CN110728244B

CN110728244B - Method and device for guiding acquisition of stocking material identity information

Info

Publication number: CN110728244B
Application number: CN201910985266.9A
Authority: CN
Inventors: 王萌
Original assignee: Ant Shengxin Shanghai Information Technology Co ltd
Current assignee: Ant Shengxin Shanghai Information Technology Co ltd
Priority date: 2019-10-16
Filing date: 2019-10-16
Publication date: 2022-06-14
Anticipated expiration: 2039-10-16
Also published as: CN110728244A

Abstract

The specification provides a method and a device for guiding acquisition of the identity information of an feeding material, wherein the method for guiding acquisition of the identity information of the feeding material comprises the following steps: acquiring identity characteristic information acquired by an acquisition terminal in various modes aiming at the feeding materials; extracting key features corresponding to the identity feature information in each mode and inputting the key features into a detection model, and performing qualification detection on the key features corresponding to the identity feature information in each mode to obtain a detection result output by the detection model and aiming at the key features corresponding to the identity feature information in each mode; if at least one key feature exists in the detection result, generating an acquisition guide instruction corresponding to the at least one key feature which is not qualified in detection under the condition that the at least one key feature is not qualified in detection; and sending a collection guide prompt for carrying out feature collection aiming at the at least one key feature which is unqualified in detection to the collection terminal by operating the collection guide instruction.

Description

Method and device for guiding acquisition of stocking material identity information

Technical Field

The specification relates to the technical field of computers, in particular to a guiding method for acquisition of feeding material identity information. The specification also relates to a guiding device for collecting the identity information of the feeding materials, a computing device and a computer readable storage medium.

Background

Along with the continuous improvement of living standard of people, working pressure and living pressure are also getting bigger and bigger, communication between people is also getting smaller and smaller gradually, in order to enrich the life of people and not bring too much burden to the life of people, more and more people like to raise pets, companion with pets can make the life of users more happy, and for some well-trained pets, some accidents occur to the old, for example, when sick, the pet can also play the role of warning, the pet is equivalent to one part of family to the raiser, therefore, a lot of industries for pets are also generated, for example, pet hospitals, bathing, pet insurance and the like.

In numerous pet industries, in order to manage pets conveniently, a pet file database is required to be established, information of each pet is stored, the pets are conveniently served better and more quickly, the satisfaction degree of a pet feeder for the services in the industry is improved, for example, the pet feeder purchases insurance for the pets, and in the process that the pets are required to be settled accidentally, the information of the pets can be quickly checked through the established pet file database, so that the quick and accurate settlement service for the pets is realized. In the process of collecting information of pets, guidance is usually performed by using a guide frame, which belongs to passive guidance and depends on the self-understanding ability of users, so that the amount of information conveyed is low and the guidance effect is poor.

Disclosure of Invention

In view of the above, the embodiments of the present specification provide a method for guiding acquisition of identity information of an animal feeding material. The specification simultaneously relates to a guiding device for collecting the identity information of the feeding materials, a computing device and a computer readable storage medium, which are used for solving the technical defects in the prior art.

According to a first aspect of embodiments of the specification, a method for guiding management-based management identity information acquisition is provided, which includes:

acquiring identity characteristic information acquired by an acquisition terminal in various modes aiming at the feeding material;

extracting key features corresponding to the identity feature information in each mode and inputting the key features into a detection model, and performing qualification detection on the key features corresponding to the identity feature information in each mode to obtain a detection result output by the detection model and aiming at the key features corresponding to the identity feature information in each mode;

if at least one key feature exists in the detection result, generating an acquisition guide instruction corresponding to the at least one key feature which is not qualified in detection under the condition that the at least one key feature is not qualified in detection;

and sending a collection guide prompt for carrying out feature collection aiming at the at least one key feature which is unqualified in detection to the collection terminal by operating the collection guide instruction.

Optionally, the extracting key features corresponding to the identity feature information in the various modalities and inputting the key features into a detection model, performing eligibility detection on the key features corresponding to the identity feature information in the various modalities, and obtaining a detection result output by the detection model and specific to the key features corresponding to the identity feature information in the various modalities includes:

extracting key features corresponding to the identity feature information in the various modes;

determining a characteristic numerical value of the key characteristic under the characteristic dimension of the corresponding mode according to the identity characteristic information in the various modes;

and inputting a multi-modal feature vector obtained by feature construction based on the feature numerical value into the detection model to detect the qualification of the key features, and obtaining the detection result output by the detection model.

Optionally, the generating of the acquisition guidance instruction corresponding to the at least one key feature that is not qualified for detection includes:

determining an adjusting mode corresponding to the at least one key feature which is not qualified in detection, and generating the acquisition guide instruction corresponding to the at least one key feature which is not qualified in detection according to the adjusting mode.

Optionally, the determining an adjustment manner corresponding to the at least one key feature that is not qualified for detection includes:

determining a feature sample corresponding to the at least one key feature which is not qualified to be detected according to a corresponding relation between the pre-established features and the feature sample;

and comparing the at least one key feature which is not qualified in detection with the feature sample, and determining the adjustment mode corresponding to the at least one key feature which is not qualified in detection according to the comparison result.

Optionally, the acquiring and collecting identity characteristic information collected by the terminal in various modalities for the feeder includes:

acquiring video streams, audio streams and/or texts acquired by the acquisition terminal in various modalities aiming at the feeding materials;

extracting a frame of corresponding image from the video stream to determine the image characteristic information, extracting audio information from the audio stream to determine the audio characteristic information, and extracting keywords from the text to serve as text characteristic information;

and taking the image feature information, the sound feature information and/or the text feature information as identity feature information in the various modalities.

Optionally, if at least one key feature exists in the detection result and the detection is not qualified, generating an acquisition guidance instruction corresponding to the at least one key feature that is not qualified, including:

if the detection result has the condition that the feature size, the feature brightness, the feature definition, the feature quantity, the feature angle and/or the feature position of the image feature information are/is unqualified, generating a distance acquisition guide instruction corresponding to the feature size of the image feature information which is unqualified in detection, generating an exposure acquisition guide instruction corresponding to the feature brightness of the image feature information which is unqualified in detection, generating a definition acquisition guide instruction corresponding to the feature definition of the image feature information which is unqualified in detection, generating a quantity acquisition guide instruction corresponding to the feature quantity of the image feature information which is unqualified in detection, generating an angle acquisition guide instruction corresponding to the feature angle of the image feature information which is unqualified in detection, and/or generating a position acquisition guide instruction corresponding to the feature position of the image feature information which is unqualified in detection, as the acquisition guide instruction;

correspondingly, executing the acquisition guidance prompting step of carrying out feature acquisition on the at least one key feature which is not qualified in detection to the acquisition terminal by operating the acquisition guidance instruction;

the step of sending a collection guidance prompt for performing feature collection on the at least one key feature which is not qualified in detection to the collection terminal by operating the collection guidance instruction comprises the following steps:

and sending an arrow guide prompt aiming at the image characteristic information to the acquisition terminal by operating the distance acquisition guide instruction, the exposure acquisition guide instruction, the definition acquisition guide instruction, the quantity acquisition guide instruction, the angle acquisition guide instruction and/or the position acquisition guide instruction to serve as the acquisition guide prompt.

if the tone size, the sound definition and/or the sound duration of the sound characteristic information exist in the detection result under the condition that the detection is not qualified, generating a tone acquisition guide instruction corresponding to the tone size of the sound characteristic information which is not qualified, generating a change environment acquisition guide instruction corresponding to the sound definition of the sound characteristic information which is not qualified, and/or generating a time acquisition guide instruction corresponding to the sound duration of the sound characteristic information which is not qualified, and using the time acquisition guide instruction as the acquisition guide instruction;

and sending a voice guide prompt aiming at the characteristic collection of the sound characteristic information to the collection terminal by operating the tone collection guide instruction, the change environment collection guide instruction and/or the time collection guide instruction to serve as the collection guide prompt.

if the description content and/or the attribute information of the text feature information exist in the detection result, generating a description acquisition guide instruction corresponding to the description content of the text feature information which is not qualified for detection, and/or generating an input acquisition guide instruction corresponding to the attribute information of the text feature information which is not qualified for detection;

and sending a character guide prompt for carrying out feature acquisition on the text feature information to the acquisition terminal by operating the description acquisition guide instruction and/or inputting the acquisition guide instruction, wherein the character guide prompt is used as the acquisition guide prompt.

Optionally, after the step of extracting the key features corresponding to the identity feature information in the various modalities and inputting the key features into the detection model, performing eligibility detection on the key features corresponding to the identity feature information in the various modalities to obtain the detection result output by the detection model for the key features corresponding to the identity feature information in the various modalities is executed, the method further includes:

if the detection result is qualified, sending a qualified acquisition prompt to the acquisition terminal;

constructing a corresponding relation between the unique identifier of the livestock and the identity characteristic information in various modes;

and storing the identity characteristic information of the feeder in the various modes into a preset database based on the corresponding relation between the unique identifier and the identity characteristic information in the various modes.

Optionally, after the step of storing the identity feature information of the animal in the various modalities into a preset database based on the corresponding relationship between the unique identifier and the identity feature information in the various modalities is executed, the method further includes:

under the condition that a service processing instruction is received, acquiring current identity characteristic information acquired by a current acquisition terminal in various modes according to the current feeding material and a unique identifier of the current feeding material;

under the condition that the unique identifier of the current feeder is matched with the unique identifier of the feeder, extracting identity characteristic information of the feeder in the various modes from the database;

calculating the degree of association between the current identity characteristic information and the identity characteristic information;

and determining the current feeder to be the feeder under the condition that the correlation degree is greater than or equal to a preset correlation degree threshold value, and performing service treatment on the current feeder.

Optionally, after the step of sending an acquisition guidance prompt for performing feature acquisition on the at least one key feature that is not qualified in detection to the acquisition terminal by operating the acquisition guidance instruction is executed, the method further includes:

determining that identity feature information collected in the various modalities for the animal feeding material is qualified in detection when receiving secondary key features collected according to the collection guidance prompt for the at least one key feature that is unqualified in detection;

and sending a qualified acquisition prompt to the acquisition terminal according to the qualified detection result.

According to a second aspect of embodiments herein, there is provided a guide device for acquisition of feeding identity information, comprising:

the acquisition characteristic information module is configured to acquire identity characteristic information acquired by the acquisition terminal in various modes aiming at the feeder;

the qualification detection module is configured to extract key features corresponding to the identity feature information in the various modalities, input the key features into a detection model, perform qualification detection on the key features corresponding to the identity feature information in the various modalities, and obtain a detection result output by the detection model and aiming at the key features corresponding to the identity feature information in the various modalities;

the instruction generating module is configured to generate an acquisition guide instruction corresponding to at least one key feature which is unqualified in detection if at least one key feature exists in the detection result and is unqualified in detection;

and the guiding and prompting module is configured to send a collecting and guiding prompt for carrying out feature collection on the at least one key feature which is not qualified in detection to the collecting terminal by operating the collecting and guiding instruction.

According to a third aspect of embodiments herein, there is provided a computing device comprising:

a memory and a processor;

the memory to store computer-executable instructions, the processor to execute the computer-executable instructions:

acquiring identity characteristic information acquired by an acquisition terminal in various modes aiming at the feeding materials;

According to a fourth aspect of embodiments herein, there is provided a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement any one of the steps of the method for directing acquisition of owner identity information.

The embodiment of the specification realizes that in the process of acquiring the identity characteristic information of the feeder, the identity characteristic information of the feeder in various modes can be acquired firstly, the detection results of the key characteristics of the feeder in various modes are acquired through the detection model, if at least one key characteristic is unqualified in detection, an acquisition guide instruction can be generated for at least one key characteristic which is unqualified in detection, and finally an acquisition guide prompt aiming at least one key characteristic is sent to the acquisition terminal by operating the acquisition guide instruction, so that when the identity characteristic information in different modes is unqualified, the acquisition guide prompt can be correctly generated for the key characteristics of the unqualified identity characteristic information and sent to the acquisition terminal, so that a user can acquire the qualified identity characteristic information of the feeder according to a correct guide mode, the experience effect of the user is improved, and the acquisition efficiency of the identity characteristic information of the collected livestock is further improved.

Drawings

FIG. 1 is a flow diagram of a method for directing acquisition of identity information of an animal feeding material according to an embodiment of the present disclosure;

fig. 2 is a process flow diagram of a guiding method applied to acquisition of feeding identity information for pet file establishment according to an embodiment of the present disclosure;

FIG. 3 is a schematic structural diagram of a guiding device for acquisition of the identity information of the feeding material provided by an embodiment of the present specification;

fig. 4 is a block diagram of a computing device according to an embodiment of the present disclosure.

Detailed Description

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present description. This description may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein, as those skilled in the art will be able to make and use the present disclosure without departing from the spirit and scope of the present disclosure.

The terminology used in the description of the one or more embodiments is for the purpose of describing the particular embodiments only and is not intended to be limiting of the description of the one or more embodiments. As used in one or more embodiments of the present specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present specification refers to and encompasses any and all possible combinations of one or more of the associated listed items.

It will be understood that, although the terms first, second, etc. may be used herein in one or more embodiments to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first can also be referred to as a second and, similarly, a second can also be referred to as a first without departing from the scope of one or more embodiments of the present description. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.

First, the noun terms to which one or more embodiments of the present specification relate are explained.

Keeping materials: refers to animals or plants raised or domesticated by users. For example, raised pets, grown flowers, are among the owners' owners.

Mode: each source or form of information may be referred to as a modality, e.g., auditory, visual, olfactory, are all of a modality; the media of information, sound, image and text also belong to a mode.

In the present specification, a method for guiding acquisition of identity information of an animal is provided, and the present specification simultaneously relates to a guiding device for acquisition of identity information of an animal, a computing device, and a computer-readable storage medium, which are described in detail in the following examples one by one.

Fig. 1 shows a flowchart of a guiding method for acquisition of the identity information of the feeding material, which includes the following steps:

step 102: and acquiring identity characteristic information acquired by the acquisition terminal in various modes aiming at the feeding materials.

In an embodiment of the present specification, the identity characteristic information specifically refers to characteristic information of the material in various modalities, for example, image characteristic information about the material in an image modality, sound characteristic information about the material in a sound modality, and the like, the acquisition terminal specifically refers to a terminal device for acquiring information with respect to the material, the acquisition terminal may be a smart phone, a computer, and the like, and the acquisition terminal needs to be configured with a sound sensor and an image sensor, so as to be capable of acquiring image characteristics and sound characteristics of the material.

In practical application, in the process that a user purchases insurance for an feeder or registers information, the information of the feeder needs to be collected so as to ensure that the information about the feeder uploaded by the user is real, and the information about the feeder uploaded by the user needs to be subjected to qualification and authenticity detection to perform subsequent service processing; in the process that a user collects identity characteristic information of the feeding material in various modes through the collecting terminal, sound, images and texts of feeding can be collected simultaneously; the method comprises the following steps of (1) under the condition that an animal is an feeder, specifically speaking sound of the feeder, specifically speaking an image or a video shot aiming at the feeder, and specifically speaking a text which is the content of character description of a user aiming at the feeder; and in the case that the material is a plant, only images and texts can be acquired without acquiring sound.

Based on this, in the process of detecting the eligibility of the identity characteristic information of the feeding material, it is required to determine whether the identity characteristic information uploaded by the user for the feeding material can be used for subsequent business processing, for example, in the process of establishing the archive for the fed pet dog, the user needs to photograph the pet dog for establishing the archive, and the user does not necessarily know how to correctly photograph the pet dog in the process of establishing the archive for the pet dog for the first time, at this time, the user needs to acquire the image of the pet dog for guidance, so that the user can acquire the qualified image of the pet dog for establishing the archive for the pet dog in a correct guidance mode.

In the guiding manner for acquiring the identity information of the feeder provided by this embodiment, in order to correctly guide a user to acquire the identity characteristic information of the feeder and acquire the identity characteristic information in different modalities, after the identity characteristic information of the feeder in various modalities is acquired, the detection results of the key characteristics of the feeder in various modalities are obtained through the detection model, if at least one key characteristic is unqualified in detection, an acquisition guiding instruction may be generated for the at least one key characteristic that is unqualified in detection, and finally an acquisition guiding prompt for the at least one key characteristic is sent to the acquisition terminal by operating the acquisition guiding instruction, so that the acquisition guiding prompt may be correctly generated for the key characteristics of the unqualified identity characteristic information and sent to the acquisition terminal when the identity characteristic information in different modalities is unqualified, the user can acquire the qualified identity characteristic information of the feeding material according to a correct guiding mode, the experience effect of the user is improved, and the acquisition efficiency of the identity characteristic information of the feeding material is further improved.

In specific implementation, in the process of acquiring the identity characteristic information of the animal in various modalities through the acquisition terminal, the acquisition of the identity characteristic information in different modalities is realized, so that the acquisition terminal can be performed in a video acquisition mode in the acquisition process, and a sound acquisition mode and/or a text acquisition mode is performed, so that the acquired identity characteristic information also exists in the form of a video stream, an audio stream and/or a text, and in one or more implementation modes of this embodiment, the process of specifically acquiring the identity characteristic information in various modalities is as follows:

Specifically, a video stream, an audio stream and/or a text acquired by an acquisition terminal in various modalities aiming at the material, at this time, image feature information about the material needs to be extracted from the video stream, sound feature information about the material needs to be extracted from the audio stream, and/or text feature information about the material needs to be extracted from the text; the image feature information specifically refers to the fact that an image contains the whole form of the material in the image, and a video stream is acquired by an acquisition terminal, so the image feature information can be used as the image feature information by extracting one image from the video stream, the sound feature information specifically refers to the fact that the audio stream contains the call sound of the material, and/or the text feature information specifically refers to the description information of the material, and the image feature information, the sound feature information and/or the text feature information can be used as the identity feature information in various modes.

In practical application, in the process of acquiring identity characteristic information of the feeder in various modes, different identity characteristic information can be selectively acquired according to the type of the feeder, for example, when the feeder is a pet dog, a video of the pet dog can be shot by a mobile phone, one frame of image in the video is extracted as image characteristic information of the pet dog, and sound in the video (specifically, the sound of the pet dog) is extracted as sound characteristic information of the pet dog; when the feeding material is a plant, a video about the plant can be shot through a mobile phone, one frame of image in the video is extracted to serve as image feature information of the plant, sound in the video (specifically, the content of the user describing the plant) is extracted, and the sound is converted into text to serve as text feature information of the plant, so that the text feature information is used in the subsequent qualification detection process of identity feature information.

In the embodiment, in the process of acquiring the identity information of the feeding materials, the identity characteristic information in different modes can be acquired aiming at different types of feeding materials, so that the subsequent qualification detection of the identity characteristic information is realized, a user can acquire the identity characteristic information aiming at different feeding material types more conveniently, and the mode of acquiring the identity characteristic information by the user is further enriched.

Step 104: extracting key features corresponding to the identity feature information in the various modes, inputting the key features into a detection model, performing qualification detection on the key features corresponding to the identity feature information in the various modes, and obtaining a detection result output by the detection model and aiming at the key features corresponding to the identity feature information in the various modes.

Specifically, on the basis of obtaining identity feature information of the feeding material in various modes, further, by extracting key features of the identity feature information in the various modes and inputting the key features into the detection model, qualification detection is performed on the key features corresponding to the identity feature information in the various modes, that is, the qualification detection is performed on the key features corresponding to the identity feature information of the collected feeding material in the various modes, and a detection result output by the detection model and aiming at the key features corresponding to the identity feature information in the various modes is obtained.

The detection result may be whether the key feature of the identity feature information in various modalities is qualified, for example, the detection model performs eligibility detection on the sound volume of the pet dog in the sound feature information of the pet dog, so as to obtain a sound qualified detection result of the pet dog output by the detection model, or an unqualified detection result of the sound volume of the pet dog.

In practical application, the detection model can simultaneously perform qualification detection on the key features of the identity feature information in various modalities, for example, the input of the detection model is the sound of a pet dog and a photo of the pet dog, the detection model performs qualification detection on the sound of the pet dog and the photo of the pet dog, and the output can be the qualified detection result of the sound of the pet dog and the qualified detection result of the photo of the pet dog, or the output can be the unqualified detection result of the sound of the pet dog and the qualified detection result of the photo of the pet dog.

Based on the above, the detection model may be a multi-classification model, which classifies the eligibility of the key features of the identity feature information in the input various modalities, and outputs the qualified or unqualified detection result of the key features of the identity feature information in the various modalities.

In specific implementation, the detection model is trained in the following way:

acquiring identity characteristic information of a large number of various livestock in various modes, extracting key characteristics in the identity characteristic information, and performing qualification detection on the key characteristics of the identity characteristic information in the various modes to obtain detection results of the key characteristics of the identity characteristic information in the various modes; inputting the key features of the identity feature information of the various materials in various modes and the corresponding detection results thereof as training samples into a detection model, and determining the incidence relation between the key features of the identity feature information of the various materials in various modes and the corresponding detection results thereof, namely completing the training of the detection model; wherein the detection result in the training sample comprises a detection qualified result and a detection unqualified result.

In a specific implementation, when the key features of the identity feature information in the various modalities are input to the detection model, vectorization processing needs to be performed on the input of the detection model to enable the key features of the identity feature information in the various modalities to be combined together as the input of the detection model, in one or more implementations of this embodiment, the eligibility detection process of the detection model for the key features of the identity feature information in the various modalities is as follows:

Specifically, the key features corresponding to the identity feature information in the various modes can be features of an feeder body shape, exposure, size of a feeder in an image and the like in the image feature information, or features of the feeder sound size, sound length, sound definition and the like in the sound feature information, or features of a feeder description information text, a feeder attribute information text and the like in the text feature information;

based on this, by extracting the key features corresponding to the identity feature information in the various modalities, further determining the feature values of the key features under the feature dimensions of the corresponding modalities according to the identity feature information in the various modalities, specifically, converting the key features into vectors in a vectorization processing manner and embodying the vectors in the feature values, further constructing the vectors based on the feature values of the key features corresponding to the identity feature information in the various modalities to obtain multi-modal feature vectors, wherein the multi-modal feature vectors are obtained by fusing the feature values of the key features corresponding to the identity feature information in the various modalities, and finally performing qualification detection on the key features corresponding to the identity feature information in the various modalities by inputting the multi-modal feature vectors into the detection model, and obtaining the detection result of the key features corresponding to the identity feature information in the various modes output by the detection model.

For example, when a user builds a file for a pet dog, the user needs to shoot the pet dog, collect the type of the pet dog, the hair color of the pet dog and the call of the pet dog, the user takes a video about the pet dog through a mobile phone, extract image feature information to determine the height feature and the hair color feature of the pet dog by acquiring a frame of image in the video as the image feature information for the pet dog, extract sound feature information to determine the call feature of the pet dog by acquiring the sound in the video as the sound feature information of the pet dog, determine a first feature value of the qualified hair color feature of the height feature in the feature dimension of a corresponding mode, determine a second feature value of the call feature in the feature dimension of the corresponding mode, obtain a multi-mode vector by performing feature construction on the first feature value and the second feature value, input the multi-mode vector to a detection model to perform qualification detection on the key feature of the pet dog, and obtaining the detection results of the height characteristic and the hair color characteristic and the detection result of the cry characteristic, and determining that the information collected by the user aiming at the pet dog can be collected and guided aiming at the key characteristic which is not qualified in the detection under the condition that the detection is not qualified according to the detection results.

In the process of detecting the key features corresponding to the identity feature information of the animal feeding material in various modes through the detection model, under the condition that the feature values of the key features corresponding to the identity feature information in various modes are determined, feature construction is carried out on the feature values to obtain the multi-mode feature vector which is used as the input of the detection model, so that the qualification detection of the key features corresponding to the identity feature information in various modes through the detection model is realized, and the qualification detection efficiency of the key features corresponding to the identity feature information in various modes is further improved.

Further, when the detection results output by the detection model and aiming at the key features corresponding to the identity feature information in the various modalities are all detected to be qualified, it is indicated that the identity feature information of the feeder in the various modalities, which is acquired by the acquisition terminal, is qualified and can be used for subsequent service processing, at this time, an acquisition qualification prompt may be sent to notify a user holding the acquisition terminal that subsequent operations may be performed, in one or more embodiments of this embodiment, when it is determined that the detection results are all detected to be qualified, the identity feature information of the feeder in the various modalities needs to be stored, and a specific implementation manner is as follows:

Specifically, if the detection result is that the detection is qualified, it is indicated that the identity characteristic information of the feeder in each mode, which is acquired by the acquisition terminal, can be used for subsequent service processing, at this time, an acquisition qualified prompt can be sent to the acquisition terminal, and a corresponding relationship between a unique identifier of the feeder and the identity characteristic information in each mode is constructed, where the unique identifier of the feeder specifically refers to an account constructed on a platform for performing service processing on the feeder, the account is used as the unique identifier of the feeder, and the identity characteristic information of the feeder in each mode is stored in a preset database based on the corresponding relationship between the unique identifier and the identity characteristic information in each mode.

In practical application, whether a user purchases and secures the feeder or establishes an archive of the feeder, identity characteristic information of the feeder can be extracted from the database according to specific service processing, and the extraction process needs to be realized according to the unique identifier of the feeder.

Further, on the basis of completing the storage of the identity characteristic information of the material in various modes, if the material needs to be subjected to service processing subsequently, information verification can be performed by extracting the identity characteristic information of the material from the database, and whether to perform service processing or not is determined according to a verification result, so as to improve the safety of the service processing, in one or more embodiments of this embodiment, a specific verification process is as follows:

Specifically, the service processing may be that after the user purchases and insures the feeder, the feeder needs to be subjected to identity verification when the feeder is accidental or ill, and when the identity verification passes, it can be determined that the feeder that is ill or has accidental is the feeder that purchased and insures, and then the feeder can be paid.

Based on this, under the condition that the service processing instruction is received, it is indicated that service processing needs to be performed on the feeder, at this time, identity verification needs to be performed on the current feeder, under the condition that the unique identifier of the current feeder is matched with the unique identifier of the feeder by acquiring current identity feature information, acquired by a current acquisition terminal, of the current feeder in various modes and the unique identifier of the current feeder, it is indicated that service processing needs to be performed on the feeder, at this time, it is required to detect whether the current feeder is the feeder when information is recorded, the identity feature information of the feeder in various modes is extracted from the database through the unique identifier of the current feeder, and the correlation degree between the identity feature information of the current feeder and the identity feature information of the feeder is calculated;

under the condition that the correlation degree is greater than or equal to a preset correlation degree threshold value, the current feeding material is the feeding material when the information is input, and then service processing is continuously performed on the current feeding material; and under the condition that the relevance degree is smaller than the preset relevance degree threshold value, the current feeder is not the feeder during information entry, and no treatment is needed.

For example, after the user buys a pet insurance for the pet dog a at 1 month and 1 day, after the pet insurance is successfully bought, the identity characteristic information about the pet dog a is stored in a database based on the pet account a, the pet dog is found to have dental diseases at 10 months and 1 day of the same year, the user needs to provide a platform for pet insurance for settlement, at this time, in order to determine the behavior of preventing the user from cheating, the insurance platform needs to verify the pet dog B who is out of insurance, acquire the identity characteristic information uploaded by the user for the pet dog B, acquire the pet account B of the pet dog B, extract the identity characteristic information about the pet dog a from the database when the pet account B and the pet account a are the same account, calculate the association degree between the identity characteristic information about the pet dog B and the identity characteristic information about the pet dog a at this time to be 95%, and determine that the association degree is 95% greater than the association degree threshold value 80%, at this point, it can be determined that pet dog B is pet dog A when pet insurance is purchased, and a subsequent claim settlement process can be performed on the user based on dental disease of pet dog A.

The identity characteristic information of the feeding materials in various modes is stored in the database, the association relationship between the unique identification of the feeding materials and the identity characteristic information is established, the association degree can be calculated based on the currently acquired identity characteristic information of the feeding materials in various modes and the identity characteristic information extracted from the database under the condition that a service processing instruction is received, and the subsequent service processing can be carried out under the condition that the association degree is greater than or equal to a preset association degree threshold value, so that the condition that fraud is carried out on the feeding materials can be avoided, and the safety of the service processing process is further improved.

Step 106: and if at least one key feature exists in the detection result, generating an acquisition guide instruction corresponding to the at least one key feature which is not qualified in detection.

Specifically, on the basis of the detection result obtained by the detection model and output for the key features corresponding to the identity feature information in the various modalities, further, when it is detected that at least one key feature exists in the detection result that the detection is not qualified, it indicates that at least one key feature that is not collected or that the collected key feature is not qualified exists in the process of collecting the livestock material by the collection terminal, for example, in the process of collecting the identity feature information of the pet dog, the sound size of the pet dog is determined by the detection model to be unqualified, or the head size of the pet dog in the image is determined to be unqualified, etc.; based on this, the acquisition guidance instruction may be generated according to the at least one key feature that is not qualified in detection, where the acquisition guidance instruction is specifically an instruction that is issued to the acquisition terminal and used for guiding the acquisition of the at least one key feature correctly in an operating manner at the acquisition terminal.

Further, in the process of generating the acquisition guidance instruction corresponding to the at least one unqualified detected key feature, in order to facilitate user operation and provide richer guidance prompts for the user, in one or more embodiments of this embodiment, different adjustment modes may be determined according to different key features, and a specific implementation mode is as follows:

Specifically, the adjusting manner is a manner of adjusting the at least one key feature that is not qualified for detection to be a manner of being qualified, and when the adjusting manner corresponding to the at least one key feature that is not qualified for detection is determined, the acquisition guidance instruction corresponding to the at least one key feature that is not qualified for detection may be generated according to the adjusting manner.

Furthermore, in the process of determining the adjustment manner according to the at least one key feature that is not qualified for detection, in order to more accurately determine the adjustment manner corresponding to the at least one key feature that is not qualified for detection, a corresponding relationship between a feature and a feature sample may be pre-established, and a feature sample corresponding to the at least one key feature that is not qualified for detection may be determined by querying the pre-established corresponding relationship between the feature and the feature sample, and in one or more embodiments of this embodiment, the specific process of determining the adjustment manner according to the at least one key feature that is not qualified for detection is as follows:

Specifically, under the condition that the at least one key feature that is not qualified for detection is determined, a feature sample corresponding to the at least one key feature that is not qualified for detection is determined by querying a correspondence between a feature established in advance and the feature sample, and then the feature sample is compared with the at least one key feature that is not qualified for detection, so as to determine a defect existing in the at least one key feature that is not qualified for detection.

For example, it is determined that at least one key feature that is not qualified in detection is that the pet dog call sound volume is unqualified, at this time, it is determined that the feature sample that is corresponding to the unqualified pet dog call sound volume is the standard pet dog call sound volume through a pre-established corresponding relationship between the feature and the feature sample, it is determined that the pet dog call sound volume is too small by comparing the pet dog call sound volume with the standard pet dog call sound volume, at this time, it can be determined that the adjustment mode for the unqualified pet dog call sound volume is to increase the pet dog call sound volume, and then the acquisition guide instruction corresponding to the unqualified pet dog call sound volume is generated based on the adjustment mode to increase the pet dog call sound volume.

In the process of generating the acquisition guide instruction corresponding to the at least one key feature which is not qualified in detection, in order to generate the acquisition guide instruction more conveniently and more conveniently, the adjustment mode of the at least one key feature which is not qualified in detection can be determined by inquiring the corresponding relation between the pre-established feature and the feature sample, and then the acquisition guide instruction of the at least one key feature which is not qualified in detection is generated according to the adjustment mode, so that different acquisition guide instructions can be determined according to different key features which are not qualified in detection, and the modes of guiding and prompting the user are further enriched.

Step 108: and sending a collection guide prompt for carrying out feature collection on the at least one key feature which is unqualified in detection to the collection terminal by operating the collection guide instruction.

Specifically, on the basis of generating an acquisition guidance instruction for the at least one key feature that is not qualified for detection, further, an acquisition guidance prompt for performing feature acquisition for the at least one key feature that is not qualified for detection may be sent to the acquisition terminal by operating the acquisition guidance instruction, where the acquisition guidance prompt specifically indicates how to correctly acquire a prompt message of the at least one key feature to a user holding the acquisition terminal through the acquisition terminal. And different unqualified key features correspond to different acquisition guide instructions, so that different unqualified key features correspond to different acquisition guide prompts.

In practical application, the collection guidance prompt may be a visual prompt, for example, a guidance prompt is performed in an image manner such as a color, a shape, an arrow mark, or a voice prompt, for example, a guidance prompt is performed in a voice broadcast manner, different guidance prompts may be set in different application scenes, and the description is not limited herein.

In specific implementation, under the condition that different acquisition guide instructions exist in different unqualified key features, different acquisition guide prompts also exist in the unqualified key features, and the different acquisition guide prompts can guide and remind a user more conveniently and more conveniently, so that a more personalized guidance prompt mode is established; based on the above, different acquisition guidance prompts are sent to the acquisition terminal according to different unqualified key characteristics, which are described by the following three conditions:

(1) if the detection result has the condition that the feature size, the feature brightness, the feature definition, the feature quantity, the feature angle and/or the feature position of the image feature information are/is unqualified, generating a distance acquisition guide instruction corresponding to the feature size of the image feature information which is unqualified in detection, generating an exposure acquisition guide instruction corresponding to the feature brightness of the image feature information which is unqualified in detection, generating a definition acquisition guide instruction corresponding to the feature definition of the image feature information which is unqualified in detection, generating a quantity acquisition guide instruction corresponding to the feature quantity of the image feature information which is unqualified in detection, generating an angle acquisition guide instruction corresponding to the feature angle of the image feature information which is unqualified in detection, and/or generating a position acquisition guide instruction corresponding to the feature position of the image feature information which is unqualified in detection, as the acquisition guide instruction; correspondingly, the step 108 is executed, where the step 108 specifically refers to sending an acquisition guidance prompt for performing feature acquisition on the at least one key feature that is not qualified for detection to the acquisition terminal by operating the acquisition guidance instruction, that is, sending an arrow guidance prompt for performing feature acquisition on the image feature information to the acquisition terminal by operating the distance acquisition guidance instruction, the exposure acquisition guidance instruction, the definition acquisition guidance instruction, the number acquisition guidance instruction, the angle acquisition guidance instruction, and/or the position acquisition guidance instruction, and taking the arrow guidance prompt as the acquisition guidance prompt.

The feature size specifically refers to the shape size of an feeder in the image, the feature brightness specifically refers to the exposure of the image with the feeder, the feature definition specifically refers to the definition of the feeder in the image with the feeder, the feature quantity specifically refers to the quantity of the feeder in the image, the feature angle specifically refers to the angle at which the feeder is shot in the image, and the feature position specifically refers to the geographical position at which the feeder is shot;

based on this, the distance acquisition guiding instruction corresponding to the characteristic size specifically refers to an instruction for adjusting distance in the process of acquiring image characteristic information of the feeding object through an acquisition terminal, the exposure acquisition guiding instruction corresponding to the characteristic brightness specifically refers to an instruction for adjusting exposure in the process of acquiring the image characteristic information of the feeding object by the acquisition terminal, the definition acquisition guiding instruction corresponding to the characteristic definition specifically refers to an instruction for adjusting definition in the process of acquiring the image characteristic information of the feeding object by the acquisition terminal, the number acquisition guiding instruction corresponding to the characteristic number specifically refers to an instruction for adjusting the number of the feeding objects in the process of acquiring the image characteristic information of the feeding object by the acquisition terminal, and the angle acquisition guiding instruction corresponding to the characteristic angle specifically refers to an instruction for adjusting the shooting angle of the feeding object in the process of acquiring the image characteristic information of the feeding object by the acquisition terminal The position acquisition guiding instruction corresponding to the characteristic position is specifically an instruction for adjusting the geographical position of the acquisition terminal in the process of acquiring the image characteristic information of the feeder.

Specifically, when it is determined that the key feature corresponding to the image feature information is not qualified through the detection result output by the detection model, it is indicated that the feature size, the feature brightness, the feature definition, the feature quantity, the feature angle and/or the feature position of the image feature information may exist in the detection result, at this time, a distance acquisition guide instruction corresponding to the feature size of the image feature information that is not qualified is generated, an exposure acquisition guide instruction corresponding to the feature brightness of the image feature information that is not qualified is generated, a definition acquisition guide instruction corresponding to the feature definition of the image feature information that is not qualified is generated, a quantity acquisition guide instruction corresponding to the feature quantity of the image feature information that is not qualified is generated, and an angle acquisition guide instruction corresponding to the feature angle of the image feature information that is not qualified is generated, and/or generating a position acquisition guide instruction corresponding to the feature position of the image feature information which is not qualified in detection;

based on the above, an arrow guidance prompt for performing feature acquisition on the feature size of the image feature information is sent to the acquisition terminal by operating the distance acquisition guidance instruction, an arrow guidance prompt for performing feature acquisition on the feature brightness of the image feature information is sent to the acquisition terminal by operating the exposure acquisition guidance instruction, an arrow guidance prompt for performing feature acquisition on the feature brightness of the image feature information is sent to the acquisition terminal by operating the definition acquisition guidance instruction, an arrow guidance prompt for the feature quantity of the image feature information is sent to the acquisition terminal by operating the quantity acquisition guidance instruction, an arrow guidance prompt for the feature angle of the image feature information is sent to the acquisition terminal by operating the angle acquisition guidance instruction, and/or an arrow guidance prompt for the feature position of the image feature information is sent to the acquisition terminal by operating the position acquisition guidance instruction Showing, as the acquisition guidance prompt; the arrow guidance prompt specifically refers to a guidance prompt sent to a user holding the acquisition terminal in a manner of displaying an arrow in the acquisition terminal.

In practical application, the arrow guide prompt corresponding to the distance acquisition guide instruction may be a guide prompt corresponding to a prompt for drawing the distance between the acquisition terminal and the livestock close or far by displaying an inward-pointing arrow perpendicular to a screen or an outward-pointing arrow perpendicular to the screen on the screen of the acquisition terminal; the arrow guide prompt corresponding to the exposure collection guide instruction can be a guide prompt corresponding to an upward arrow or a downward arrow displayed in a screen of the collection terminal and used for reminding the exposure of the collection terminal to be adjusted to be higher or lower; the arrow guide prompt corresponding to the definition acquisition guide instruction can be a guide prompt corresponding to the adjustment of the focal length of the acquisition terminal, wherein the arrow guide prompt corresponding to the definition acquisition guide instruction is a leftward arrow or a rightward arrow displayed on a screen of the acquisition terminal;

the arrow guiding prompt corresponding to the quantity acquisition guiding prompt may be a guiding prompt for displaying a plurality of arrows in the acquisition terminal, one arrow corresponds to the number of the feeding objects, the guiding prompt for reminding the acquisition terminal of adjusting the number of the feeding objects in the process of acquiring the feeding objects is used for displaying the arc-shaped arrow in the acquisition terminal by displaying the number of the arrows, a numerical value for adjusting the shooting angle again is marked above or below the arrow for reminding the acquisition terminal of adjusting the shooting angle in the process of acquiring the image of the feeding objects, the arrow guiding prompt corresponding to the position acquisition guiding prompt may be a guiding prompt for displaying a current city in the acquisition terminal, and the current geographic position of the acquisition terminal is shown by enabling the arrow to be perpendicular to a certain position in the map, a guiding prompt for reminding the acquisition terminal to be changed to a position corresponding to the original geographic position (the original geographic position specifically refers to the geographic position where the feeding material is located when the feeding material is uploaded for the first time);

when the position acquisition guide prompt is mostly used for position verification in the subsequent service processing process, the position acquisition guide prompt is sent to the acquisition terminal under the condition that the current position of the acquisition terminal is not matched with the original position, and the characteristic acquisition of the feeding materials can be carried out at the original position by a user holding the acquisition terminal.

In addition, the acquisition guidance prompts corresponding to different acquisition guidance instructions can be in other forms, for example, the acquisition guidance prompt corresponding to the exposure acquisition guidance instruction can also be that a bulb is displayed in a screen of the acquisition terminal to remind the acquisition terminal of increasing or decreasing the exposure; therefore, the acquisition guidance prompt can be set according to an actual application scene, and the description is not limited herein.

For example, in the process that a user purchases an insurance for a pet dog through a pet insurance platform, image feature information of the pet dog needs to be collected, the user uploads the image feature information of the pet dog to the pet insurance platform in a short video shooting mode, the pet insurance platform detects the qualification of the image feature information of the pet dog, the obtained detection result is that the feature definition of the image feature information is unqualified, a definition collection guide instruction corresponding to the feature definition is generated at the moment, an arrow guide prompt for feature collection aiming at the feature definition is sent to a mobile phone of the user through the running definition collection guide instruction, the arrow guide prompt is displayed in a mode that the arrow points to the left on the mobile phone of the user, and is used for reminding the user to collect the image feature information of the pet dog after adjusting the focus of the mobile phone.

(2) If the tone size, the sound definition and/or the sound duration of the sound feature information exist in the detection result and are/is not qualified in detection, generating a tone acquisition guide instruction corresponding to the tone size of the sound feature information which is not qualified in detection, generating an environment change acquisition guide instruction corresponding to the sound definition of the sound feature information which is not qualified in detection, and/or generating a time acquisition guide instruction corresponding to the sound duration of the sound feature information which is not qualified in detection as the acquisition guide instruction; correspondingly, the step 108 is executed, where the step 108 specifically refers to sending an acquisition guidance prompt for performing feature acquisition on the at least one key feature that is not qualified for detection to the acquisition terminal by operating the acquisition guidance instruction, that is, sending a voice guidance prompt for performing feature acquisition on the sound feature information to the acquisition terminal by operating the tone acquisition guidance instruction, the change environment acquisition guidance instruction, and/or the time acquisition guidance instruction, and using the voice guidance prompt as the acquisition guidance prompt.

The sound pitch specifically refers to the sound of the feeding sound in the audio stream with the feeding sound, the sound definition specifically refers to the sound definition of the feeding sound in the audio stream with the feeding sound, and the sound duration specifically refers to the duration of the feeding sound in the audio stream with the feeding sound; the tone acquisition guide instruction corresponding to the tone size specifically refers to an instruction for adjusting the tone in the process of acquiring the sound characteristic information of the feeding materials through the acquisition terminal, the environment change acquisition guide instruction corresponding to the sound definition specifically refers to an instruction for changing the sound acquisition environment in the process of acquiring the sound characteristic information of the feeding materials through the acquisition terminal, and the time acquisition guide instruction corresponding to the sound duration specifically refers to an instruction for increasing or reducing the sound acquisition time of the feeding materials in the process of acquiring the sound characteristic information of the feeding materials through the acquisition terminal.

Specifically, when the detection result output by the detection model determines that the key feature corresponding to the sound feature information is not qualified, it indicates that the tone size, the sound definition and/or the sound duration of the sound feature information in the detection result are/is unqualified, at this time, the tone acquisition guidance instruction corresponding to the tone size of the sound feature information that is not qualified is generated, the change environment acquisition guidance instruction corresponding to the sound definition of the sound feature information that is not qualified is generated, and/or the time acquisition guidance instruction corresponding to the sound duration of the sound feature information that is unqualified is generated;

based on the above, a voice guidance prompt for performing feature acquisition according to the tone size of the sound feature information is sent to the acquisition terminal by operating the tone acquisition guidance instruction, a voice guidance prompt for performing feature acquisition according to the sound definition of the sound feature information is sent to the acquisition terminal by operating the change environment acquisition guidance instruction, and/or a voice guidance prompt for performing feature acquisition according to the sound duration of the sound feature information is sent to the acquisition terminal by operating the time acquisition guidance instruction to serve as the acquisition guidance prompt; the voice guidance prompt specifically refers to a guidance prompt sent to a user holding the acquisition terminal in a voice broadcasting mode in the acquisition terminal.

In practical application, the voice guidance prompt corresponding to the tone acquisition guidance instruction can be a voice prompt for broadcasting the overhigh tone or the overlow tone of the livestock and poultry calling sound in a voice broadcasting manner through the acquisition terminal, and is used for reminding the acquisition terminal of the corresponding guidance prompt when the acquisition terminal acquires the livestock and poultry calling sound; the voice guidance prompt corresponding to the changed environment acquisition guidance instruction can be a voice prompt for broadcasting excessive environment noise in a voice broadcasting mode through the acquisition terminal and is used for reminding the acquisition terminal of changing the guidance prompt corresponding to the sound acquisition environment when the acquisition terminal acquires the cry of the livestock; the voice guidance prompt corresponding to the time acquisition guidance instruction can be a voice prompt for reporting that the sound-calling time of the feeding material is too short or too long in a voice broadcasting mode through the acquisition terminal, and is used for reminding the guidance prompt for prolonging or shortening the acquisition time when the acquisition terminal acquires the sound-calling of the feeding material.

In addition, the acquisition guide prompts corresponding to different acquisition guide instructions can be in other forms, for example, the acquisition guide prompt corresponding to the time acquisition guide instruction can be that a stopwatch is displayed in a screen of the acquisition terminal to remind the acquisition terminal of increasing or reducing the sound-calling duration of the acquisition of the livestock when the acquisition terminal acquires the sound-calling of the livestock; therefore, the acquisition guidance prompt can be set according to an actual application scene, and the description is not limited herein.

For example, in the process that a user purchases an insurance for a pet dog through the pet insurance platform, the sound characteristic information of the pet dog needs to be collected, the user uploads the video of the pet dog to the pet insurance platform in a mode of shooting a short video, the pet insurance platform obtains the sound characteristic information of the pet dog through extracting an audio stream from the video, by detecting the qualification of the sound characteristic information of the pet dog, the obtained detection result is that the sound duration of the sound characteristic information is unqualified, at the moment, a time acquisition guide instruction corresponding to the sound duration is generated, sending a voice guidance prompt for performing feature acquisition according to the sound duration to the mobile phone of the user through the running time acquisition guide instruction, wherein the voice guidance prompt is prompted in a voice broadcasting mode on the mobile phone of the user, the pet dog voice prompt system is used for reminding a user to increase or decrease the time for collecting the pet dog voice and then collecting the voice characteristic information of the pet dog.

(3) If the description content and/or the attribute information of the text feature information exist in the detection result, generating a description acquisition guide instruction corresponding to the description content of the text feature information which is not qualified for detection, and/or generating an input acquisition guide instruction corresponding to the attribute information of the text feature information which is not qualified for detection; correspondingly, the step 108 is executed, where the step 108 specifically refers to sending an acquisition guidance prompt for performing feature acquisition on the at least one key feature that is not qualified for detection to the acquisition terminal by operating the acquisition guidance instruction, that is, sending a text guidance prompt for performing feature acquisition on the text feature information to the acquisition terminal by operating the description acquisition guidance instruction and/or inputting the acquisition guidance instruction, and using the text guidance prompt as the acquisition guidance prompt.

The description content specifically refers to information for performing character description on the feeding material by a user, the attribute information specifically refers to information about the attribute of the feeding material, which is filled by the user aiming at the feeding material, the description acquisition guide instruction corresponding to the description content specifically refers to an instruction for performing character description on the feeding material by an acquisition terminal acquisition user, and the input acquisition guide instruction corresponding to the attribute information specifically refers to an instruction for performing attribute filling on the feeding material by the acquisition terminal acquisition user.

Specifically, when the detection result output by the detection model determines that the key feature corresponding to the text feature information is not qualified, it indicates that the description content and/or the attribute information of the text feature information in the detection result is unqualified, and at this time, a description acquisition guidance instruction corresponding to the description content of the text feature information that is unqualified is generated, and/or an input acquisition guidance instruction corresponding to the description content of the text feature information that is unqualified is generated;

based on the text characteristic information, operating the description acquisition guide instruction to send a character guide prompt for performing characteristic acquisition on the description content of the text characteristic information to the acquisition terminal, and/or operating the input acquisition guide instruction to send a character guide prompt for performing characteristic acquisition on the description content of the text characteristic information to the acquisition terminal to serve as the acquisition guide prompt; the text guidance prompt specifically refers to a guidance prompt sent to a user holding the acquisition terminal in a text display mode in a screen of the acquisition terminal.

In practical application, the text guidance prompt corresponding to the description acquisition guidance instruction may be a text prompt for displaying too little or too much description information of the livestock in a text display mode through a screen of the acquisition terminal, and is used for reminding the acquisition terminal of the corresponding guidance prompt when the acquisition terminal acquires the description content of the livestock; the character guide prompt corresponding to the input acquisition guide instruction can be a character prompt for displaying attribute information of the feeding material in a character display mode through a screen of the acquisition terminal, and is used for reminding the acquisition terminal of acquiring the corresponding guide prompt when the attribute information of the feeding material is acquired.

In addition, the acquisition guidance prompts corresponding to different acquisition guidance instructions can be in other forms, for example, the acquisition guidance prompt describing the acquisition guidance instructions can be a filling figure displayed in a screen of the acquisition terminal to remind the acquisition terminal to increase or decrease the description content of the acquisition material when the description content of the acquisition material is acquired; therefore, the acquisition guidance prompt can be set according to an actual application scene, and the description is not limited herein.

For example, in the process that a user purchases insurance for a pet dog through a pet insurance platform, the text characteristic information of the pet dog needs to be collected, the user uploads the text characteristic information of the pet dog to the pet insurance platform in a form filling mode, the qualification detection is carried out on the text characteristic information of the pet dog, the obtained detection result is that the attribute information of the text characteristic information is unqualified, an input collection guide instruction corresponding to the attribute information is generated at the moment, a character guide prompt for carrying out feature collection on the attribute information is sent to a mobile phone of the user through operating the input collection guide instruction, the character guide prompt is used for prompting the user that the filled attribute information is too much or too little through displaying characters on the mobile phone of the user, and then the text characteristic information is collected for the pet dog.

In addition, under the condition that a plurality of key features which are not qualified in detection exist at the same time, corresponding acquisition guide instructions can be generated aiming at the plurality of key features which are not qualified in detection at the same time, in the process of operating a plurality of acquisition guide instructions, the acquisition guide instructions can be sequenced, then the acquisition guide instructions are operated one by one according to the sequencing result, acquisition guide prompts aiming at key features which are not qualified in detection are sent to the acquisition terminal, in the event that the user re-acquires the key features for the occupant according to the acquisition guidance prompt and is eligible, then sending a next acquisition guiding prompt aiming at the key features which are not qualified in the next detection to the acquisition terminal, and when the user finishes collecting the key features aiming at the feeding materials again according to all the collection guiding prompts and is qualified, sending a collection qualified prompt to the user with the collection terminal.

In the process of sending the acquisition guide prompt for performing feature acquisition on the at least one key feature which is not qualified in detection to the acquisition terminal, different acquisition guide prompts can be sent to the acquisition terminal according to different key features, the operation difficulty of a user for performing key feature acquisition according to the acquisition guide prompt is reduced, the qualification rate of the user for acquiring the identity feature information of the livestock in various modes is improved, and the experience effect of the user is improved.

In specific implementation, when it is determined that the identity characteristic information acquired again is qualified on the basis of sending the acquisition guidance prompt to the acquisition terminal, an acquisition qualification prompt may be sent to the acquisition terminal, and in one or more implementation modes of this embodiment, a process of sending the acquisition qualification prompt to the acquisition terminal is as follows:

Specifically, after the acquisition guide prompt is sent to the acquisition terminal, the user uploads identity feature information again according to the acquisition guide prompt, at this time, a secondary key feature acquired according to the acquisition guide prompt aiming at the at least one key feature which is not qualified in detection is received, the secondary key feature specifically refers to a feature acquired again aiming at the at least one key feature which is not qualified in detection, and based on the secondary key feature, when it is determined that the identity feature information acquired in the various modalities aiming at the feeding material is qualified in detection, it is indicated that the identity feature information of the feeding material does not need to be acquired continuously, and an acquisition qualified prompt is sent to the acquisition terminal according to the detection qualified result.

According to the guiding mode for the acquisition of the identity information of the feeding material, after the acquisition of the identity characteristic information of the feeding material in various modes is completed, the detection results of the key characteristics of the feeding material in various modes are obtained through the detection model, if at least one key characteristic is unqualified in detection, an acquisition guiding instruction can be generated for the at least one key characteristic which is unqualified in detection, and finally an acquisition guiding prompt for the at least one key characteristic is sent to the acquisition terminal by operating the acquisition guiding instruction, so that the acquisition guiding prompt can be correctly generated for the key characteristics of the unqualified identity characteristic information and sent to the acquisition terminal under the condition that the identity characteristic information in different modes is unqualified, and a user can acquire the qualified identity characteristic information of the feeding material according to a correct guiding mode, the experience effect of the user is improved, and the acquisition efficiency and the acquisition qualification rate of the identity characteristic information of the collected materials are further improved.

The following description further illustrates the guiding method for acquiring the identity information of the animal feeding material by taking the application of the guiding method for acquiring the identity information of the animal feeding material provided in the present specification in the pet file establishment as an example with reference to fig. 2. Fig. 2 shows a processing flow diagram of a guiding method applied to pet archive establishment and feeding identity information acquisition, which is provided in an embodiment of the present specification, and specifically includes the following steps:

step 202: and acquiring video streams and audio streams which are acquired by a user in various modalities aiming at the pet dog through a mobile phone.

Specifically, a user receives a pet dog, and in order to ensure that the pet dog feeding is legal, the pet dog needs to be subjected to file establishment; based on this, the user includes the body shooting of pet dog and the sound of calling of this pet dog in a section of video that this pet dog was recorded to through the cell-phone in this video.

Step 204: and extracting a frame of image in the video stream as image characteristic information of the pet dog.

Step 206: and extracting audio information from the audio stream as audio characteristic information of the pet dog.

Step 204 and step 206 may be executed simultaneously or sequentially, and the specific execution sequence may be set according to the actual application scenario.

Step 208: and extracting the image brightness and the image definition in the image characteristic information.

Step 210: and extracting the tone and the sound time length in the sound characteristic information.

Step 208 and step 210 may be executed simultaneously or sequentially, and the specific execution order may be set according to the actual application scenario.

Step 212: and determining a first characteristic numerical value and a second characteristic numerical value of the image brightness and the image definition under the characteristic dimension of the corresponding modality according to the image characteristic information.

Step 214: and determining a third characteristic value and a fourth characteristic value of the tone and the sound duration under the characteristic dimension of the corresponding mode according to the sound characteristic information.

Step 212 and step 214 may be executed simultaneously or sequentially, and the specific execution order may be set according to the actual application scenario.

Step 216: and performing feature construction on the first feature numerical value, the second feature numerical value, the third feature numerical value and the fourth feature numerical value to obtain a multi-mode feature vector, and inputting the multi-mode feature vector into a detection model to perform qualification detection to obtain a detection result.

Step 218: and determining that the image brightness is unqualified and the sound duration is unqualified according to the detection result.

Specifically, it is determined that the image brightness is too high and the sound duration is too short according to the detection result.

Step 220: and generating an exposure acquisition guide instruction corresponding to the unqualified detection image brightness, and generating a time acquisition guide instruction corresponding to the unqualified detection sound duration.

Step 222: and the operation duration acquisition guide instruction sends a voice guide prompt for acquiring the features according to the sound duration to the mobile phone of the user.

Specifically, the exposure degree of the mobile phone when the pet dog is shot is reminded to be adjusted to be low by an arrow guide prompt; and reminding the user that the duration of the mobile phone for collecting the pet dog cry needs to be increased through the voice guide instruction.

Step 224: and acquiring image characteristic information and sound characteristic information which are acquired again by the user according to the arrow guide prompt and the voice guide prompt.

Step 226: and under the condition that the identity characteristic information in various modes is qualified, establishing a file of the pet dog and storing the file into a database.

The guiding mode for collecting the identity information of the feeding materials provided by the specification realizes that the collecting guiding prompt can be correctly generated aiming at the key features of the unqualified identity feature information and sent to the user under the condition that the identity feature information in different modes is unqualified, so that the user can collect the qualified identity feature information of the pet dog according to the correct guiding mode, the experience effect of the user is improved, and the collecting efficiency and the collecting qualification rate for collecting the identity feature information of the pet dog are further improved.

Corresponding to the embodiment of the method, the description also provides an embodiment of a guiding device for acquisition of the identity information of the feeding material, and fig. 3 shows a schematic structural diagram of the guiding device for acquisition of the identity information of the feeding material provided by the embodiment of the description. As shown in fig. 3, the apparatus includes:

the acquiring characteristic information module 302 is configured to acquire identity characteristic information acquired by the acquisition terminal in various modalities according to the feeder;

the qualification detection module 304 is configured to extract key features corresponding to the identity feature information in the various modalities, input the key features into a detection model, perform qualification detection on the key features corresponding to the identity feature information in the various modalities, and obtain a detection result output by the detection model and specific to the key features corresponding to the identity feature information in the various modalities;

a generating instruction module 306 configured to generate an acquisition guidance instruction corresponding to at least one key feature that is not qualified in detection if the at least one key feature exists in the detection result and is not qualified in detection;

a guidance prompt module 308 configured to issue a collection guidance prompt for feature collection for the at least one key feature that is not qualified for detection to the collection terminal by executing the collection guidance instruction.

In an alternative embodiment, the qualification module 304 includes:

the key feature extraction unit is configured to extract key features corresponding to the identity feature information in the various modalities;

a feature value determining unit configured to determine, according to the identity feature information in the various modalities, a feature value of the key feature in a feature dimension of the corresponding modality;

and the model detection unit is configured to input a multi-modal feature vector obtained by feature construction based on the feature numerical value into the detection model to detect the qualification of key features, and obtain the detection result output by the detection model.

In an optional embodiment, the generation instruction module 306 is further configured to:

In an optional embodiment, the module 302 for obtaining feature information includes:

an acquisition unit configured to acquire video streams, audio streams and/or texts acquired by the acquisition terminal in various modalities with respect to the feeder;

a first determination unit configured to determine image feature information by extracting an image corresponding to one frame in the video stream, determine audio information in the audio stream as sound feature information, and extract a keyword as text feature information in the text;

a second determination unit configured to use the image feature information, the sound feature information, and/or the text feature information as the identity feature information in the various modalities.

accordingly, the guidance prompt module 308 is run;

the guidance prompt module 308 is further configured to:

accordingly, the guidance prompt module 308 is run;

the guidance prompt module 308 is further configured to:

accordingly, the guidance prompt module 308 is run;

the guidance prompt module 308 is further configured to:

In an optional embodiment, the device for guiding the acquisition of the identity information of the animal feed further comprises:

the reminding module is configured to send a qualified acquisition reminding to the acquisition terminal if the detection result is qualified;

the building module is configured to build a corresponding relation between the unique identifier of the feeder and the identity characteristic information in the various modalities;

a storage module configured to store the identity feature information of the feeder in the various modalities into a preset database based on the correspondence between the unique identifier and the identity feature information in the various modalities.

the current characteristic information acquisition module is configured to acquire current identity characteristic information acquired by a current acquisition terminal in various modes aiming at the current feeder and a unique identifier of the current feeder under the condition that a service processing instruction is received;

an extraction feature information module configured to extract identity feature information of the current feeder in the various modalities if the unique identifier of the feeder matches the unique identifier of the feeder;

a correlation degree calculation module configured to calculate a correlation degree between the current identity feature information and the identity feature information;

and the service processing module is configured to determine that the current feeder is the feeder and perform service processing on the current feeder under the condition that the association degree is greater than or equal to a preset association degree threshold value.

a determination that identity feature information collected in the various modalities for the animal feeding is qualified for detection if a secondary key feature collected for the at least one key feature that is not qualified for detection according to the collection guidance prompt is received;

and the qualified reminding module is configured to send out qualified collection reminding to the collection terminal according to the qualified detection result.

According to the guiding device for acquiring the identity information of the feeding material, after the identity characteristic information of the feeding material in various modes is acquired, the detection results of the key characteristics of the feeding material in various modes are obtained through the detection model, if at least one key characteristic is unqualified in detection, an acquisition guiding instruction can be generated for the at least one key characteristic which is unqualified in detection, and finally an acquisition guiding prompt for the at least one key characteristic is sent to the acquisition terminal by operating the acquisition guiding instruction, so that the acquisition guiding prompt can be correctly generated for the key characteristics of unqualified identity characteristic information and sent to the acquisition terminal under the condition that the identity characteristic information in different modes is unqualified, and a user can acquire the qualified identity characteristic information of the feeding material according to a correct guiding mode, the experience effect of the user is improved, and the acquisition efficiency and the acquisition qualification rate of the identity characteristic information of the collected materials are further improved.

The above is an illustrative scheme of the guiding device for acquisition of the identity information of the feeding materials in the embodiment. It should be noted that the technical scheme of the guiding device for acquiring the identity information of the feeding material and the technical scheme of the guiding method for acquiring the identity information of the feeding material belong to the same concept, and details of the technical scheme of the guiding device for acquiring the identity information of the feeding material, which are not described in detail, can be referred to the description of the technical scheme of the guiding method for acquiring the identity information of the feeding material.

FIG. 4 illustrates a block diagram of a computing device 400 provided according to an embodiment of the present description. The components of the computing device 400 include, but are not limited to, a memory 410 and a processor 420. Processor 420 is coupled to memory 410 via bus 430 and database 450 is used to store data.

Computing device 400 also includes access device 440, access device 440 enabling computing device 400 to communicate via one or more networks 460. Examples of such networks include the Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the internet. The access device 440 may include one or more of any type of network interface (e.g., a Network Interface Card (NIC)) whether wired or wireless, such as an IEEE802.11 Wireless Local Area Network (WLAN) wireless interface, a worldwide interoperability for microwave access (Wi-MAX) interface, an ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a bluetooth interface, a Near Field Communication (NFC) interface, and so forth.

In one embodiment of the present description, the above-described components of computing device 400, as well as other components not shown in FIG. 4, may also be connected to each other, such as by a bus. It should be understood that the block diagram of the computing device architecture shown in FIG. 4 is for purposes of example only and is not limiting as to the scope of the present description. Those skilled in the art may add or replace other components as desired.

Computing device 400 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., tablet, personal digital assistant, laptop, notebook, netbook, etc.), mobile phone (e.g., smartphone), wearable computing device (e.g., smartwatch, smartglasses, etc.), or other type of mobile device, or a stationary computing device such as a desktop computer or PC. Computing device 400 may also be a mobile or stationary server.

Wherein processor 420 is configured to execute the following computer-executable instructions:

The above is an illustrative scheme of a computing device of the present embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the method for guiding the acquisition of the identity information of the material to be maintained belong to the same concept, and details of the technical scheme of the computing device, which are not described in detail, may all be referred to in the description of the technical scheme of the method for guiding the acquisition of the identity information of the material to be maintained.

An embodiment of the present specification also provides a computer readable storage medium storing computer instructions that, when executed by a processor, are operable to:

The above is an illustrative scheme of a computer-readable storage medium of the present embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the method for guiding the acquisition of the identity information of the animal feeding material belong to the same concept, and details that are not described in detail in the technical scheme of the storage medium can be referred to in the description of the technical scheme of the method for guiding the acquisition of the identity information of the animal feeding material.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The computer instructions comprise computer program code which may be in the form of source code, object code, an executable file or some intermediate form, or the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U.S. disk, removable hard disk, magnetic diskette, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signal, telecommunications signal, and software distribution medium, etc. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.

It should be noted that, for the sake of simplicity, the foregoing method embodiments are described as a series of acts or combinations, but those skilled in the art should understand that the present disclosure is not limited by the described order of acts, as some steps may be performed in other orders or simultaneously according to the present disclosure. Further, those skilled in the art should also appreciate that the embodiments described in this specification are preferred embodiments and that acts and modules referred to are not necessarily required for this description.

In the above 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.

The preferred embodiments of the present specification disclosed above are intended only to aid in the description of the specification. Alternative embodiments are not exhaustive and do not limit the invention to the precise embodiments described. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the specification and its practical application, to thereby enable others skilled in the art to best understand the specification and utilize the specification. The specification is limited only by the claims and their full scope and equivalents.

Claims

1. A method for guiding acquisition of storage identity information, comprising:

acquiring identity characteristic information acquired by an acquisition terminal in various modes aiming at the material-storing materials, wherein different types of material-storing materials acquire identity characteristic information in different modes, and the source or form of each type of information is called a mode;

2. The guiding method for acquisition of the identity information of the feeding material according to claim 1, wherein the step of extracting the key features corresponding to the identity feature information in the various modalities and inputting the key features into a detection model, and performing eligibility detection on the key features corresponding to the identity feature information in the various modalities to obtain a detection result output by the detection model for the key features corresponding to the identity feature information in the various modalities comprises the steps of:

3. The method for guiding acquisition of feeding identity information according to claim 1, wherein the generating of acquisition guide instructions corresponding to the at least one key feature that is not qualified for detection comprises:

determining an adjusting mode corresponding to the at least one key feature which is unqualified in detection, and generating the acquisition guide instruction corresponding to the at least one key feature which is unqualified in detection according to the adjusting mode.

4. The method for directing acquisition of feeding identity information according to claim 3, wherein said determining the adjustment mode corresponding to the at least one key feature that fails to qualify for detection comprises:

and comparing the at least one key feature which is not qualified in detection with the feature sample, and determining the adjusting mode corresponding to the at least one key feature which is not qualified in detection according to the comparison result.

5. The method for guiding acquisition of identity information of an feeder according to claim 1, wherein acquiring identity characteristic information acquired by the acquisition terminal in various modalities with respect to the feeder comprises:

6. The method for guiding management identity information acquisition according to claim 5, wherein if at least one key feature exists in the detection result and is detected unqualified, generating an acquisition guide instruction corresponding to the at least one key feature that is detected unqualified, comprises:

7. The method for guiding management identity information acquisition according to claim 5, wherein if at least one key feature exists in the detection result and is detected unqualified, generating an acquisition guide instruction corresponding to the at least one key feature that is detected unqualified, comprises:

if the tone size, the sound definition and/or the sound duration of the sound feature information exist in the detection result and are/is not qualified in detection, generating a tone acquisition guide instruction corresponding to the tone size of the sound feature information which is not qualified in detection, generating an environment change acquisition guide instruction corresponding to the sound definition of the sound feature information which is not qualified in detection, and/or generating a time acquisition guide instruction corresponding to the sound duration of the sound feature information which is not qualified in detection as the acquisition guide instruction;

8. The method for guiding acquisition of identity information of an animal according to claim 5, wherein if at least one key feature exists in the detection result, the detection result is not qualified, generating an acquisition guide instruction corresponding to the at least one key feature, the acquisition guide instruction comprising:

9. The method for guiding acquisition of identity information of an animal feeding material according to claim 1, wherein after the step of extracting key features corresponding to the identity feature information in the various modalities and inputting the key features into a detection model, performing eligibility detection on the key features corresponding to the identity feature information in the various modalities to obtain a detection result output by the detection model for the key features corresponding to the identity feature information in the various modalities is executed, the method further comprises:

and storing the identity characteristic information of the material in the various modes into a preset database based on the corresponding relation between the unique identifier and the identity characteristic information in the various modes.

10. The method for directing acquisition of identity information of an feeder according to claim 9, further comprising, after the step of storing the identity information of the feeder in the various modalities into a preset database based on the correspondence between the unique identifier and the identity information in the various modalities is performed:

11. The guiding method for acquisition of feeding identity information according to claim 1, further comprising after the step of performing an acquisition guidance prompt for feature acquisition for the at least one key feature that is not qualified for detection is performed by executing the acquisition guidance instruction to the acquisition terminal, the step of performing feature acquisition for the at least one key feature that is not qualified for detection further comprises:

12. A guide device for home identity information acquisition, comprising:

the system comprises a characteristic information acquisition module, a characteristic information acquisition module and a characteristic information analysis module, wherein the characteristic information acquisition module is configured to acquire identity characteristic information acquired by an acquisition terminal in various modes aiming at the materials, different types of materials are acquired by different types of materials, and the source or form of each type of information is called as a mode;

the instruction generation module is configured to generate an acquisition guide instruction corresponding to at least one key feature which is unqualified in detection if the at least one key feature exists in the detection result and is unqualified in detection;

13. A computing device, comprising:

a memory and a processor;

the memory is to store computer-executable instructions, and the processor is to execute the computer-executable instructions to:

acquiring identity characteristic information acquired by an acquisition terminal in various modes aiming at the material, wherein different types of materials are acquired by different modes of identity characteristic information, and the source or form of each type of information is called a mode;

14. A computer readable storage medium storing computer instructions which, when executed by a processor, carry out the steps of the method for directing acquisition of identity information of an occupant according to any one of claims 1 to 11.