN110443210B (en) Pedestrian tracking method and device and terminal
CN107808111B (en) Method and apparatus for pedestrian detection and attitude estimation
CN111930524B (en) Method and system for distributing computing resources
CN112380955B (en) Action recognition method and device
WO2016201683A1 (en) Cloud platform with multi camera synchronization
CN114679607B (en) Video frame rate control method and device, electronic equipment and storage medium
CN111652181A (en) Target tracking method and device and electronic equipment
CN114092678A (en) Image processing method, image processing device, electronic equipment and storage medium
CN111626251A (en) Video classification method, video classification device and electronic equipment
CN106303420A (en) A kind of monitoring method being applied to moving target and monitoring system
CN115103161B (en) Video propulsion-based patrol method, system, equipment and medium
CN113627334A (en) Object behavior identification method and device
CN109214326A (en) A kind of information processing method, device and system
CN111126159A (en) Method, apparatus, electronic device, and medium for tracking pedestrian in real time
CN113627421B (en) Image processing method, training method of model and related equipment
CN114639076A (en) Target object detection method, target object detection device, storage medium, and electronic device
CN110135517B (en) Method and device for obtaining vehicle similarity
CN114764902A (en) Behavior recognition method and device and storage medium
CN111143703A (en) Intelligent line recommendation method and related product
CN114449346B (en) Video processing method, device, equipment and storage medium
CN113468913B (en) Data processing method, motion recognition method, model training method, device and storage medium
CN113569771B (en) Video analysis method and device, electronic equipment and storage medium
CN111353470B (en) Image processing method and device, readable medium and electronic equipment
CN116580054A (en) Video data processing method, device, equipment and 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
GR01 Patent grant
GR01 Patent grant