An information determination method, an electronic device and a computer readable storage medium

Abstract

Embodiments of the present application disclose a method for determining information, which comprises: obtaining a parameter of a candidate object; wherein the parameter represents attribute information of the candidate object; determining a target object set based on the parameter of the candidate object; wherein objects in the target object set have a correlation relationship based on the parameter; receiving selection information of a participating object for the candidate object, and determining a target parameter based on the selection information; and determining a target object from the target object set based on the target parameter and outputting the target object. Embodiments of the present application also disclose an electronic device and a computer readable storage medium.

Description

TECHNICAL FIELD

[0001] The present application relates to the information determination technology in the computer field, and in particular to an information determination method, an electronic device and a computer readable storage medium. BACKGROUND

[0002] With the rapid development of new forms and new modes such as live streaming e-commerce, the online and offline consumption modes are accelerating the integration, which injects strong impetus into the consumption market. The anchor's targeted recommendation and related product display in the live streaming room can bring the target customers the most intuitive visual experience in a very short time. However, the number of e-commerce products is in the tens of thousands, and the parameters of various products are different, so even professional anchors will make mistakes when remembering related product data. There are problems such as the anchor's inability to answer the potential customers' related questions about the products in the live streaming room in time, the anchor's inability to provide alternative products with inventory in time for the hot products that have been sold out, and the potential loss of orders, thereby affecting the order conversion rate. SUMMARY

[0003] To solve the above technical problems, the embodiments of the present application expect to provide an information determination method, an electronic device and a computer readable storage medium, which solve the problem that the related art cannot provide suitable products for users in time when displaying products in live streaming, thereby causing the loss of orders, and improve the order conversion rate.

[0004] The technical solution of the present application is implemented as follows:

[0005] An information determination method, the method comprising:

[0006] obtaining parameters of a candidate object; wherein the parameters represent attribute information of the candidate object;

[0007] determining a target object set based on the parameters of the candidate object; wherein the objects in the target object set have an association relationship based on the parameters;

[0008] receiving selection information of a participating object for the candidate object, and determining a target parameter based on the selection information;

[0009] determining a target object from the target object set based on the target parameter and outputting.

[0010] In the above solution, the obtaining parameters of the candidate object comprises:

[0011] determining initial first type information and initial second type information of the candidate object;

[0012] screening and format processing the initial first type information and the initial second type information of the candidate object, to obtain first type information and second type information of the candidate object; wherein the first type information represents attribute information of the candidate object; the second type information at least includes identification information and information representing performance of the candidate object; the parameters include the first type information and the second type information.

[0013] In the above scheme, the target object set is determined based on the parameters of the candidate object, comprising:

[0014] A plurality of first nodes are constructed, and the parameter corresponding to each first node is determined as the first type information; wherein each first node corresponds to a first type information;

[0015] A plurality of second nodes are constructed, and the parameter corresponding to each second node is determined as the second type information;

[0016] Based on the matching relationship between the candidate object corresponding to the second type information and the first type information of the candidate object, the association relationship between the second node and the first node is set;

[0017] Based on the plurality of first nodes, the plurality of second nodes and the association relationship, the target graph model is determined; wherein the target object set includes the target graph model.

[0018] In the above scheme, the selection information of the participating object for the candidate object is received, and the target parameter is determined based on the selection information, comprising:

[0019] In the case of outputting the video information of the first participating object to the electronic device, the voice information of the first participating object is collected and the semantic information is obtained by performing semantic recognition on the voice information; wherein the video information is the explanation information of the candidate object;

[0020] The semantic information is analyzed to obtain a first target parameter;

[0021] The comment information input by the second participating object for the video information is received, and the second target parameter is obtained by analyzing the comment information; wherein the target parameter includes the first target parameter and the second target parameter.

[0022] In the above scheme, the target object is determined from the target object set based on the target parameter and output, comprising:

[0023] determine a first target node matching the first target parameter and the second target parameter from the plurality of first nodes based on the graph path of the target graph model, and determine a second target node matching the first target parameter and the second target parameter from the plurality of second nodes based on the graph path of the target graph model;

[0024] determine the target object based on the parameters corresponding to the first target node and the second target node and output.

[0025] In the above scheme, the first target node and the second target node are determined from the plurality of first nodes based on the graph path of the target graph model, and the first target node and the second target node are determined from the plurality of second nodes based on the graph path of the target graph model, comprising:

[0026] determine the generation time of the first target parameter and the second target parameter;

[0027] sort the first target parameter and the second target parameter based on the generation time of the first target parameter and the second target parameter to obtain sorted parameters;

[0028] determine a first target node matching the sorted parameters from the plurality of first nodes based on the graph path of the target graph model and the sorted parameters, and determine a second target node matching the sorted parameters from the plurality of second nodes based on the graph path of the target graph model and the sorted parameters.

[0029] In the above scheme, the first target node and the second target node are determined from the plurality of first nodes based on the graph path of the target graph model and the sorted parameters, and the first target node and the second target node are determined from the plurality of second nodes based on the graph path of the target graph model and the sorted parameters, comprising:

[0030] determine a node matching the first sorted parameter from the target graph model based on the graph path of the target graph model, to obtain a first sub-graph model;

[0031] determine a node matching the second sorted parameter from the first sub-graph model based on the graph path of the first sub-graph model, to obtain a second sub-graph model;

[0032] determine a node matching the i-th sorted parameter from the second sub-graph model based on the graph path of the second sub-graph model, until the sorted parameters are all matched, to obtain a target sub-graph model including the first target node and the second target node.

[0033] In the above scheme, the method further comprises:

[0034] In a case where the video information for the first participant object is output to the electronic device and the new object is acquired, first type information and second type information of the new object are determined;

[0035] Based on the relationship between the first type information and the second type information of the new object and the first type information and the second type information in the target graph model, the target graph model is updated.

[0036] An electronic device, comprising a processor, a memory and a communication bus;

[0037] The communication bus is configured to realize communication connection between the processor and the memory;

[0038] The processor is configured to execute an information determination program in the memory to realize the steps of the information determination method described above.

[0039] A computer readable storage medium stores one or more programs, which can be executed by one or more processors to realize the steps of the information determination method described above.

[0040] The information determination method, the electronic device and the computer readable storage medium provided by the embodiments of the present application acquire parameters representing attribute information of a candidate object, determine a target object set based on the parameters of the candidate object, the objects in the target object set have a correlation relationship based on the parameters, receive selection information of a participant object for the candidate object, and determine a target parameter based on the selection information, determine a target object from the target object set based on the target parameter and output the target object. In this way, the target object can be selected from the target object set determined based on the parameters of the candidate object based on the received selection information of the participant object, rather than being determined by the host artificially. The problem that the user cannot be provided with a suitable product in a live product display in the related art, resulting in order loss, is solved, and the order conversion rate is improved. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 A flowchart of an information determination method provided by an embodiment of the present application is provided.

[0042] Figure 2 A flowchart of another information determination method provided by an embodiment of the present application is provided.

[0043] Figure 3 A schematic diagram of a target graph model in an information determination method provided by an embodiment of the present application is provided.

[0044] Figure 4A schematic diagram of another target graph model in an information determination method provided by an embodiment of the present application;

[0045] Figure 5 A schematic diagram of a flow of another information determination method provided by an embodiment of the present application;

[0046] Figure 6 A schematic diagram of a system corresponding to an information determination method provided by an embodiment of the present application;

[0047] Figure 7 A structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0048] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application.

[0049] It should be understood that the "embodiments of the present application" or "the foregoing embodiments" mentioned throughout the specification mean that the specific features, structures or characteristics related to the embodiments are included in at least one embodiment of the present application. Therefore, "in the embodiments of the present application" or "in the foregoing embodiments" appearing throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in any suitable manner in one or more embodiments. In various embodiments of the present application, the size of the serial number of each process does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The serial number of the above-mentioned embodiments of the present application is only for description, not representing the advantages and disadvantages of the embodiments.

[0050] Unless otherwise specified, the electronic device executes any step in the embodiments of the present application, which can be a processor of the electronic device executing the step. It is also worth noting that the embodiments of the present application do not limit the order of the steps executed by the electronic device. In addition, the way of processing data in different embodiments can be the same method or different method. It should be noted that any step in the embodiments of the present application can be independently executed by the electronic device, that is, the electronic device can execute any step in the embodiments below without depending on the execution of other steps.

[0051] It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0052] Embodiments of the present application provide an information determination method, which is applied to an electronic device, as shown in Figure 1 The method comprises the following steps:

[0053] Step 101, obtaining parameters of a candidate object.

[0054] The parameter of the candidate object represents attribute information of the candidate object.

[0055] In the embodiments of the present application, the candidate object can be a plurality of objects from which a target object needs to be selected; in a feasible implementation manner, the candidate object can be a plurality of products to be sold, which can be of the same category or different categories. Moreover, the parameter of the candidate object can be some parameters about attribute information of the candidate object.

[0056] Step 102, determining a target object set based on the parameter of the candidate object.

[0057] The objects in the target object set have a correlation relationship based on the parameter.

[0058] In the embodiments of the present application, the target object set can be classified according to different candidate parameters, and a matching relationship between different categories of candidate parameters is determined, and then a model is constructed based on the different categories of candidate parameters and the matching relationship between the different categories of candidate parameters to obtain a target graph model. It should be noted that the objects in the graph model have a certain correlation relationship based on the relationship between the parameters.

[0059] Step 103, receiving selection information of a participating object for the candidate object, and determining a target parameter based on the selection information.

[0060] In the embodiments of the present application, the participating object can include a plurality of participating objects, and the selection information can be different information about the candidate object input by the plurality of participating objects in different input modes. Moreover, the target parameter can be obtained by analyzing the selection information.

[0061] Step 104, determining a target object from the target object set based on the target parameter and outputting.

[0062] The electronic device can select the target object from the target object set based on the target parameter. It should be noted that the electronic device can select nodes matching a plurality of target parameters determined based on the selection information of different participating objects from the target graph model, and then determine the target object based on the parameters corresponding to the matching nodes.

[0063] The information determination method provided by the embodiments of the present application obtains parameters of a candidate object, the parameters representing attribute information of the candidate object, determines a target object set based on the parameters of the candidate object, the objects in the target object set having a correlation relationship based on the parameters, receives selection information of a participating object for the candidate object, and determines a target parameter based on the selection information, determines a target object from the target object set based on the target parameter, and outputs the target object. In this way, the target object can be selected from the target object set determined based on the parameters of the candidate object based on the selection information of the participating object, instead of being determined by the host artificially. The problem that the user cannot be provided with a suitable product in a live broadcast in the related art, resulting in order loss, is solved, and the order conversion rate is improved.

[0064] Based on the foregoing embodiments, the embodiments of the present application provide an information determination method, as shown in Figure 2 The method comprises the following steps:

[0065] Step 201, determining initial first type information and initial second type information of a candidate object.

[0066] The first type information represents attribute information of the candidate object; and the second type information at least includes identification information and information representing performance of the candidate object.

[0067] In the embodiments of the present application, the first type information can be attribute information representing a belonging side of the candidate object. It should be noted that the first type information can include a brand of the candidate object; the second type information can include identification information of the candidate object and component information of the candidate object; in a feasible implementation manner, the brand can refer to a manufacturer of the candidate object, the identification information can be identification information of the candidate object, and can refer to a name of the candidate object, and the component information can include a central processing unit (CPU), a hard disk, a memory, a network card and other parameters representing performance of the candidate object.

[0068] The initial first type information refers to first type information before processing, and the initial second type information refers to second type information before processing.

[0069] Step 202, performing screening and format processing on the initial first type information and the initial second type information of the candidate object, to obtain first type information and second type information of the candidate object.

[0070] The parameters of the candidate object include the first type information and the second type information.

[0071] In the embodiments of the present application, screening and format processing of the initial first type information and the initial second type information can refer to automatic identification and matching of the initial first type information and the initial second type information in the order of national standards, industry standards and enterprise standards, prompting, manual changing and screening of the initial first type information and the initial second type information that do not match successfully. Then, if the measurement units of the parameters in the components of the selected object are different, the measurement units are uniformly converted to the first matched measurement unit, so as to ensure that the formats of the first type information and the second type information are uniform; at the same time, the name of the selected object in the initial second type information is format processed to ensure the consistency of the name format.

[0072] Step 203, a plurality of first nodes are constructed, and parameters corresponding to each first node are determined as first type information.

[0073] Each first node corresponds to a first type information.

[0074] In the embodiments of the present application, the target graph model finally constructed can be a graph model including a plurality of first nodes and second nodes having an association relationship. The first node can refer to the first type information of the selected object, that is, the first node can be constructed based on the first type information of the selected object.

[0075] Step 204, a plurality of second nodes are constructed, and parameters corresponding to each second node are determined as second type information.

[0076] The second node can refer to the second type information of the selected object, that is, the second node can be constructed based on the second type information of the selected object.

[0077] Step 205, based on the matching relationship between the second type information corresponding to the selected object and the first type information of the selected object, an association relationship between the second node and the first node is set.

[0078] In the embodiments of the present application, the electronic device can determine the matching relationship between the second type information corresponding to the selected object and the first type information of the selected object, and determine the association relationship between the first node and the second node according to the matching relationship

[0079] Step 206, based on the plurality of first nodes, the plurality of second nodes and the association relationship, a target graph model is determined.

[0080] The target object set includes the target graph model. The objects in the target object set have an association relationship based on parameters.

[0081] In the embodiments of the present application, the to-be-selected object is a notebook computer, the first type of information is Lenovo (brand), the identification information in the second type of information is R9000P, and the component information in the second type of information can include at least one of the following: CPU, operating system (OS), battery, graphics card, random access memory (RAM), storage, graphics processing unit (GPU), etc. For example, the CPU is AMD Ryzen 7 5800H, the RAM is 16GB, the storage is 512GB SSD, the GPU is RTX3060, the graphics card is 15.6"WQHD IPS, the battery is 4Cell, and the OS is Windows 10 Home Chinese Edition. As shown in the generated target graph model, Figure 3 The first type of information can be a first node, and the second type of information can be a second node. The first node and the second node can be displayed in the target graph model according to the association relationship determined by the matching relationship, and the second type of information in the target graph model can have an association relationship with the first type of information.

[0082] In another possible implementation, the to-be-selected object also includes another first type of information Lenovo (brand), the identification information in the second type of information is R9000K, and the component information in the second type of information includes CPU, OS, battery, graphics card, RAM, storage, GPU, etc. For example, the CPU is AMD Ryzen 9 5900H, the RAM is 32GB, the storage is 512GB SSD, the GPU is RTX3070, the graphics card is 15.6"WQHD IPS, the battery is 4Cell, and the OS is Windows 10 Home Chinese Edition. As shown in the generated target graph model, Figure 4 Figure 4 The target graph model shown in the target graph model includes the brand Lenovo, the identification information of the two models R9000P and R9000K, and the first type of information and the second type of information of the two models are displayed in the target graph model with a certain association relationship. Figure 4

[0083] Step 207, in the case of outputting the video information of the first participant object to the electronic device, collecting the voice information of the first participant object and performing semantic recognition on the voice information to obtain semantic information.

[0084] The video information is the explanation information of the to-be-selected object.

[0085] ​​In the embodiments of the present application, the first participating object can be an anchor who gives a commentary on the to-be-selected object; in a feasible implementation manner, the video information can be a video generated when the anchor gives a live commentary on the to-be-selected object. The semantic information can be obtained by the electronic device performing semantic recognition on the video of the anchor's commentary on the to-be-selected object.

[0086] In step 208, the electronic device parses the semantic information to obtain a first target parameter.

[0087] The first target parameter can be some parameters about the target object obtained by the electronic device parsing the recognized semantic information.

[0088] In other embodiments of the present application, the first target parameter can also be obtained by acquiring image information or voice information of the commentary of the first participating object on the to-be-selected object, then performing semantic recognition on the image information or voice information, and parsing the obtained semantic information; or the first target parameter can also be obtained by acquiring text information of the commentary of the first participating object on the to-be-selected object, and parsing the text information; of course, the first target parameter can also be obtained based on other formats of information of the commentary of the first participating object on the to-be-selected object.

[0089] In step 209, the electronic device receives comment information input by a second participating object for the video information, and parses the comment information to obtain a second target parameter.

[0090] The target parameters include the first target parameter and the second target parameter.

[0091] In the embodiments of the present application, the second participating object can refer to a user who watches the live broadcast, and the comment information can be information about the target object input by the user who watches the live broadcast when watching the live broadcast video; the second target parameter can be some parameters about the target object obtained by the electronic device parsing the comment information. In a feasible implementation manner, the comment information can be brand or identification information or component information of the target object that the user is interested in.

[0092] In step 210, the electronic device determines, based on a graph path of the target graph model, a first target node matching the first target parameter and the second target parameter from a plurality of first nodes, and a second target node matching the first target parameter and the second target parameter from a plurality of second nodes.

[0093] In the embodiment of the present application, because the first node and the second node respectively refer to different class information of the to-be-selected object, the electronic device can filter out the first target node matching the first target parameter and the second target parameter from the first node and the second target node matching the first target parameter and the second target parameter from the second node based on the graph path of the target graph model.

[0094] In step 211, the electronic device determines the target object based on the parameters corresponding to the first target node and the second target node and outputs.

[0095] In the embodiment of the present application, the electronic device can determine the parameters corresponding to the first target node and the second target node based on the target graph model, and determine the final target object based on the parameters corresponding to the first target node and the second target node.

[0096] It should be noted that the electronic device can be a device corresponding to the first participant object. In a feasible implementation manner, if the first participant object is an anchor who explains the to-be-selected object, the electronic device can be a device used by the anchor for live streaming.

[0097] It should be noted that the same or corresponding steps in the present embodiment and other embodiments can refer to the description in other embodiments, and will not be described here.

[0098] The information determination method provided by the embodiments of the present application can select the target object from the target object set determined based on the parameters of the to-be-selected object based on the received selection information of the participant object, instead of manually determining the product by the anchor, thereby solving the problem that in the related art, the user cannot be provided with a suitable product in time when a product is displayed in live streaming, resulting in order loss, and improving the order conversion rate.

[0099] Based on the foregoing embodiments, the embodiments of the present application provide an information determination method, which refers to Figure 5 The method includes the following steps:

[0100] In step 301, initial first class information and initial second class information of a to-be-selected object are determined.

[0101] The first class information represents attribute information of the to-be-selected object, and the second class information includes at least identification information and information representing performance of the to-be-selected object.

[0102] In step 302, the initial first class information and the initial second class information of the to-be-selected object are filtered and format-processed to obtain first class information and second class information of the to-be-selected object.

[0103] The parameters of the to-be-selected object include first type information and second type information.

[0104] In step 303, a plurality of first nodes are constructed, and a parameter corresponding to each first node is determined as first type information.

[0105] Each first node corresponds to a first type information.

[0106] In the embodiments of the present application, the target graph model finally constructed can be

[0107] In step 304, a plurality of second nodes are constructed, and a parameter corresponding to each second node is determined as second type information.

[0108] In step 305, based on a matching relationship between a to-be-selected object corresponding to the second type information and the first type information of the to-be-selected object, an association relationship between the second node and the first node is set.

[0109] In step 306, based on the plurality of first nodes, the plurality of second nodes and the association relationship, a target graph model is determined.

[0110] The target object set includes the target graph model. The objects in the target object set have an association relationship based on the parameters.

[0111] In step 307, in the case of outputting video information of the first participant object to the electronic device, voice information of the first participant object is collected and semantic information is obtained by performing semantic recognition on the voice information.

[0112] The video information is explanation information of the to-be-selected object.

[0113] In step 308, the semantic information is parsed to obtain a first target parameter.

[0114] In step 309, comment information input by a second participant object for the video information is received, and a second target parameter is obtained by parsing the comment information.

[0115] The target parameter includes the first target parameter and the second target parameter.

[0116] In step 310, the generation time of the first target parameter and the second target parameter is determined.

[0117] In the embodiments of the present application, the generation time of the first target parameter can be the generation time of the semantic information corresponding to the first target parameter, and the generation time of the second target parameter can be the generation time of the comment information corresponding to the second target parameter.

[0118] In step 311, based on the generation time of the first target parameter and the second target parameter, the first target parameter and the second target parameter are sorted to obtain a sorted parameter.

[0119] In the embodiments of the present application, the first target parameter and the second parameter can be mixed and sorted according to the generation time of the first target parameter and the second target parameter; that is, the sorted parameters include the first target parameter and the second target parameter.

[0120] In step 312, based on the graph path of the target graph model and the sorted parameters, a first target node matching the sorted parameters is determined from the plurality of first nodes, and a second target node matching the sorted parameters is determined from the plurality of second nodes.

[0121] In the embodiments of the present application, the electronic device can filter out the first target node matching the sorted first target parameter and the sorted second target parameter from the first nodes based on the graph path of the target graph model, and filter out the second target node matching the sorted first target parameter and the sorted second target parameter from the second nodes.

[0122] It should be noted that step 312, based on the graph path of the target graph model and the sorted parameters, determines a first target node matching the sorted parameters from a plurality of first nodes, and determines a second target node matching the sorted parameters from a plurality of second nodes, which can be implemented in the following way:

[0123] In step 312a, based on the graph path of the target graph model, a node matching the first sorted sorted parameter is determined from the target graph model to obtain a first sub-graph model.

[0124] The first sorted sorted parameter can refer to a parameter in the first target parameter or a parameter in the second target parameter; in a feasible implementation manner, the first sorted sorted parameter can be Storage, and the Storage is 512GB SSD; that is, the nodes included in the first sub-graph model can be nodes in the target graph model matching the parameter of the Storage being 512GB SSD.

[0125] In step 312b, based on the graph path of the first sub-graph model, a node matching the second sorted sorted parameter is determined from the first sub-graph model to obtain a second sub-graph model.

[0126] The second sorted sorted parameter can refer to a parameter in the first target parameter or a parameter in the second target parameter; in a feasible implementation manner, the second sorted sorted parameter can be OS, and the OS is Windows 10; that is, the nodes included in the second sub-graph model can be nodes in the first sub-graph model matching the parameter of the OS being Windows 10.

[0127] Step 312c, based on the graph path of the second sub-graph model, determining the node matching the ranked parameter of the third ranking from the second sub-graph model to obtain a third sub-graph model, and then based on the graph path of the second sub-graph model, determining the node matching the ranked parameter of the fourth ranking from the third sub-graph model, and repeating the above steps in turn until the ranked parameters are all matched.

[0128] In the embodiment of the present application, the electronic device determines the node matching the ranked parameter of the third ranking from the second sub-graph model based on the graph path of the second sub-graph model to obtain a third sub-graph model, and then determines the node matching the ranked parameter of the fourth ranking from the third sub-graph model based on the graph path of the second sub-graph model, and repeats the above steps in turn until the ranked parameters are all matched. At this time, the nodes included in the obtained target sub-graph model are the first target node and the second target node. In a feasible implementation manner, assuming that there are three ranked parameters in total, based on the foregoing description, the ranked parameter of the third ranking can be RAM, and the RAM is 6GB. Then, based on the first target node and the second target node, the target object can be determined as the product with the identification information R9000P. Figure 4 Taking the target graph model shown in the figure as an example, the finally determined target object can be a product with the identification information R9000P.

[0129] Step 313, determining the target object based on the parameters corresponding to the first target node and the second target node and outputting.

[0130] Based on the foregoing embodiment, in other embodiments of the present application, the method can further include the following steps:

[0131] Step 314, in the case that the video information of the first participating object is output to the electronic device and the new object is obtained, determining the first type information and the second type information of the new object.

[0132] Step 315, updating the target graph model based on the relationship between the first type information and the second type information of the new object and the first type information and the second type information in the target graph model.

[0133] In the embodiment of the present application, in the process that the anchor continuously live broadcasts the to-be-selected object, if a new to-be-selected object is obtained, at this time, the electronic device can obtain the first type information and the second type information of the new object according to the method of obtaining the first type information and the second type information of the to-be-selected object. Then, the association relationship between the first type information and the second type information of the new object and the first type information and the second type information in the target graph model is determined, and the first type information and the second type information of the new object are added to the target graph model in the form of the first node and the second node according to the association relationship, so as to update the target graph model. In this way, when a new product is temporarily added before or during the live broadcast, due to the characteristics of the graph model itself, the update is real-time operation, which is almost imperceptible to the anchor who is live broadcasting.

[0134] In addition, the application can reduce the memory burden of the host and the human assistance of other people assisting the host because the target object is determined based on the constructed target graph model. When the graph model is constructed, the requirement for the integrity of the live product parameters is not high, the parameter information of each product does not need to be aligned, and only the main information of the product can provide high-accuracy product information and alternative product prompts through the graph model. The timeliness is very high, which is suitable for the scene of rapid iteration of live goods. The query range and dimension of the alternative product of the sold-out product are larger and more flexible, and the query is faster.

[0135] In other embodiments of the application, the information determination method provided by the application is applied to the product live scene of the first participating object (i.e., the host), and the corresponding system block diagram can be as shown in Figure 6 The host performs live broadcast of the to-be-selected product through the receiving device of the live broadcast room. Meanwhile, the user watching the live broadcast can input text (comment information) through the live broadcast chat box. Then, the first target parameter and the second target parameter are obtained through the analysis of the product semantic recognition and timing component. Next, the related product and the alternative product (target product) are obtained through the matching processing of the graph retrieval and matching component in the target graph model, and then returned to the host. The target graph model can be generated in advance based on the first type of information and the second type of information of the to-be-selected product.

[0136] It should be noted that the descriptions of the same or corresponding steps in this embodiment and other embodiments can refer to the descriptions in other embodiments, which will not be repeated here.

[0137] The information determination method provided by the embodiments of the application can select the target object from the target object set determined based on the parameter of the to-be-selected object based on the received selection information of the participating object, instead of manually determining the product by the host. The problem that the user cannot be provided with a suitable product in a timely manner when the product is displayed in the related art, resulting in order loss, is solved, and the order conversion rate is improved.

[0138] Based on the foregoing embodiments, the embodiments of the application provide an electronic device, which can be applied to the information determination method provided by the embodiments of the application corresponding to Figure 1 , 2 and 5, refer to Figure 7 The electronic device 4 can include a processor 41, a memory 42, and a communication bus 43, where:

[0139] The communication bus 43 is used to realize the communication connection between the processor 41 and the memory 42;

[0140] The processor 41 is configured to execute the information determination program in the memory 42 to realize the following steps:

[0141] acquire a parameter of the candidate object; wherein the parameter represents attribute information of the candidate object;

[0142] determine a target object set based on the parameter of the candidate object; wherein the objects in the target object set have a correlation relationship based on the parameter;

[0143] receive selection information of the participating object for the candidate object, and determine a target parameter based on the selection information;

[0144] determine a target object from the target object set based on the target parameter and output.

[0145] In other embodiments of the present application, the processor 41 is configured to execute the information determination program stored in the memory 42 to acquire the parameter of the candidate object, so as to implement the following steps:

[0146] determine the initial first type information and the initial second type information of the candidate object;

[0147] screen and format process the initial first type information and the initial second type information of the candidate object to obtain the first type information and the second type information of the candidate object;

[0148] wherein, the first type information represents the attribute information of the candidate object; the second type information at least includes identification information and information representing the performance of the candidate object; the parameter includes the first type information and the second type information.

[0149] In other embodiments of the present application, the processor 41 is configured to execute the information determination program stored in the memory 42 to determine the target object set based on the parameter of the candidate object, so as to implement the following steps:

[0150] construct a plurality of first nodes, and determine the parameter corresponding to each first node as the first type information;

[0151] wherein each first node corresponds to a first type information;

[0152] construct a plurality of second nodes, and determine the parameter corresponding to each second node as the second type information;

[0153] based on the matching relationship between the candidate object corresponding to the second type information and the first type information of the candidate object, set the correlation relationship between the second node and the first node;

[0154] determine a target graph model based on the plurality of first nodes, the plurality of second nodes and the correlation relationship;

[0155] wherein the target object set includes the target graph model.

[0156] In other embodiments of the present application, the processor 41 is configured to execute the information determination program stored in the memory 42 to determine selection information of the receiving participant object for the to-be-selected object, and determine a target parameter based on the selection information, to implement the following steps:

[0157] In the case of outputting the video information of the first participant object to the electronic device, the voice information of the first participant object is collected and semantic information is obtained by performing semantic recognition on the voice information;

[0158] The video information is the explanation information of the to-be-selected object.

[0159] The semantic information is analyzed to obtain a first target parameter.

[0160] The comment information input by the second participant object for the video information is received, and a second target parameter is obtained by analyzing the comment information.

[0161] The target parameter includes the first target parameter and the second target parameter.

[0162] In other embodiments of the present application, the processor 41 is configured to execute the information determination program stored in the memory 42 to determine a target object from a target object set based on the target parameter and output, to implement the following steps:

[0163] Based on the graph path of the target graph model, a first target node matching the first target parameter and the second target parameter is determined from a plurality of first nodes, and a second target node matching the first target parameter and the second target parameter is determined from a plurality of second nodes.

[0164] Based on the parameters corresponding to the first target node and the second target node, the target object is determined and output.

[0165] In other embodiments of the present application, the processor 41 is configured to execute the information determination program stored in the memory 42 to determine a target object from a target object set based on the target parameter and output, to implement the following steps:

[0166] The generation time of the first target parameter and the second target parameter is determined.

[0167] Based on the generation time of the first target parameter and the second target parameter, the first target parameter and the second target parameter are sorted to obtain sorted parameters.

[0168] determine a first target node matching the ranked parameters from the plurality of first nodes, and determine a second target node matching the ranked parameters from the plurality of second nodes based on the graph path of the target graph model and the ranked parameters.

[0169] In other embodiments of the present application, the processor 41 is configured to execute the information determination program stored in the memory 42 to determine the graph path of the target graph model and the ranked parameters, determine a first target node matching the ranked parameters from the plurality of first nodes, and determine a second target node matching the ranked parameters from the plurality of second nodes based on the graph path of the target graph model and the ranked parameters, to implement the following steps:

[0170] determine a node matching the first ranked parameter from the target graph model based on the graph path of the target graph model, to obtain a first sub-graph model;

[0171] determine a node matching the second ranked parameter from the first sub-graph model based on the graph path of the first sub-graph model, to obtain a second sub-graph model;

[0172] determine a node matching the i-th ranked parameter from the second sub-graph model based on the graph path of the second sub-graph model, until the ranked parameters are all matched, to obtain a target sub-graph model including the first target node and the second target node.

[0173] In other embodiments of the present application, the processor 41 is configured to execute the information determination program stored in the memory 42, and can also implement the following steps:

[0174] In a case where the video information of the first participant is output to the electronic device and a new object is obtained, determine the first type information and the second type information of the new object;

[0175] update the target graph model based on the relationship between the first type information and the second type information of the new object and the first type information and the second type information in the target graph model.

[0176] It should be noted that the specific implementation process of the steps performed by the processor in this embodiment can refer to the implementation process in the information determination method provided in the corresponding embodiments of Figure 1 、 2 and 5, which will not be described here again.

[0177] The electronic device provided in the embodiments of the present application can select a target object from a target object set determined based on parameters of a to-be-selected object based on the received selection information of the participant object, instead of manually determining the product by the host, thereby solving the problem in the related art that the user cannot be provided with a suitable product in time when a product is displayed in live streaming, and thus the order is lost, and improving the order conversion rate.

[0178] Based on the foregoing embodiments, the embodiments of the present application provide a computer readable storage medium storing one or more programs, which can be executed by one or more processors to implement the method as Figure 1 、 2 The steps of the information determination method provided by the embodiments corresponding to Embodiments 1 to 5 are provided.

[0179] Those skilled in the art will understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage, etc.) containing computer-usable program code.

[0180] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus generate a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks Figure 1 The functions specified in one or more flows and / or blocks

[0181] These computer program instructions can also be stored in a computer-readable memory capable of causing the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including instruction means, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks Figure 1 The functions specified in one or more flows and / or blocks

[0182] These computer program instructions can also be loaded into a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide steps for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks Figure 1 The functions specified in one or more flows and / or blocks

[0183] The above descriptions are merely some example embodiments of the present application, not intended to limit the protective scope of the present application.

Claims

1. An information determination method, the method comprising: When a live streamer showcases a product, parameters of the candidate product are obtained; wherein, the parameters represent the attribute information of the candidate product. A target product set is determined based on the parameters of the candidate products; wherein, the products in the target product set have a correlation relationship based on the parameters; Receive selection information from the host and viewers regarding the candidate products, and determine target parameters based on the selection information; Based on the target parameters, the target product is determined from the target product set and output.

2. The method according to claim 1, wherein obtaining the parameters of the candidate product includes: Determine initial first-class information and initial second-class information for the candidate products; wherein, the initial first-class information represents the brand information of the candidate products; the initial second-class information includes at least identification information and information representing the performance of the candidate products; The initial first type of information and the initial second type of information of the candidate products are filtered and formatted to obtain the first type of information and the second type of information of the candidate products; wherein, the first type of information represents the brand information of the candidate products; the second type of information includes at least identification information and information representing the performance of the candidate products; the parameters include the first type of information and the second type of information.

3. The method according to claim 2, wherein determining the target product set based on the parameters of the candidate products includes: Multiple brand nodes are constructed, and the parameters corresponding to each brand node are determined to be the first type of information; wherein, each brand node corresponds to one type of first information; Construct multiple performance nodes and determine the parameters corresponding to each performance node as the second type of information; Based on the matching relationship between the candidate products corresponding to the second type of information and the first type of information of the candidate products, the association relationship between the brand node and the performance node is set; Based on the multiple brand nodes, the multiple performance nodes, and the relationships, the target graph model is determined; wherein, the target product set includes the target graph model.

4. The method according to claim 3, wherein receiving selection information from the broadcaster and viewers regarding the candidate products, and determining target parameters based on the selection information, comprises: When outputting video information for the broadcaster to an electronic device, text information of the broadcaster's explanation of the candidate product is collected; The text information is parsed to obtain a first target parameter; wherein, the first target parameter is a plurality of parameters related to the target product corresponding to the anchor; The system receives comments input by viewers regarding the video information and parses the comments to obtain a second target parameter; wherein the target parameter includes the first target parameter and the second target parameter; the second target parameter is a plurality of parameters related to the target product corresponding to the viewers.

5. The method according to claim 4, wherein determining and outputting the target product from the target product set based on the target parameter comprises: Based on the graph path of the target graph model, target brand nodes that match the first target parameter and the second target parameter are determined from the plurality of brand nodes, and target performance nodes that match the first target parameter and the second target parameter are determined from the plurality of performance nodes. Based on the first type of information and the second type of information corresponding to the target brand node and the target performance node, the target product is determined from the target product set and output.

6. The method according to claim 5, wherein determining the target brand node matching the first target parameter and the second target parameter from the plurality of brand nodes based on the graph path of the target graph model, and determining the target performance node matching the first target parameter and the second target parameter from the plurality of performance nodes, comprises: Determine the generation time of the first target parameter and the second target parameter; Based on the generation time of the first target parameter and the second target parameter, the first target parameter and the second target parameter are sorted to obtain sorted parameters; wherein, the sorted parameters represent the brand information and performance information of the target product; Based on the graph path of the target graph model and the sorted parameters, a target brand node matching the sorted parameters is determined from the plurality of brand nodes, and a target performance node matching the sorted parameters is determined from the plurality of performance nodes.

7. The method according to claim 6, wherein determining a target brand node matching the sorted parameters from the plurality of brand nodes based on the graph path of the target graph model and the sorted parameters, and determining a target performance node matching the sorted parameters from the plurality of performance nodes, comprises: Based on the graph path of the target graph model, the nodes that match the sorted parameters of the first sorted node and the connection relationship between them are retained in the target graph model to obtain the first sub-graph model. Based on the graph path of the first subgraph model, the nodes that match the sorted parameters of the second sorting and their connection relationships with the nodes that match the sorted parameters of the second sorting are retained in the target graph model to obtain the second subgraph model. Based on the graph path of the second subgraph model, the node that matches the sorted parameters of the i-th sorted node and the connection relationship between them are retained in the target graph model until all sorted parameters are matched, thus obtaining a target subgraph model including the first target node and the second target node.

8. The method according to claim 3, further comprising: When video information for the broadcaster is output to an electronic device and a new product is obtained, the first type of information and the second type of information of the new product are determined. Based on the relationship between the first and second types of information of the newly added product and the first and second types of information in the target graph model, the target graph model is updated.

9. An electronic device, the electronic device comprising: Processor, memory, and communication bus; The communication bus is used to realize the communication connection between the processor and the memory; The processor is used to execute an information determination program in the memory to implement the steps of the information determination method as described in any one of claims 1 to 8.

10. A computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the steps of the information determination method as described in any one of claims 1 to 8.

Images