CN113076964A

CN113076964A - Method and device for identifying similar objects and electronic equipment

Info

Publication number: CN113076964A
Application number: CN202010006966.1A
Authority: CN
Inventors: 申小伟; 虞新阳; 孔明明
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2020-01-03
Filing date: 2020-01-03
Publication date: 2021-07-06
Anticipated expiration: 2040-01-03
Also published as: CN113076964B

Abstract

The invention discloses a method, a device and electronic equipment for identifying similar objects, wherein the method comprises the following steps: acquiring a target object and an object set to be identified corresponding to the target object; performing similar recognition in the object set aiming at the target object respectively through each recognition model of at least two recognition models to obtain a similar object list recognized respectively; and obtaining a similar object list of the target object according to the respectively identified similar object list.

Description

Method and device for identifying similar objects and electronic equipment

Technical Field

The present invention relates to a data processing technology, and more particularly, to a method of identifying similar objects, a method of identifying similar goods, an apparatus of identifying similar objects, an electronic device, and a computer-readable storage medium.

Background

At present, similar identification is applied in many occasions, wherein the similar identification is also used for identifying whether two objects are similar, for example, distribution errors are avoided through the similar identification in logistics distribution, and distribution accuracy is improved.

In the prior art, similarity identification is to determine whether two objects are similar through one identification model, for example, determine whether images of two objects are similar through one deep learning model. In the process of performing similarity identification through an identification model, a similarity threshold needs to be set to divide similar objects and dissimilar objects, and here, since the similarity threshold is usually an empirical value, but the similarity threshold plays a decisive role in identifying whether two objects are similar, there is a problem of low accuracy in performing similarity identification through an identification model in the prior art, which is reflected in that a similar object list obtained by identifying any object is incomplete, or a similar object list obtained by identifying any object contains dissimilar objects, for example.

Disclosure of Invention

An object of the embodiments of the present invention is to provide a new technical solution for performing similarity identification, so as to improve the accuracy of similarity identification.

According to a first aspect of the present invention, there is provided a method of identifying similar objects, comprising:

acquiring a target object and an object set to be identified corresponding to the target object;

performing similar recognition in the object set aiming at the target object respectively through each recognition model of at least two recognition models to obtain a similar object list recognized respectively;

and obtaining a similar object list of the target object according to the respectively identified similar object list.

Optionally, the performing, by each of the at least two recognition models, similar recognition on the target object in the object set respectively to obtain the respective recognized similar object lists includes:

respectively obtaining a similarity index value between each object in the object set and the target object through each recognition model;

and for each recognition model, obtaining a similar object list recognized by the corresponding recognition model according to the similar index value obtained by the corresponding recognition model.

Optionally, the obtaining the similar object list identified by the corresponding identification model according to the similar index value obtained by the corresponding identification model includes:

and selecting a set number k of objects with the highest similarity index value from the object set according to the similarity index value obtained by the corresponding identification model to form a similar object list identified by the corresponding identification model.

Optionally, the method further includes a step of determining the set number k, including:

according to the current numerical value of the set number k, obtaining a current similar object list respectively identified by each identification model;

acquiring a next similar object list respectively identified by each identification model when the set number k is a next numerical value larger than the current numerical value;

for each recognition model, comparing the corresponding next similar object list with the corresponding current similar object list to obtain a corresponding newly added object list;

determining the current numerical value as the final value of the set number k under the condition that the occurrence frequency of at least part of objects in the current similar object list in all the newly added object lists is smaller than a set first frequency threshold;

and adjusting the current value of the set value under the condition that the frequency of occurrence of any one object in at least part of objects in all the newly added object lists is greater than or equal to the first frequency threshold.

Optionally, the step of determining the set number k further includes a step of selecting the at least part of the objects, including:

and selecting the objects with the frequency of occurrence greater than or equal to a set second frequency threshold from all the current similar object lists as the at least part of the objects.

Optionally, the step of determining the set number k further includes:

and increasing the value of the set number k according to the set step distance on the basis of the current value of the set number k to serve as the next value.

Optionally, the adjusting the current value of the set value includes:

and updating the current value of the set value to be equal to the next value.

Optionally, the obtaining a similarity index value between each object in the object set and the target object includes:

extracting vector values of the target object for feature vectors set by corresponding recognition models through corresponding recognition models, and extracting vector values of each object in the object set for the feature vectors;

for each object in the object set, obtaining a distance value between the vector value of the corresponding object and the vector value of the target object through a corresponding recognition model, and using the distance value as a similarity index value between the corresponding object and the target object.

Optionally, the obtaining a similar object list of the target object according to the respective identified similar object lists includes:

for each object in all the similar object lists, obtaining the similar score of the corresponding object according to the occurrence frequency of the corresponding object in all the similar object lists;

and screening out objects similar to the target object from all the similar object lists according to the similar scores of all the objects in all the similar object lists to form a similar object list of the target object.

Optionally, the screening, according to the similarity score of each object in all the similar object lists, an object similar to the target object in all the similar object lists includes:

and screening out the objects with the similarity scores larger than or equal to a set score threshold value from all the similar object lists as the objects similar to the target object.

Optionally, the obtaining the target object and the set of objects to be identified corresponding to the target object includes:

and responding to the selection operation of the plurality of objects, selecting any object from the plurality of selected objects as the target object, and selecting other objects to form an object set to be identified corresponding to the target object.

and responding to the selection operation of any object in the object list, selecting the selected object as a target object, and selecting other objects in the object list to form an object set corresponding to the target object.

Optionally, the method further includes:

and outputting a similar object list of the target object.

Optionally, the outputting the similar object list of the target object includes:

and sending the similar object list of the target object to a terminal device bound with a target account, wherein the target account provides an account of distribution service for the target object and the objects in the object set.

Optionally, the method further includes:

and selecting the at least two recognition models matched with the object type from a recognition model set according to the object type of the target object.

According to a second aspect of the present invention, there is also provided a method of identifying similar goods, comprising:

acquiring a commodity set of commodities with at least one same distribution characteristic;

for each commodity in the commodity set, performing similar identification on the corresponding commodity in the commodity set through each identification model of at least two identification models to obtain a respective identified similar commodity list;

and obtaining a similar commodity list of the corresponding commodity according to the respectively identified similar commodity list.

Optionally, the acquiring the commodity set of commodities with at least one same distribution characteristic includes:

a commodity set of commodities corresponding to the same delivery box and the same delivery time is obtained.

Optionally, the method further includes:

and sending the obtained similar commodity list to terminal equipment bound with a target account, wherein the target account is a distributor account for providing distribution service for a corresponding distribution box at the corresponding distribution time.

According to a third aspect of the present invention, there is also provided a method of identifying similar goods, comprising:

for each commodity in the commodity set, obtaining a similar list of the corresponding commodity in the commodity set according to a similar commodity list of the corresponding commodity in a commodity library, which is obtained in advance;

providing an obtained similar list through the terminal equipment bound with the target account;

wherein, obtaining the similar commodity list of the corresponding commodity in the commodity library comprises:

performing similar identification in the commodity library aiming at corresponding commodities respectively through each identification model of at least two identification models to obtain a similar commodity list which is respectively identified;

and obtaining a similar commodity list of the corresponding commodity in the commodity library according to the respectively identified similar commodity list.

According to a fourth aspect of the present invention, there is also provided a method of identifying similar goods, comprising:

acquiring a commodity selected from a current commodity list as a target commodity;

respectively carrying out similar identification on the target commodity in the current commodity list through each identification model of at least two identification models to obtain respective identified similar commodity lists;

obtaining a similar commodity list of the target commodity according to the respectively identified similar commodity list;

and displaying the similar commodity list in the current commodity list.

According to a fifth aspect of the present invention, there is also provided a similarity identification method, including:

according to a similar commodity list of the target commodity in a commodity library, which is obtained in advance, a similar list of the target commodity in a current commodity list is obtained;

displaying the similar commodity list in the current commodity list;

wherein the obtaining of the similar commodity list of the target commodity in the commodity library comprises:

performing similar identification in the commodity library aiming at the target commodity through each identification model of at least two identification models to obtain a similar commodity list which is respectively identified;

and obtaining a similar commodity list of the target commodity in the commodity library according to the respectively identified similar commodity list.

According to a sixth aspect of the present invention, there is also provided an apparatus for identifying similar objects, comprising:

the object acquisition module is used for acquiring a target object and an object set to be identified corresponding to the target object;

the identification processing module is used for performing similar identification on the target object in the object set through each identification model of at least two identification models to obtain a similar object list which is respectively identified; and the number of the first and second groups,

and the list generation module is used for obtaining the similar object list of the target object according to the respectively identified similar object list.

According to a seventh aspect of the present invention, there is also provided an electronic device, comprising the apparatus according to the third aspect of the present invention; alternatively, the first and second electrodes may be,

the electronic device comprises a memory and a processor;

the memory stores a computer program which, when executed by the processor, implements the method according to any one of the first to fifth aspects of the invention.

According to a fifth aspect of the present invention, there is also provided a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program which can be read and executed by a computer, and the computer program is used for executing the method according to any one of the first to fifth aspects of the present invention when the computer program is read and executed by the computer.

Based on the similar identification scheme provided by the embodiment of the invention, the target object can be subjected to similar identification through at least two identification models, so that the similar object lists which are respectively identified are respectively obtained through each identification model, and the objects which are similar to the target object are screened out according to the obtained similar object lists, so as to generate the similar object list of the target object. According to the similar identification scheme, the objects similar to the target object can be screened according to the similar object lists respectively identified by the plurality of identification models, so that the influence of the similar threshold on the similar identification result can be reduced, and the accuracy of the similar identification is improved.

Other features of the present invention and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.

Drawings

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

FIG. 1a is a schematic diagram illustrating an application scenario of an alternative embodiment of the present invention;

FIG. 1b is a schematic diagram illustrating an application scenario of another alternative embodiment of the present invention;

FIG. 2 is a schematic block diagram of the hardware architecture of an electronic device that can be used to implement the method of identifying similar objects of the present invention;

FIG. 3 is a flow diagram of a method of identifying similar objects according to one embodiment;

FIG. 4 is a flowchart illustrating the steps of determining the set number k according to one embodiment;

FIG. 5 is a schematic illustration of the operation steps for determining the set number k, according to one example;

FIG. 6 is a flow diagram of a method of identifying similar merchandise, according to one embodiment;

FIG. 7 is a flow diagram of a method of identifying similar items according to yet another embodiment;

FIG. 8 is a flow diagram of an apparatus to identify similar objects according to one embodiment.

Detailed Description

Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.

In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.

The method of this embodiment may be used to identify similar objects of a target object to generate a similar object list of the target object, where the object may be any article, a human face image, or the like, and is not limited herein. In the method of this embodiment, similar recognition is performed on a target object through at least two recognition models to obtain respective similar object lists, and according to the similar object lists obtained through the recognition models, similar objects of the target object are screened out from the similar object lists in a voting manner or the like, so as to generate a similar object list of the target object. The present embodiment may be applied to any scene that needs to perform similar recognition, for example, a logistics distribution scene, a similar goods pushing scene, a person tracking scene, and the like, that is, the object in the present embodiment may be a good, another article, a face image, and the like, which is not limited herein.

Fig. 1a shows an application of the method of the present embodiment in a logistics distribution scenario in which a distribution system distributes corresponding commodities to each distribution box according to an order address and the like, for example, commodity 1, commodity 2, commodity 3, commodity 4, commodity 5 and the like to the # 1 distribution box for distribution, and commodity 1, commodity 5, commodity 6, commodity 7, commodity 8 to the # 1 distribution box for distribution and the like. In the logistics distribution scene, if similar commodities exist in the same distribution box, a distributor is prone to have a distribution error in the process of distributing the commodities, so that for each distribution box, similar identification can be performed on each commodity in the corresponding distribution box within the commodity range of the corresponding distribution box through the similar identification method of the embodiment to obtain a similar commodity list of each commodity, and the similar commodity list is sent to a mobile phone of the distributor of the corresponding distribution box to remind the distributor of the existence of the similar commodities in the distribution box for which the distributor is responsible, so that the distribution error is avoided.

As shown in fig. 1a, according to the method of the present embodiment, for example, three different recognition models are provided, namely, recognition model M1, recognition model M2, and recognition model M3. Taking the # 1 delivery box as an example, according to the method of the present embodiment, for each commodity in the # 1 delivery box, a similar commodity list can be identified within the commodity range of the # 1 delivery box. Continuing with the example of the product 1 in the # 1 delivery box, taking the product 1 as a target product, taking the other products in the # 1 delivery box as a product set to be identified corresponding to the product 1, identifying the products similar to the product 1 in the other products in the # 1 delivery box through the identification model M1, and forming a similar product list S1 of the product 1; identifying the similar commodities to the commodity 1 among other commodities in the 1# distribution box through the identification model M2, and forming a similar commodity list S2 of the commodity 1; and identifying the similar commodities to the commodity 1 from the other commodities in the 1# distribution box through the identification model M2 to form a similar commodity list S3 of the commodity 1; finally, a list of similar items of the product 1 in the # 1 delivery box is obtained from the similar product list S1, the similar product list S2 and the similar product list S3, which may be obtained by, for example, voting and counting the products in these similar product lists S1, S2 and S3. After identifying and obtaining the similar commodity lists of the corresponding commodities in the commodity range of the 1# distribution box for each commodity in the 1# distribution box, the similar commodity lists can be sent to the distributor mobile phone 3100A of the 1# distribution box, so that the distributor can perform key identification on the similar commodities in the 1# distribution box when distributing the commodities by inquiring the similar commodity lists of each commodity in the 1# distribution box on the mobile phone 3100A, and distribution errors are avoided.

Similarly, taking the # 2 delivery box as an example, according to the method of the present embodiment, for each product in the # 2 delivery box, a respective similar product list can be identified within the product range of the # 2 delivery box. For example, there is also product 1 in the 2# delivery box, and continuing with product 1 in the 2# delivery box as an example, product 1 is taken as a target product, and the other products in the 2# delivery box are taken as a product set to be identified corresponding to product 1, and among the other products in the 2# delivery box, products similar to product 1 are identified by identification model M1, and a similar product list S4 of product 1 is formed; identifying the similar commodities to the commodity 1 among other commodities in the 2# distribution box through the identification model M2, and forming a similar commodity list S5 of the commodity 1; and identifying the similar commodities to the commodity 1 from the other commodities in the 2# distribution box through the identification model M3 to form a similar commodity list S6 of the commodity 1; finally, a similar item list of the article 1 in the # 2 delivery box is obtained from the similar article list S4, the similar article list S5, and the similar article list S6. After identifying and obtaining the similar commodity lists of the corresponding commodities in the commodity range of the 2# distribution box for each commodity in the 2# distribution box, the similar commodity lists can be sent to the mobile phone 3100B of the distributor of the 2# distribution box, so that the distributor can perform key identification on the similar commodities in the 2# distribution box when distributing the commodities by inquiring the similar commodity lists of each commodity in the 2# distribution box on the mobile phone 3100B, and distribution errors are avoided.

Fig. 1b shows an application of the method of the present embodiment in a goods push scenario. In this scenario, for example, a user searches for "sports pants" in a client of the e-commerce platform through the user terminal 2000, the client will provide a product list with a product tag of "sports pants", on this basis, if the user selects the product 1 in the product list, for example, clicks a list item of the product 1, the user may select the selected product 1 as a target product, and select other products in the product list to form a product set to be identified of the selected product 1, so as to apply the method according to this embodiment, identify a product similar to the selected product 1 in the product set, further obtain a similar product list of the selected product 1, and recommend the similar product list to the user, so as to narrow a screening range of the user when screening the desired product. In this scenario, according to the method in this embodiment, a similar commodity to commodity 1 is identified from among the other searched commodities by the identification model M1, and a similar commodity list S7 of commodity 1 is formed; identifying the commodities similar to the commodity 1 from the other searched commodities through the identification model M2 to form a similar commodity list S8 of the commodity 1; identifying the commodities similar to the commodity 1 from the other searched commodities through the identification model M3 to form a similar commodity list S9 of the commodity 1; finally, according to the similar commodity list S7, the similar commodity list S8 and the similar commodity list S9, a similar item list of the commodity 1 in the searched commodities is obtained, where the similar item list includes, for example, the commodities 1-1, 1-2, 1-3, 1-4, etc., and based on the similar commodity list, similar commodity entries are added to the commodity list, and list items of the commodities in the similar commodity list are provided under the similar commodity entries for the user to quickly select.

For any application scenario of the similar identification method in this embodiment, the method for identifying similar objects may be implemented on line in each event that needs to be performed by the similar identification method, and hereinafter, the method for identifying similar objects, the method for identifying similar goods, and the like will be collectively referred to as the similar identification method.

For any application scenario of the similar identification method of this embodiment, in the background, similar identification may be performed on all objects in the object library, for example, on all commodities in the commodity library, according to the similar identification method of this embodiment in advance, so as to generate a similar list of each object in the object library, and then, when the above event occurs, the similar list of the target object in the object library may be searched, so as to obtain and output the similar list of the target object in the corresponding event. For example, if the set of objects to be identified in the corresponding event includes the objects 1 to 4, for each of the objects 1 to 4, it may be found whether there is a corresponding object in a previously obtained similarity list of the target object in the object library, and if there is a corresponding object, it indicates that the similarity list of the target object in the corresponding event includes the corresponding object.

< hardware configuration >

Fig. 2 shows a schematic block diagram of a hardware structure of an electronic device that can be used to perform the similar identification method of any embodiment of the present invention.

As shown in fig. 2, the electronic device 1000 may be any type of terminal device, and may also be any type of server, including a cloud server, a server cluster, and the like, which is not limited herein.

The terminal device may be a portable computer, a desktop computer, a mobile phone, a tablet computer, and the like, which is not limited herein.

As shown in fig. 2, the electronic device 1000 may include a processor 1100, a memory 1200, an interface device 1300, a communication device 1400, a display device 1500, an input device 1600, a speaker 1700, a microphone 1800, and the like, all connected to the processor. Wherein the processor 1100 is adapted to execute computer programs. The computer program may be written in an instruction set of an architecture such as x86, Arm, RISC, MIPS, SSE, etc. The memory 1200 includes, for example, a ROM (read only memory), a RAM (random access memory), a nonvolatile memory such as a hard disk, and the like. The interface device 1300 includes, for example, a USB interface, a headphone interface, and the like. The communication device 1400 is capable of wired or wireless communication, for example, and may specifically include Wifi communication, bluetooth communication, 2G/3G/4G/5G communication, and the like. The display device 1500 is, for example, a liquid crystal display panel. The input device 1600 may include, for example, a touch screen, a keyboard, voice input, somatosensory input, and the like. The speaker 1700 is used to output an audio signal. The microphone 1800 is used to collect audio signals.

As applied to any embodiment of the present invention, the memory 1200 of the electronic device 1000 is configured to store instructions (computer programs) for controlling the processor 1100 to operate so as to perform a similar identification method provided in accordance with any embodiment of the present invention. The skilled person can design the instructions according to the disclosed solution. How the instructions control the operation of the processor is well known in the art and will not be described in detail herein.

It should be understood by those skilled in the art that although a plurality of devices are shown in fig. 1 for the electronic apparatus 1000, the present invention may only relate to some of the devices, for example, the electronic apparatus 1000 only relates to the processor 1100 and the memory 1200, etc.

In further embodiments, the electronic device 1000 may further include a similar identification apparatus according to any embodiment of the present invention, and the respective modules of the similar identification apparatus may be implemented by the processor 1100 of the electronic device 1000 in the above embodiments.

< method embodiment I >

FIG. 3 is a flow diagram of a similar identification method according to one embodiment. In this embodiment, the similar identification method may be implemented by any electronic device, for example, the electronic device 1000 in fig. 1, where the electronic device may be a terminal device or a server.

As shown in fig. 3, the similar identification method of the present embodiment may include the following steps S3100 to S3300:

step S3100, a target object and a set of objects to be recognized corresponding to the target object are acquired.

In this embodiment, the object may be any entity, for example, an article such as a commodity, any object, a face image, and the like, which is not limited herein.

In this embodiment, objects similar to the target object need to be identified in the object set to be identified, and a similar object list of the target object is further obtained, that is, the similar object list includes objects similar to the target object.

In one embodiment, the method is applied to any scenario in which, among a selected plurality of objects, other objects similar to any of them are identified, for example, to a logistics distribution scenario as shown in fig. 1 a.

In this embodiment, the acquiring the target object and the object set to be recognized corresponding to the target object in step S3100 may include: and responding to the selection operation of the plurality of objects, selecting any object from the plurality of selected objects as the target object, and selecting other objects to form an object set to be identified corresponding to the target object.

In one embodiment, the method may also be applied to any scenario in which, for a selected one of the objects, other objects similar to the object are identified, for example, to a merchandise push scenario as shown in fig. 1b, or the like.

In this embodiment, the acquiring the target object and the object set to be recognized corresponding to the target object in step S3100 may include: and responding to the selection operation of any object in the object list, selecting the selected object as a target object, and selecting other objects in the object list to form an object set corresponding to the target object.

In this embodiment, the object list is used to show the list items of the objects queried according to the search condition input by the user, that is, the object list contains the list items of the respective objects queried according to the search condition. The list item can contain basic information of the corresponding object and the like, and the detailed interface of the corresponding object can be accessed by clicking the list item.

Step S3200, performing similar recognition on the target object in the object set through each of the at least two recognition models, to obtain similar object lists recognized by each recognition model.

In this embodiment, two different recognition models or more than two different recognition models may be set.

The recognition model may be any model capable of performing similar recognition.

The recognition model may include two parts, one being a feature extraction model and the other being a similarity calculation model. The feature extraction model is used for extracting a vector value of an arbitrary object with respect to a set feature vector, so as to represent the corresponding object by the vector value, wherein the feature vector can be one-dimensional, namely, composed of one feature, or multi-dimensional, namely, composed of a plurality of features, and the vector value is composed of the feature value of the arbitrary object with respect to each feature. For example, if the feature vector includes 15 features, the vector value of the feature vector of an arbitrary object includes 15 feature values.

The similarity calculation model is used for calculating a similarity index value representing the similarity degree between the two objects according to the vector values of the two objects, wherein the similarity index value is a distance value representing the distance between the two vector values, and the similarity index value is larger to indicate that the two objects are more similar.

The feature extraction model may be based on any deep learning model. The similarity index value calculated by the similarity calculation model may be, for example, an euclidean distance value, a manhattan distance value, a minuscule distance value, a cosine distance value, a pearson correlation coefficient, and the like, which is not limited herein.

For the two recognition models, as long as any one of the feature extraction model and the similarity calculation model is different, the two recognition models are different recognition models.

The at least two recognition models in this embodiment may include at least one of a siernese model, a DeepRanking model, and an inclusion model, for example.

According to step S3200, an object similar to the target object may be screened out from the object set through each of the at least two recognition models, and a similar object list recognized by each of the at least two recognition models is further obtained, that is, the similar object list includes objects similar to the target object screened out from the object set by the corresponding recognition model.

Still taking the scenario of fig. 1 as an example, for the example of three recognition models M1, M2, M3 being set, according to step S3200, a similar object list recognized by the recognition model M1, a similar object list recognized by the recognition model M2, and a similar object list recognized by the recognition model M3 will be obtained.

In this example, since the three recognition models M1, M2, and M3 are different in at least one of feature extraction and similarity calculation, there is a high possibility that there is a difference in the objects included in the similar object lists recognized by the respective recognition models.

In one embodiment, for any recognition model, the similarity index value of each object in the object set to the target object is obtained through the recognition model, and the similar object list obtained through the recognition model is obtained according to the high-low ordering of the obtained similarity index values, which is beneficial to obtaining the similar object list obtained through the recognition model with less data processing consumption.

In this embodiment, in step S3200, performing similar recognition on the target object in the object set by using each of at least two recognition models, to obtain a list of similar objects recognized by each recognition model, which may include the following steps S3210 to S3220:

in step S3210, similarity index values between each object in the object set and the target object are obtained through each recognition model.

In step S3210, each recognition model is called to obtain a similarity index value between each object in the object set and the target object.

Continuing with fig. 1 as an example, in the step S3210, similarity values between each object in the object set and the target object are obtained through the recognition model M1, that is, one object corresponds to one similarity value obtained through the recognition model M1; obtaining a similarity index value between each object in the object set and the target object through the recognition model M2, namely, one object corresponds to one similarity index value obtained through the recognition model M2; and obtaining the similarity index value between each object in the object set and the target object through the recognition model M3, namely, one object corresponds to one similarity index value obtained through the recognition model M3.

In step S3210, obtaining a similarity index value between each object in the object set and the target object may include:

in step S3211, vector values of the feature vectors set by the target object for the corresponding recognition models are extracted through the corresponding recognition models, and vector values of each object in the object set for the feature vectors are extracted.

In step S3211, for each recognition model, a feature vector to be extracted by the feature extraction model may be preset.

Different feature vectors may be set for different recognition models, or the same feature vector may be set for different recognition models, which is not limited herein.

The recognition model may extract vector values of feature vectors set by the object for the recognition model from object data. The object data includes at least one of an object image and character information describing the object.

In step S3212, for each object in the object set, a distance value between the vector value of the corresponding object and the vector value of the target object is obtained through the corresponding recognition model, and the distance value is used as a similarity index value between the corresponding object and the target object.

Through the steps S3211 and S3212, similarity index values between each object in the object set and the target object can be obtained through each recognition model, so as to obtain a similar object list recognized by the corresponding recognition model according to the high-low ordering of the similarity index values.

S3220, for each recognition model, according to the similarity index value obtained by the corresponding recognition model, obtaining a similar object list recognized by the corresponding recognition model.

In this embodiment, for each recognition model, a set number k of objects with the highest similarity index value may be selected from the object set according to the high-low order of the similarity index values obtained through the corresponding recognition model, so as to form a list of similar objects recognized by the corresponding recognition model.

The different recognition models may correspond to the same set number k or different set numbers k, and are not limited herein.

Continuing to refer to fig. 1, for example, if the set number k of each recognition model is set to be 5, and the set object set includes 30 objects, the similarity index value of each object in the 30 objects to the target object is obtained through the recognition model M1, and the 5 objects with the highest similarity index values are selected from the 30 objects, so as to form a similar object list recognized by the recognition model M1; obtaining similarity index values of each object in the 30 objects for the target object through the recognition model M2, and selecting 5 objects with the highest similarity index values from the 30 objects to form a similar object list recognized by the recognition model M2; and the recognition model M3 obtains the similarity index value of each object in the 30 objects for the target object, and selects 5 objects with the highest similarity index values from the 30 objects to form a similar object list recognized by the recognition model M3.

In one embodiment, the set number k corresponding to each recognition model may be a preset fixed value.

Since the number of similar objects in the object set is different for different target objects, the set fixed number k may obtain a more accurate recognition result for some target objects, and for other target objects, a problem that a finally obtained similar object list includes dissimilar objects or the similar objects in the similar object list are not complete may occur.

Step S3300, obtaining a similar object list of the target object according to the similar object list respectively identified by all the identification models.

In step S3300, a similarity score of each object in each similar object list may be obtained according to the appearance of each object in each similar object list, and whether the corresponding object can be listed in the final similar object list as an object similar to the target object is determined according to the similarity score.

Therefore, in one embodiment, the step S3300 of obtaining the similar object list of the target object according to the similar object list recognized by all the recognition models respectively may include the following steps S3310 to S3330:

step S3310, for each object in all the similar object lists, according to the appearance of the corresponding object in all the similar object lists, obtaining the similarity score of the corresponding object.

The occurrence may include a frequency of occurrence, and the similarity score may simply be equal to the frequency of occurrence of the corresponding object in each list of similar objects. For example, if an object appears in the list of similar objects identified by two recognition models, the similarity score of the object is equal to 2.

The appearance may also include a similar object list in which the corresponding object appears, and correspondingly, the similarity score may also be determined according to the similar object list in which the corresponding object appears. Since the similar object list where the corresponding object appears has a mapping relationship with the recognition model, different weights can be set for different recognition models, and the similarity score of the corresponding object can be calculated according to the weights. For example, if an object appears in the list of similar objects identified by two identification models, the similarity score of the object will be equal to the sum of the weights of the two identification models, and so on.

Step S3320, according to the similarity score of each object in all the similar object lists, screening out objects similar to the target object from all the similar object lists, and forming a similar object list of the target object.

According to this step, for example, an object whose similarity score is greater than or equal to a set score threshold may be screened out from all similar object lists as an object similar to the target object, thereby forming a similar object list of the target object.

In a case that the similarity score is equal to the occurrence frequency, the score threshold may be determined according to the number of the set recognition models, and the score threshold may be a majority of the recognition models, for example, if three recognition models are set, the score threshold may be set to 2, and if five recognition models are set, the score threshold may be set to 3, and the like, which is not limited herein.

To facilitate setting the scoring threshold, in one embodiment, the at least two recognition models may be set to an odd number of recognition models.

As can be seen from steps S3100 to S3300, in the method of this embodiment, similar recognition is performed on a target object in a range of a corresponding object set on respective channels by at least two recognition models, so as to obtain similar object lists of the target object recognized by each recognition model, respectively, and obtain a similar object list of the target object according to the similar object lists.

In one embodiment, the set number k may be adaptively adjusted according to the situation of the similar object list recognized by each recognition model during the recognition process, so that each recognition model can obtain the similar object list recognized by each recognition model based on the adaptively adjusted set number k.

In this embodiment, as shown in fig. 4, the method for determining the value of the set number k may include the following steps S4100 to S4500:

step S4100, obtaining a current similar object list respectively identified by each identification model according to the current numerical value of the set number k.

In this embodiment, an initial value of the set number k may be preset, and the initial value may be a small value, for example, the initial value is 2 or 3.

In this embodiment, in the first recognition operation performed according to the set number k, the current value is the initial value of the set number k. In the second recognition operation according to the set number k, the current value is equal to the value obtained by increasing the set step size from the initial value.

The set step distance may be determined in consideration of the similarity recognition accuracy and the processing speed, for example, the set step distance is selected to be 1 to preferentially obtain the highest similarity recognition accuracy.

Thus, for example, if the initial value of the set number k is 2, the current value of the set number k is 3 in the second recognition operation, and the current value of the set number is increased by 1 in each subsequent recognition operation.

In step S4200, a list of next similar objects respectively identified by each of the identification models when the set number k is a next number greater than the current number is obtained.

The next value may be a value obtained by increasing the set number k by the set step size based on the current value. In this regard, the step of determining the set number k may further include: and increasing the value of the set number k according to the set step distance on the basis of the current value of the set number k to serve as the next value.

The next value may also be other values greater than the current value, and is not limited herein.

Step S4300, for each recognition model, comparing the corresponding next similar object list with the corresponding current similar object list to obtain a corresponding new added object list.

According to the step S4300, for each recognition model, a new added object list is obtained.

Referring to the example of fig. 1, according to the step S4300, for the recognition model M1, new objects of the next similar object list recognized by the recognition model M1 relative to the current similar object list recognized by the recognition model M1 are obtained, and then a corresponding new object list is obtained; for the recognition model M2, obtaining a new added object of the next similar object list recognized by the recognition model M2 relative to the current similar object list recognized by the recognition model M2, and further obtaining a corresponding new added object list; and for the recognition model M3, obtaining a new added object of the next similar object list recognized by the recognition model M3 relative to the current similar object list recognized by the recognition model M3, and further obtaining a corresponding new added object list. That is, in this example, three new addition object lists will be obtained by step S4300.

In step S4400, when the frequency of occurrence of at least some objects in the current similar object list in all the new added object lists is less than the set first frequency threshold, determining that the current value is the final value of the set number k.

In step S4400, the at least part of the objects may be selected from all the current similarity lists as reference objects.

For example, each object in all current similar object lists can be taken as the reference object.

For another example, all objects satisfying the setting condition in the current similar object list may be set as the reference object.

The set condition is that the occurrence frequency in all the current similar object lists is greater than or equal to a set second frequency threshold value.

The setting condition may be, for example, the same as the score threshold value of the similarity score, and is not limited herein.

After the final value of the set number k is determined, the operation of determining the set number k may be ended, and the similar object lists identified by the plurality of identification models may be further determined according to the final value of the set number k.

The first frequency threshold may be determined in consideration of the similarity recognition accuracy and the processing speed, for example, the first frequency threshold may be 1 in consideration of avoiding missing similar objects as much as possible.

The first frequency threshold may also be determined according to the number of the set recognition models, for example, the frequency threshold may be a majority of the recognition models, and the like, which is not limited herein.

When the first frequency threshold is 1, according to the step S4400, as long as the frequency of occurrence of each reference object in all the new object lists is less than 1, that is, as long as no reference object appears in the new object lists, the final value of the set number k may be determined to be the current value.

In step S4500, in a case that the frequency of occurrence of any one of at least some of the objects (i.e., the reference objects) in the list of all the newly added objects is greater than or equal to the first frequency threshold, the current value of the set value is adjusted.

After adjusting the current value of the set value k, it can be determined whether the adjusted current value is the final value of the set value k through the above steps S4100 to S4500 again. The adjustment may be performed according to a set step pitch, or may be performed randomly, which is not limited herein.

The adjusting the current value of the setting value in step S4500 may include: and updating the current value of the set value to be equal to the next value.

If the first frequency threshold is 1, according to step S4500, if any reference object appears in any newly added object list, it means that, if the set value k is the current value, objects similar to the target object are omitted from the similar object list identified by at least one identification model, and the value of the set number k needs to be adjusted.

After step S4500, the process returns to step S4100 and continues to step S4100 until the final value of the set number k of recognition models is determined.

Fig. 5 shows an example of determining the set number k, and in the example of fig. 5, the method sets three recognition models M1, M2, M3 to participate in recognizing similar objects of the target object 15. In this example, the first frequency threshold is set to 1, the second frequency threshold is set to 2, the initial value of the set number k is 3, the step pitch is set to 1, the similarity score is represented by the frequency of occurrence, and the score threshold is set to 2.

As shown in fig. 5, for the target object 15, similarity index values between each object in the object set and the target object 15 are determined by the recognition model M1, and the objects positioned at the top 8 th position in the object set include an object 01, an object 08, an object 05, an object 04, an object 02, an object 18, an object 11, and an object 10, which are arranged from top to bottom according to the similarity index values. For the target object 15, similarity index values between each object in the object set and the target object 15 are determined through the recognition model M2, and the objects positioned at the top 8 bits in the object set comprise an object 01, an object 05, an object 02, an object 08, an object 04, an object 18, an object 07 and an object 12 according to the similarity index values arranged from high to low. The similarity index value between each object in the object set and the target object 15 is determined through the recognition model M3, and the objects positioned at the top 8 bits in the object set comprise an object 01, an object 08, an object 06, an object 04, an object 05, an object 16, an object 14 and an object 13 according to the similarity index value from high to low.

When the set number k is adaptively adjusted to determine a final value of the set number k, a first recognition operation is performed, and at this time, a current value of the set number k is an initial value 3. According to step S4100, as shown in fig. 5, the current similar object list obtained and identified by the identification model M1 will include the 3 objects with the highest similarity index values, that is, the object 01, the object 08 and the object 05; obtaining that the current similar object list identified by the identification model M2 includes 3 objects with the highest similarity index values, namely including the object 01, the object 05 and the object 02; and obtaining the object with the highest 3 similarity index values, namely the object 01, the object 08 and the object 06, which is identified by the identification model M3 in the current similar object list.

Then, the set value k is increased by the set step 1, and the next value of the set value k is obtained as 4.

In the case where the set number k is 4, according to step S4200, as shown in fig. 5, the next similar object list identified by the identification model M1 is obtained to include 4 objects with the highest similarity index values, that is, including the object 01, the object 08, the object 05, and the object 04; the next similar object list identified by the identification model M2 is obtained to include 4 objects with the highest similarity index values, namely including the object 01, the object 05, the object 02 and the step 08; and obtaining that the next similar object list identified by the identification model M3 includes the objects with the highest 4 similarity index values, i.e., includes the object 01, the object 08, the object 06, and the object 04.

Continuing with step S4300, the newly added object list including object 04 corresponding to the recognition model M1 may be obtained, the newly added object list including object 08 corresponding to the recognition model M2 may be obtained, and the newly added object list including object 04 corresponding to the recognition model M3 may be obtained.

After each new object list is obtained, all the current similar object lists can be screened

At least some of the objects whose frequency of occurrence is greater than or equal to the set second frequency threshold (2 in this example) are taken as reference objects, and the obtained reference objects include object 01, object 08, and object 05.

After the reference object is obtained, the determination is performed according to step S4400 and step S4500, in this example, since the reference object 8 appears 1 time in each new object list and the requirement of the first frequency threshold is met, the current value of the set value needs to be updated to 4 according to step S4500 to perform the second identification operation.

When the second recognition operation is performed, the current value of the value is set to be 4, and each current similar object list obtained in step S4100 is the next similar object list in the first recognition operation, which is not described herein again.

Then, the set value k is increased by the set step 1, and the next value of the set value k is obtained as 5.

In the case where the set number k is 5, according to step S4200, as shown in fig. 5, the next similar object list identified by the identification model M1 is obtained to include 5 objects with the highest similarity index values, that is, including the object 01, the object 08, the object 05, the object 04, and the object 02; obtaining the next similar object list identified by the identification model M2, which includes 5 objects with the highest similarity index values, that is, including object 01, object 05, object 02, object 08 and object 04; and obtaining the object with the next similar object list identified by the identification model M3, which includes 5 objects with the highest similarity index value, that is, including the object 01, the object 08, the object 06, the object 04, and the object 05.

Continuing with step S4300, the newly added object list including object 02 corresponding to the recognition model M1 may be obtained, the newly added object list including object 04 corresponding to the recognition model M2 may be obtained, and the newly added object list including object 05 corresponding to the recognition model M3 may be obtained.

After each new object list is obtained, all the current similar object lists can be screened for reference objects with the frequency of occurrence greater than or equal to a set second frequency threshold (2 in this example), and the obtained reference objects include object 01, object 08, object 05 and object 04.

After the reference object is obtained, a determination is made according to steps S4400 and S4500, in this example, since the reference object 05 and the reference object 04 appear 1 time in each new object list and the requirement of the first frequency threshold is met, the current value of the set value needs to be updated to be 5 according to step S4500 to perform the third identification operation.

When the third recognition operation is performed, the current value of the value is set to be 5, and each current similar object list obtained in step S4100 is the next similar object list in the second recognition operation, which is not described herein again.

Then, the set value k is increased by the set step 1, and the next value of the set value k is obtained as 6.

In the case where the set number k is 5, according to step S4200, as shown in fig. 5, the next similar object list identified by the identification model M1 is obtained to include the 6 objects with the highest similarity index values, that is, the object 01, the object 08, the object 05, the object 04, the object 02, and the object 18; obtaining the next similar object list identified by the identification model M2, which includes the 6 objects with the highest similarity index values, that is, including the object 01, the object 05, the object 02, the object 08, the object 04, and the object 18; and obtaining the object with the next similar object list identified by the identification model M3, which includes 5 objects with the highest similarity index value, that is, including the object 01, the object 08, the object 06, the object 04, the object 05 and the object 14.

Continuing with step S4300, the newly added object list including object 18 corresponding to the recognition model M1 may be obtained, the newly added object list including object 18 corresponding to the recognition model M2 may be obtained, and the newly added object list including object 16 corresponding to the recognition model M3 may be obtained.

After obtaining each of the additional object lists, reference objects including object 01, object 08, object 05, object 04, and object 02 may be obtained.

After the reference object is obtained, a determination is made according to steps S4400 and S4500, and in this example, no reference object appears in the new object list, so that the final value of the set number k can be determined to be the current value 5.

In the case that the final value of the set number k is determined to be 5, the similar object list identified by each identification model in step S3200 is the current similar object list in the third identification operation of determining the set number k. In this example, according to step S3300, a list of similar objects of the target object 15 may be obtained according to the list of similar objects identified by each identification model, and the list may be sorted from high to low according to the similarity score, including object 01, object 08, object 04, object 05, and object 02.

According to the embodiment, after the similarity index value of each object in the object set to the target object is obtained through each recognition model, the setting value is adaptively adjusted through the method of the embodiment, so that the setting value is the most appropriate value for the determined target object and the object set and the determined recognition model, thus when the similarity index value obtained according to each recognition model is screened out from the object set according to the adjusted setting number k and the similar object list of the target object is obtained according to the similar object lists, the finally obtained similar object list can be ensured not to contain objects which are not similar to the target object or not to omit objects which are similar to the target object, and the influence of the setting of each value and the threshold value on the accuracy of the recognition result is reduced to the maximum extent, the accuracy of similar identification is effectively improved.

In one embodiment, the method may further comprise: after the target object is acquired according to step S3100, at least two recognition models matching the object type may be selected from the recognition model set according to the object type of the target object, so as to implement step S3200.

In this embodiment, a recognition model set may be set, where the recognition model set includes a plurality of recognition models, and a mapping table that records recognition models respectively matching different object types is stored in advance, so that, after a target object is determined, a recognition model suitable for performing similar recognition on the target object may be selected according to the object type of the target object and the mapping table.

The object type may be, for example, an object image, a face image, text content, and the like.

In the embodiment, because different recognition models have recognition objects which are good at each other, the embodiment selects a plurality of recognition models matched with the object type of the target object for similar recognition, which is beneficial to improving the accuracy of the recognition result.

In one embodiment, the method may further comprise: after obtaining the similar object list of the target object according to step S3300, the similar object list of the target object may be output.

The outputting the similar object list of the target object comprises at least one of displaying the similar object list, printing the similar object list and sending the similar object list to the target device.

For example, the list of similar objects of the output target object may include: and sending the similar object list of the target object to the terminal equipment bound with the target account, wherein the target account provides an account for distribution service aiming at the target object and the objects in the object set.

The account providing the distribution service is, for example, a work account of a distributor of # 1 distribution box in the column shown in fig. 1 a.

< method example two >

In this embodiment, a similar identification method is also provided, and this embodiment may be applied to the logistics distribution scenario shown in fig. 1 a.

As shown in fig. 6, in this embodiment, the similarity identification method may include the following steps S6100 to S6300:

in step S6100, a product set of products having at least one same distribution feature is obtained.

In step S6100, for example, a product set of products corresponding to the same delivery box and the same delivery time may be acquired, that is, the acquired product set may be simultaneously allocated to the same delivery box and collectively delivered.

Step S6200, for each commodity in the commodity set, performing similar identification on the corresponding commodity in the commodity set through each identification model of the at least two identification models, and obtaining a similar commodity list identified respectively.

In this embodiment, it should be understood that, when performing similar identification in the product set for the corresponding product, similar identification of the corresponding product and the same product in the product set does not need to be performed, that is, other products in the product set except for the corresponding product constitute a product set to be identified for the corresponding product.

And S6300, obtaining a similar commodity list of the corresponding commodity according to the respectively identified similar commodity list.

Therefore, the distributor of the distribution box at the distribution time can acquire the similarity relation of all the commodities in the distribution box according to the similar commodity list, and further distinguish the similar commodities in the distribution process in a focused manner so as to realize accurate distribution.

In one embodiment, the method may further comprise: and sending the obtained similar commodity list to terminal equipment bound with a target account, wherein the target account is a distributor account for providing distribution service for a corresponding distribution box at the corresponding distribution time.

In another embodiment, the similar goods list can be directly printed and pasted on the distribution box, so that a distributor can distinguish the similar goods for use in the distribution process.

In the logistics distribution scenario, in an embodiment, the similar identification method may also include the following steps:

in step S6100', a commodity set of commodities having at least one same distribution feature is obtained.

Step S6200', for each commodity in the commodity set, a similar list of the corresponding commodity in the commodity set is obtained according to a similar commodity list of the corresponding commodity in a commodity library, which is obtained in advance.

In this step, the similar list of the corresponding product in the product collection may be determined by looking up whether there are other products in the product collection in the similar product list of the corresponding product in the product library.

In this embodiment, the obtaining of the similar product list of the corresponding product in the product library in advance may include: performing similar identification in the commodity library aiming at corresponding commodities respectively through each identification model of at least two identification models to obtain a similar commodity list which is respectively identified; and according to the respective identified similar commodity list, obtaining a similar commodity list of the corresponding commodity in the commodity library.

In step S6300', the obtained similar list is provided by the terminal device bound to the target account, where the target account is a distributor account providing distribution service for the commodity set.

In this embodiment, the similar product list of each product in the product library obtained in advance may be stored in the server, and when the distributor needs to acquire the similar product list in the product set constituted by the distributed products in the distribution box, the distributor may transmit the product list of the product set to the server to perform the above steps S6100 'to S6300'. In this regard, in step S6300', the providing of the obtained list of similar lists by the terminal device bound to the target account may include: and sending the obtained similar commodity list to the terminal equipment bound with the target account.

In this embodiment, the steps S6100 to S6300' may be performed by a terminal device, for example, a terminal device bound to the target account. In this regard, the terminal device may obtain, from the server, a similar product list of each product in the product library, which is obtained in advance, to determine the similar product list of each product in the product set, which is not limited herein.

< method example III >

In this embodiment, a similar identification method is also provided, and this embodiment may be applied to the product push scenario shown in fig. 1 b.

As shown in fig. 7, in this embodiment, the similar identification method may include the following steps S7100 to S7400:

step S7100, a commodity selected in the current commodity list is acquired as a target commodity.

The current goods list may be a list of goods which are searched according to a search condition input by a user and meet the search condition, and the goods list includes list items of the searched goods which meet the search condition.

Step S7200, performing similar identification in the current commodity list aiming at the target commodity through each identification model of at least two identification models to obtain the respective identified similar commodity list.

In this embodiment, it should be understood that, when similar identification is performed on a corresponding product in the product list, similar identification of the corresponding product and the same product in the product list does not need to be performed, that is, other products in the product list except for the corresponding product constitute a product set to be identified of the corresponding product.

Step S7300, obtaining a similar product list of the target product according to the respective identified similar product lists.

Step S7400, the similar merchandise list is displayed in the current merchandise list.

The step S7400 may be to add a similar merchandise area displaying similar merchandise in the current merchandise list, and display the list items of the merchandise in the similar merchandise list in the similar merchandise area, as shown in fig. 1 b.

In the commodity pushing scenario, in an embodiment, the similar identification method may also include the following steps:

in step S7100', the product selected in the current product list is acquired as a target product.

Step S7200', according to the similar commodity list of the target commodity in the commodity library, a similar list of the target commodity in the current commodity list is obtained.

In this step, it may be determined whether there are other products in the current product list in the similar product list of the target product in the product library, so as to determine the similar list of the corresponding product in the current product list.

In this embodiment, obtaining the similar product list of the target product in the product library in advance may include: performing similar identification in a commodity library aiming at a target commodity through each identification model of at least two identification models to obtain a similar commodity list which is respectively identified; and obtaining a similar commodity list of the target commodity in the commodity library according to the respectively identified similar commodity list.

Step S7300', the similar merchandise list is displayed in the current merchandise list.

< apparatus embodiment >

In one embodiment, an apparatus for identifying similar objects is also provided, and FIG. 8 illustrates a functional block diagram of the apparatus 8000 in one embodiment.

As shown in fig. 8, the apparatus 8000 may include an object acquisition module 6010, a recognition processing module 8020, and a list generation module 8030.

The object obtaining module 8010 is configured to obtain a target object and a set of objects to be recognized corresponding to the target object.

The identification processing module 8020 is configured to perform similar identification on the target object in the object set through each of the at least two identification models, so as to obtain a list of similar objects identified by each identification model.

The list generating module 8030 obtains a similar object list of the target object according to the respective identified similar object lists.

In an embodiment, the identification processing module 8020, when performing similar identification on the target object in the object set through each of at least two identification models to obtain a list of similar objects respectively identified, may be configured to: respectively obtaining a similarity index value between each object in the object set and the target object through each recognition model; and for each recognition model, obtaining a similar object list recognized by the corresponding recognition model according to the similar index value obtained by the corresponding recognition model.

In an embodiment, the identification processing module 8020, when obtaining the similar object list identified by the corresponding identification model according to the similarity index value obtained by the corresponding identification model, may be configured to: and selecting a set number k of objects with the highest similarity index value from the object set according to the similarity index values obtained by the corresponding recognition models to form a similar object list recognized by the corresponding recognition models.

In one embodiment, the apparatus 8000 may further include a parameter determination module that, when determining the set number k, may be configured to: according to the current numerical value of the set number k, obtaining a current similar object list respectively identified by each identification model; increasing the value of the set number k according to the set step pitch to be used as the next value of the set number k; acquiring a next similar object list respectively identified by each identification model when the set number k is the next numerical value; for each recognition model, comparing the corresponding next similar object list with the corresponding current similar object list to obtain a corresponding newly added object list; selecting a reference object from all the current similar object lists; under the condition that the occurrence frequency of each reference object in all the newly-added object lists is smaller than a set first frequency threshold, determining the current numerical value as the final value of the set number k; and updating the current value of the set value to be equal to the next value when the frequency of occurrence of any reference object in all the newly added object lists is greater than or equal to a first frequency threshold.

In one embodiment, the parameter determination module, when selecting the reference object in all the current similar object lists, may be configured to: and selecting the object with the frequency of occurrence greater than or equal to a set second frequency threshold from all the current similar object lists as a reference object.

In one embodiment, the object obtaining module 8010 may be configured to, when obtaining similarity metric values between each object in the object set and the target object: extracting vector values of the target objects for the feature vectors set by the corresponding recognition models through the corresponding recognition models, and extracting vector values of each object in the object set for the feature vectors; and for each object in the object set, obtaining a distance value between the vector value of the corresponding object and the vector value of the target object through the corresponding recognition model as a similarity index value between the corresponding object and the target object.

In an embodiment, the list generating module 8030, when obtaining the similar object list of the target object according to the respectively identified similar object lists, may be configured to: for each object in all the similar object lists, obtaining the similar score of the corresponding object according to the occurrence frequency of the corresponding object in all the similar object lists; and screening out objects similar to the target object from all the similar object lists according to the similarity score of each object in all the similar object lists to form a similar object list of the target object.

In one embodiment, the list generating module 8030, when screening out objects similar to the target object from all similar object lists according to the similarity score of each object in all similar object lists, may be configured to: and screening out the objects with the similarity scores larger than or equal to the set score threshold value from all the similar object lists as the objects similar to the target object.

In one embodiment, the object capturing module 8010, in capturing a target object and a set of objects to be recognized corresponding to the target object, may be configured to: and responding to the selection operation of the plurality of objects, selecting any object from the plurality of selected objects as the target object, and selecting other objects to form an object set to be identified corresponding to the target object.

In one embodiment, the object capturing module 8010, in capturing a target object and a set of objects to be recognized corresponding to the target object, may be configured to: and responding to the selection operation of any object in the object list, selecting the selected object as a target object, and selecting other objects in the object list to form an object set corresponding to the target object.

In one embodiment, the similarity recognition apparatus 8000 may further include an output processing module for outputting the similar object list of the target object provided by the list generating module 8030.

In one embodiment, the output processing module, when outputting the list of similar objects of the target object, may be configured to: and sending the similar object list of the target object to the terminal equipment bound with the target account, wherein the target account provides an account of distribution service for the target object and the objects in the object set.

In one embodiment, the apparatus 8000 may further include a model selection module for selecting at least two recognition models matching the object type from the recognition model set according to the object type of the target object, and providing the selected recognition models to the recognition processing module 8020.

< apparatus embodiment >

In one embodiment, there is also provided an electronic device that may include the apparatus 8000 for identifying similar objects according to any of the embodiments of the present invention.

In another embodiment, the electronic device may further comprise a memory storing a computer program which, when executed by the processor, implements a similar recognition method according to any of the embodiments of the invention, and a processor.

In this embodiment, the modules of the apparatus 8000 for identifying similar objects may be implemented by a processor of an electronic device.

In this embodiment, the electronic device may be, for example, the electronic device 1000 shown in fig. 2. The electronic device may be any terminal device, may also be any server, and is not limited herein.

Embodiments of the present invention further provide a computer-readable medium, on which a computer program is stored, which, when being executed by a processor, implements a similarity identification method according to any of the embodiments of the present invention.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the device and apparatus embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference may be made to some descriptions of the method embodiments for relevant points.

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 present invention may be a system, method and/or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied therewith for causing a processor to implement various aspects of the present invention.

The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.

The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.

The computer program instructions for carrying out operations of the present invention may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present invention are implemented by personalizing an electronic circuit, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA), with state information of computer-readable program instructions, which can execute the computer-readable program instructions.

Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, by software, and by a combination of software and hardware are equivalent.

Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope of the described embodiments. The terms used herein were chosen in order to best explain the principles of the embodiments, the practical application, or technical improvements to the techniques in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the invention is defined by the appended claims.

Claims

1. A method of identifying similar objects, comprising:

2. The method of claim 1, wherein the performing similar recognition in the object set separately for the target object through each of at least two recognition models, and obtaining a list of the respective recognized similar objects comprises:

3. The method according to claim 2, wherein the obtaining of the similar object list identified by the corresponding identification model according to the similarity index value obtained by the corresponding identification model comprises:

4. The method of claim 3, wherein the method further comprises the step of determining the set number k, comprising:

5. The method of claim 4, wherein the step of determining the set number k further comprises the step of selecting the at least some objects, further comprising:

6. The method of claim 4, wherein the step of determining the set number k further comprises:

7. The method of claim 4, wherein said adjusting the current value of the set value comprises:

and updating the current value of the set value to be equal to the next value.

8. The method of claim 2, wherein the obtaining a similarity metric value between each object in the set of objects and the target object comprises:

9. The method of claim 1, wherein said obtaining a list of similar objects for the target object from the respective identified list of similar objects comprises:

10. The method of claim 9, wherein the screening of objects similar to the target object in all of the similar object lists according to the similarity score of each object in all of the similar object lists comprises:

11. The method of claim 1, wherein the obtaining a target object and a set of objects to be identified corresponding to the target object comprises:

12. The method of claim 1, wherein the obtaining a target object and a set of objects to be identified corresponding to the target object comprises:

13. The method of any of claims 1 to 12, wherein the method further comprises:

and outputting a similar object list of the target object.

14. The method of claim 13, wherein the outputting the list of similar objects to the target object comprises:

15. The method of any of claims 1 to 12, wherein the method further comprises:

16. A method of identifying similar merchandise, comprising:

17. The method of claim 16, wherein said obtaining a set of items of merchandise having at least one same delivery characteristic comprises:

18. The method of claim 17, wherein the method further comprises:

19. A method of identifying similar merchandise, comprising:

providing an obtained similar list through a terminal device bound with a target account, wherein the target account is a distributor account for providing distribution service for the commodity set;

20. A method of identifying similar merchandise, comprising:

and displaying the similar commodity list in the current commodity list.

21. A method of identifying similar merchandise, comprising:

displaying the similar commodity list in the current commodity list;

22. An apparatus for identifying similar objects, comprising:

23. An electronic device comprising the apparatus of claim 22; alternatively, the first and second electrodes may be,

the electronic device comprises a memory and a processor;

the memory stores a computer program which, when executed by the processor, performs the method according to any one of claims 1-21.

24. A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program readable for execution by a computer, the computer program being adapted to perform the method according to any one of claims 1-21 when read by the computer.