Commodity publicity picture multi-dimensional element risk information intelligent analysis method and system

Abstract

The invention provides an intelligent analysis method and system for multi-dimensional element risk information of a commodity propaganda picture, and terminal equipment obtains a to-be-detected commodity propaganda picture and to-be-shelved platform and region information, sends a query request message to a server, receives a query response message from the server, and sends the query response message to the server; the query response message comprises risk prompt information, the risk prompt information represents the policy violation risk of the target comprehensive extension semantics of the comprehensive context of the commodity propaganda picture, and the terminal device displays the risk prompt information. Therefore, compared with an existing compliance detection system, semantic recognition and semantic extension can be carried out on the image context and the text context of the commodity propaganda picture in the propaganda information compliance dimension, and more comprehensive and accurate compliance detection risk recognition is carried out according to the extension semantics of the multiple contexts; the comprehensiveness and the accuracy of processing the commodity propaganda picture data by the system are improved, and the use convenience and the scene applicability of the user are improved.

Description

Technical Field

[0001] The present application relates to the field of information processing technology, and in particular to a method and system for intelligently analyzing risk information of multi-dimensional elements in product promotional images. Background Art

[0002] At present, in response to the compliance testing needs of products on e-commerce platforms, third-party compliance testing systems generally conduct appearance testing of products with similar appearance to the products to be listed, or conduct risk testing in the dimension of trademark infringement.

[0003] With regard to compliance monitoring of promotional information in product promotional images, the current compliance detection system is unable to meet relevant functional requirements and cannot satisfy user needs. Summary of the invention

[0004] The present application provides a method and system for intelligent analysis of multi-dimensional risk information of product promotional images. The system of the present application can perform semantic recognition and semantic extension on the image context and text context of product promotional images uploaded by merchant users in the dimension of compliance of promotional information, and perform more comprehensive and accurate compliance detection risk identification based on the extended semantics of multiple contexts, thereby improving the comprehensiveness and accuracy of the system in processing product promotional image data, as well as improving user convenience and scenario applicability.

[0005] In the first aspect, the present application provides a method for intelligently analyzing risk information of multi-dimensional elements of product promotion pictures, which is applied to a terminal device, and the terminal device is communicatively connected to a server, and the method includes: displaying a first interface, the first interface including a first editing area and a second editing area; obtaining the product promotion picture to be detected entered through the first editing area, and obtaining the platform and regional information to be put on the shelf entered through the second editing area, the product promotion picture including at least one graphic object and at least one text object; sending a query request message carrying the product promotion picture and the platform and regional information to be put on the shelf to the server, the query request message is associated with risk warning information, and the risk warning information represents the policy violation risk of the target comprehensive extended semantics of the comprehensive context of the product promotion picture, The comprehensive context represents the comprehensive action context state of the image semantic context and the text semantic context, the target comprehensive extended semantics associates the first extended information of the first original semantics of the target graphic object and the second extended information of the second original semantics of the target text object, the risk warning information includes a first area identifier and a second area identifier, the first area identifier is used to identify the first image area of ​​the target graphic object, the second area identifier is used to identify the second image area of ​​the target text object, the target graphic object is a graphic object in the at least one graphic object, and the target text object is a text object in the at least one text object; receive a query response message from the server, and display the first area identifier and the second area identifier of the risk warning information.

[0006] In a second aspect, the present application provides a product promotional image risk analysis system, comprising a terminal device and a server, wherein the terminal device is used to execute the steps performed by the terminal device in any method in the first aspect; and the server is used to execute the steps performed by the server in any method in the first aspect.

[0007] It can be seen that in the embodiment of the present application, after the terminal device obtains the product promotional pictures to be detected and the platform and area information to be listed, it sends a query request message to the server, and then receives a query response message from the server, the query response message includes the first area identifier and the second area identifier of the product promotional pictures where there is a risk of policy violation, and the terminal device displays the first area identifier and the second area identifier. Therefore, compared with the existing compliance detection system, a detection function specifically for the policy compliance of promotional information in promotional pictures is realized, and when realizing this function, the system of the present application can perform semantic recognition and semantic extension on the image context and text context in the compliance dimension of the promotional information for the product promotional pictures uploaded by merchant users, and perform more comprehensive and accurate compliance detection risk identification based on the extended semantics of multiple contexts, thereby improving the comprehensiveness and accuracy of the system in processing product promotional picture data, as well as improving user convenience and scenario applicability. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0009] Figure 1 A schematic diagram of the structure of a product promotion picture risk analysis system provided in an embodiment of the present application; Figure 2 A flowchart of a method for intelligently analyzing risk information of multi-dimensional elements of product promotion pictures provided in an embodiment of the present application; Figure 3 An example display diagram of a first interface including two editing areas provided in an embodiment of the present application; Figure 4 A schematic diagram of a first method for highlighting a region mark provided in an embodiment of the present application; Figure 5 A schematic diagram of a second method for highlighting area identification provided in an embodiment of the present application; Figure 6 A schematic diagram of a third method for highlighting area identification provided in an embodiment of the present application; Figure 7 An example diagram of a first interface including target policy description information provided in an embodiment of the present application; Figure 8 An example display diagram of a first interface including three editing areas provided in an embodiment of the present application; Fig. 9A schematic diagram of the structure of a server provided in an embodiment of the present application. DETAILED DESCRIPTION

[0010] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0011] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0012] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0013] In the embodiments of the present application, "and / or" describes the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B can represent the following three situations: A exists alone; A and B exist at the same time; B exists alone. Among them, A and B can be singular or plural.

[0014] In the embodiment of the present application, the symbol " / " can indicate that the objects associated with each other are in an "or" relationship. In addition, the symbol " / " can also indicate a division sign, that is, performing a division operation. For example, A / B can indicate A divided by B.

[0015] In the embodiments of the present application, "at least one item" or similar expressions refer to any combination of these items, including any combination of single items or plural items, and refer to one or more, and multiple refers to two or more. For example, at least one item of a, b, or c can represent the following seven situations: a, b, c, a and b, a and c, b and c, a, b, and c. Among them, each of a, b, and c can be an element or a set containing one or more elements.

[0016] In the embodiments of the present application, "equal to" can be used in conjunction with greater than, and is applicable to the technical solution adopted when greater than, and can also be used in conjunction with less than, and is applicable to the technical solution adopted when less than. When equal to is used in conjunction with greater than, it is not used in conjunction with less than; when equal to is used in conjunction with less than, it is not used in conjunction with greater than.

[0017] In order to solve the above problems, the present application provides a method and system for intelligent analysis of risk information of multi-dimensional elements of product promotional images. The system of the present application can perform semantic recognition and semantic extension on the image context and text context of the product promotional images uploaded by merchant users in the dimension of compliance of promotional information, and perform more comprehensive and accurate compliance detection risk identification based on the extended semantics of multiple contexts, thereby improving the comprehensiveness and accuracy of the system in processing product promotional image data, as well as improving user convenience and scenario applicability.

[0018] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0019] See also Figure 1 and Figure 2 , Figure 1 A schematic diagram of the structure of a product promotion picture risk analysis system provided in an embodiment of the present application. Figure 2 A flowchart of a method for intelligently analyzing risk information of multi-dimensional elements of product promotional images provided in an embodiment of the present application.

[0020] like Figure 1 As shown, the product promotion picture risk analysis system includes a terminal device 10 and a server 20, and the terminal device 10 and the server 20 are connected to each other in a wired or wireless communication manner.

[0021] The terminal device 10 may specifically include a front-end device applied to the user side and capable of realizing functions such as data collection and data transmission, and may be a user equipment (UE) such as a mobile phone, a smart phone, a laptop, a digital broadcast receiver, a personal digital assistant (PDA), a tablet computer (PAD), a handheld device, a vehicle-mounted device, a wearable device, a computing device or other processing equipment connected to a wireless modem, a mobile station (MS), a mobile terminal, etc. Alternatively, the terminal device 10 may also be a software application that can be run in the above electronic devices. For example, it may be an APP running on a mobile phone.

[0022] The server 20 may specifically include a server that is applied to one side of the network platform and is responsible for data processing in the background, which can realize functions such as data transmission and data processing. It may be a physical server, or a server cluster or distributed system composed of multiple physical servers. In this embodiment, the number of servers is not specifically limited. Alternatively, it may also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0023] The terminal device 10 is Figure 2 The execution subject of the method for intelligently analyzing the risk information of multi-dimensional elements of product promotion pictures shown in the figure comprises the following steps S201 to S204: Step S201: The terminal device displays a first interface, which includes a first editing area and a second editing area.

[0024] Step S202: the terminal device obtains the promotional pictures of the products to be tested entered through the first editing area, and obtains the platform and area information to be put on the shelves entered through the second editing area.

[0025] The product promotion picture includes at least one graphic object and at least one text object.

[0026] For details, see Figure 3 , Figure 3 This is a display example diagram of the first interface provided in the embodiment of the present application, such as Figure 3 As shown, the first interface 3 includes a first editing area 31 and a second editing area 32. The first editing area 31 is used to upload promotional pictures of commodities to be tested, and the second editing area 32 is used to set the platform for listing commodities and its regional information.

[0027] Step S203: the terminal device sends a query request message carrying the product promotion picture and the platform and area information to be listed to the server.

[0028] Among them, after the user uploads the promotional pictures of the products to be tested and sets the platform and regional information to be listed, he clicks the query control in the first interface 3, the terminal device creates a query request message, and sends the query request message to the server. The query request message carries the promotional pictures of the products and the platform and regional information to be listed.

[0029] After receiving the query request message, the server generates risk warning information for the product promotional image. The specific process is as follows: In step a, the server performs image semantic analysis on each graphic object in the at least one graphic object to obtain at least one third original semantic.

[0030] Step b: The server performs text semantic analysis on each text object in the at least one text object to obtain at least one fourth original semantics.

[0031] Step c: the server performs a first concept extension on each third original semantics to obtain at least one third extended information.

[0032] In step d, the server performs a second concept extension on each fourth original semantics to obtain at least one fourth extended information.

[0033] In step e, the server obtains a policy set adapted to the platform and regional information to be listed.

[0034] In step f, the server performs comprehensive semantic expansion on the at least one third extended information and the at least one fourth extended information to obtain at least one reference comprehensive extended semantic.

[0035] In some embodiments, the performing comprehensive semantic expansion on the at least one third extended information and the at least one fourth extended information to obtain at least one reference comprehensive extended semantic includes: Step f1, the server creates an information group from the at least one third extended information and the at least one fourth extended information to obtain a plurality of information groups, each of which includes a single third extended information and a single fourth extended information, and the extended information in any two information groups are not completely the same; Step f2, the server performs semantic relationship analysis on the third extended information and the fourth extended information in each information group to obtain a semantic relationship analysis result, wherein the semantic relationship includes at least one of the following: causal relationship, progressive relationship, transition relationship, purpose relationship, and conditional relationship; Step f3: the server constructs a keyword logical relationship between the third extended information and the fourth extended information according to the semantic relationship analysis result to obtain a reference comprehensive extended semantics of the information group.

[0036] Step g: The server performs compliance detection of the policy set on the at least one reference comprehensive extended semantics to obtain the target comprehensive extended semantics and target policy with high-risk identification results.

[0037] Among them, the target comprehensive extended semantics is a reference comprehensive extended semantics for the risk of policy violation, which is one of at least one reference comprehensive extended semantics. The third extended information associated with the target comprehensive semantics is recorded as the first extended information, and the fourth extended information associated with the target comprehensive semantics is recorded as the second extended information. The original semantics corresponding to the first extended information is recorded as the first original semantics, and the original semantics corresponding to the second extended information is recorded as the second original semantics. The first original semantics corresponds to the target graphic object, and the second original semantics corresponds to the target text object.

[0038] Step h: the server creates the first area identifier and the second area identifier according to the target graphic object and the target text object.

[0039] Among them, the risk warning information includes a first area identifier and a second area identifier, and the risk warning information represents the policy violation risk of the product promotion picture. The first area identifier is used to identify the first image area of ​​the target graphic object, and the second area identifier is used to identify the second image area of ​​the target text object. The target graphic object is a graphic object in at least one graphic object, and the target text object is a text object in at least one text object. In some embodiments, the area identifier can be information such as the relative position and size of the target object in the product promotion picture. The first area identifier is used to identify graphic objects in graphic objects that have policy violation risks, and the second area identifier is used to identify text objects in text objects that have policy violation risks.

[0040] After creating the first area identifier and the second area identifier, the server sends the query response message carrying the first area identifier and the second area identifier to the terminal device.

[0041] For example, see Figure 4The product promotion picture 4 in the product promotion picture includes two graphic objects, namely a hair removal device p1 and a celebrity image p2. The product promotion picture includes a text object, and the text object is the advertising slogan t1 of the hair removal device p1. Among them, the original semantic information of p1 is the hair removal device, the original semantic information of p2 is the exposed neck and shoulders of the female celebrity, and the advertising slogan t1 is suspected of being a sensitive word. The server extends the original semantics according to the above graphic objects and text objects, and obtains the comprehensive extended semantics according to the above extended semantics. The server determines that the above comprehensive extended semantics has a policy violation risk based on the policy collection, and then determines that the celebrity image p2 and the advertising slogan t1 have a violation risk based on the above comprehensive extended semantics, obtains the area identification of the celebrity image p2 and the advertising slogan t1 in the product promotion picture 4, and displays the area identification on the terminal device.

[0042] Step S204: the terminal device receives the query response message from the server and displays the first area identifier and the second area identifier of the risk warning information.

[0043] Specifically, after the server completes the detection of the product promotional image, it generates a query response message, which includes risk warning information, that is, the area identification of the graphic objects and / or text objects that have the risk of policy violation. After receiving the query response message, the terminal device obtains the area identification in the risk warning information and displays the area identification on the display screen.

[0044] In some embodiments, the first area identifier and the second area identifier for displaying the risk warning information include: displaying the product promotion picture in the first display area of ​​the first interface or the second interface; performing a first highlighting process on the first image area indicated by the first area identifier in the product promotion picture; and performing a second highlighting process on the second image area indicated by the second area identifier in the product promotion picture.

[0045] In this embodiment, when the terminal device displays the area identification, it first displays the entire product promotional image in the first display area, and then highlights the image area corresponding to the area identification to clearly show the area where there is a risk of policy violation.

[0046] Among them, the highlighting processing includes but is not limited to bolding and highlighting the boundaries of the area marker, or highlighting the image area of ​​the area marker, or marking it with icons such as arrows, or changing the brightness, color, etc. of other areas except the area marker.

[0047] In some embodiments, the first highlight process and the second highlight process are the same, see Figure 4The product promotion picture uploaded by the user is displayed in the first display area 33, and the first image area S1 corresponding to the first area identifier and the second image area S2 corresponding to the second area identifier in the product promotion picture are fluorescently highlighted.

[0048] In some embodiments, the first highlighting process and the second highlighting process are different; the risk warning information also includes the first extended information of the first original semantics and the second extended information of the second original semantics; the method also includes: displaying the first extended information of the first original semantics in the fourth display area of ​​the first interface or the second interface, and the display state of the fourth display area is the same as the display state presented by the first highlighting process; displaying the second extended information of the second original semantics in the fifth display area of ​​the first interface or the second interface, and the display state of the fifth display area is the same as the display state presented by the second highlighting process.

[0049] The risk warning information also includes first extended information of the first original semantics of the graphic object with policy violation risk, and second extended information of the second original semantics of the text object with policy violation risk. The first extended information is displayed in the fourth display area, and the display state of the fourth display area is the same as the display state presented by the first highlighting process; the second extended information is displayed in the fifth display area, and the display state of the fifth display area is the same as the display state presented by the second highlighting process.

[0050] The same display state presented by the terminal device means that the user's perception is the same. Through the display state, the user can directly determine that there is a corresponding relationship between the two, for example, the colors are the same.

[0051] For example, see Figure 5 , the first extended information of the graphic object is displayed in the fourth display area 34, and the second extended information of the text object is displayed in the fifth display area 35. The first extended information is the same as the highlighted state of the graphic object, and the second extended information is the same as the highlighted state of the text.

[0052] In some embodiments, the first area identifier and the second area identifier for displaying the risk warning information include: displaying the first image area indicated by the first area identifier in the second display area of ​​the first interface or the second interface; and displaying the first image area indicated by the first area identifier in the third display area of ​​the first interface or the second interface.

[0053] In this embodiment, when the terminal device displays the area identification, the image area corresponding to the first area identification is directly displayed in the second display area, and the image area corresponding to the second area identification is directly displayed in the third display area. In this embodiment, it is equivalent to directly cutting out the image area with policy violation risks, and the area with policy violation risks can also be clearly shown.

[0054] For example, see Figure 6 The terminal device obtains the corresponding image area according to the area identifier, and displays the first image area S1 corresponding to the first area identifier in the second display area 36, ​​and displays the second image area S2 corresponding to the second area identifier in the third display area 37.

[0055] It can be seen that in the embodiment of the present application, after the terminal device obtains the product promotional pictures to be detected and the platform and area information to be listed, it sends a query request message to the server, and then receives a query response message from the server, the query response message includes the first area identifier and the second area identifier of the product promotional pictures where there is a risk of policy violation, and the terminal device displays the first area identifier and the second area identifier. Therefore, compared with the existing compliance detection system, a detection function specifically for the policy compliance of promotional information in promotional pictures is realized, and when realizing this function, the system of the present application can perform semantic recognition and semantic extension on the image context and text context in the compliance dimension of the promotional information for the product promotional pictures uploaded by merchant users, and perform more comprehensive and accurate compliance detection risk identification based on the extended semantics of multiple contexts, thereby improving the comprehensiveness and accuracy of the system in processing product promotional picture data, as well as improving user convenience and scenario applicability.

[0056] In some embodiments, the risk warning information also includes description information of the target policy that the target comprehensive extended semantics is suspected of violating; after receiving the query response message from the server, the method also includes: displaying the description information of the target policy in the sixth display area of ​​the first interface or the second interface.

[0057] In this embodiment, the risk warning information also includes description information of the target policy that the target comprehensive semantics is suspected of violating, and the description information of the target policy is displayed in the sixth display area.

[0058] For example, see Figure 7 The first interface 3 also includes a sixth display area 38, which is used to display description information of the target policy suspected of being violated.

[0059] In some embodiments, the first interface also includes a third editing area, the third editing area is associated with an auxiliary description text information set, the auxiliary description text information set includes an auxiliary description text information set of the entered product promotion picture; the auxiliary description text information is associated with the first original semantics and / or the second original semantics.

[0060] Among them, see Figure 8 The first interface also includes a third editing area 39, which is used to write an auxiliary description text information set of the product promotion picture, including but not limited to descriptions of the product's functions, applicable scenarios, etc., such as a product manual. The server can construct the first original semantics of the graphic object and the second original semantics of the text object based on the auxiliary description text information set and the graphic objects and text objects of the product promotion picture, thereby enhancing the accuracy of the original semantic extraction of the product promotion picture.

[0061] The editing operation for the third editing area is an optional operation. In some embodiments, the auxiliary description text information includes a state of an empty set.

[0062] It should be noted that the specific implementation process of this embodiment can refer to the specific implementation process described in the above method embodiment, which will not be described here.

[0063] See also Fig. 9 , Fig. 9 A schematic diagram of the structure of a server provided in an embodiment of the present application, such as Fig. 9 As shown, the server 20 includes a processor 91, a memory 93, a communication interface 92, and one or more programs 931. The one or more programs 931 are stored in the memory 93 and are configured to be executed by the processor 91. The programs include methods for executing the methods described in the above embodiments.

[0064] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method described in the above method embodiments, and the above computer includes an electronic device.

[0065] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0066] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0067] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0068] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0069] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0070] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the above-mentioned methods in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0071] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable memory, which may include a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0072] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for intelligently analyzing multi-dimensional risk information of product promotion pictures, characterized in that: Applied to a terminal device, the terminal device is communicatively connected with a server, and the method comprises: Displaying a first interface, wherein the first interface includes a first editing area and a second editing area; Acquire the product promotion picture to be detected entered through the first editing area, and acquire the platform and area information to be put on the shelf entered through the second editing area, wherein the product promotion picture includes at least one graphic object and at least one text object; Sending a query request message carrying the product promotion picture and the platform and area information to be listed to a server, wherein the query request message is associated with risk warning information, wherein the risk warning information represents the policy violation risk of the target comprehensive extended semantics of the comprehensive context of the product promotion picture, wherein the comprehensive context represents the comprehensive action context state of the image semantic context and the text semantic context, wherein the target comprehensive extended semantics is associated with first extended information of the first original semantics of the target graphic object and second extended information of the second original semantics of the target text object, wherein the risk warning information includes a first area identifier and a second area identifier, wherein the first area identifier is used to identify a first image area of ​​the target graphic object, and the second area identifier is used to identify a second image area of ​​the target text object, wherein the target graphic object is a graphic object among the at least one graphic object, and the target text object is a text object among the at least one text object; A query response message is received from the server, and the first area identifier and the second area identifier of the risk warning information are displayed.

2. The method according to claim 1, characterized in that The first area identifier and the second area identifier for displaying the risk warning information include: Displaying the product promotion picture in the first display area of ​​the first interface or the second interface; Performing a first highlighting process on the first image area indicated by the first area identifier in the product promotion picture; A second highlighting process is performed on the second image area indicated by the second area identifier in the product promotion picture.

3. The method according to claim 1, characterized in that The first area identifier and the second area identifier for displaying the risk warning information include: Displaying the first image area indicated by the first area identifier in a second display area of ​​the first interface or the second interface; The first image area indicated by the first area identifier is displayed in a third display area of ​​the first interface or the second interface.

4. The method according to claim 2, characterized in that: The first highlighting process is different from the second highlighting process; the risk warning information further includes first extended information of the first original semantics and second extended information of the second original semantics; The method further comprises: Displaying the first extended information of the first original semantics in a fourth display area of ​​the first interface or the second interface, wherein the display state of the fourth display area is the same as the display state presented by the first highlighting process; The second extended information of the second original semantics is displayed in a fifth display area of ​​the first interface or the second interface, and the display state of the fifth display area is the same as the display state presented by the second highlighting process.

5. The method according to any one of claims 1 to 4, characterized in that: The risk warning information also includes description information of the target policy that the target comprehensive extended semantics is suspected of violating; after receiving the query response message from the server, the method also includes: The description information of the target policy is displayed in the sixth display area of ​​the first interface or the second interface.

6. The method according to any one of claims 1 to 4, characterized in that: The first interface further includes a third editing area, the third editing area is associated with an auxiliary description text information set, and the auxiliary description text information set includes an auxiliary description text information set of the input product promotion picture; The auxiliary description text information is associated with the first original semantics and / or the second original semantics.

7. The method according to claim 6, characterized in that The auxiliary description text information includes a state of being an empty set.

8. The method according to any one of claims 1 to 4, characterized in that: The risk warning information is used to instruct the server to perform the following operations: Performing image semantic analysis on each of the at least one graphic object to obtain at least one third original semantic; Performing text semantic analysis on each text object in the at least one text object to obtain at least one fourth original semantics; Performing first concept extension on each third original semantics to obtain at least one third extended information; Performing a second concept extension on each fourth original semantics to obtain at least one fourth extended information; Obtain a policy set that is suitable for the platform and region information to be listed; Performing comprehensive semantic expansion on the at least one third extended information and the at least one fourth extended information to obtain at least one reference comprehensive extended semantics; Performing compliance detection of a policy set on the at least one reference integrated extended semantics to obtain the target integrated extended semantics and target policy with a high-risk identification result, wherein the target integrated extended semantics is one of the at least one reference integrated extended semantics, and the target integrated semantics is associated with a first extended information of the at least one third extended information and a second extended information of the at least one fourth extended information, the first extended information corresponds to the first original semantics of the at least one third original semantics, the second extended information corresponds to the second original semantics of the at least one fourth original semantics, the first original semantics corresponds to the target graphic object, and the second original semantics corresponds to the target text object; Creating the first area identifier and the second area identifier according to the target graphic object and the target text object; Sending the query response message carrying the first area identifier and the second area identifier.

9. The method according to claim 8, characterized in that The step of performing comprehensive semantic expansion on the at least one third extended information and the at least one fourth extended information to obtain at least one reference comprehensive extended semantic includes: The at least one third extended information and the at least one fourth extended information are used to create an information group to obtain a plurality of information groups, each of which includes a single third extended information and a single fourth extended information, and the extended information in any two information groups are not completely the same; Performing semantic relationship analysis on the third extended information and the fourth extended information in each information group to obtain a semantic relationship analysis result, wherein the semantic relationship includes at least one of the following: a causal relationship, a progressive relationship, a transition relationship, a purpose relationship, and a conditional relationship; A keyword logical relationship is constructed between the third extended information and the fourth extended information according to the semantic relationship analysis result to obtain a reference comprehensive extended semantics of the information group.

10. A product promotion picture risk analysis system, characterized in that: Including terminal equipment and servers, among which, The terminal device is used to perform the steps performed by the terminal device in any method as claimed in claims 1-9; The server is used to execute the steps executed by the server in any method as claimed in claims 1-9.

Images