Label information processing method, device, electronic device and storage medium
By obtaining and predicting the unused target label operation information of the target delivery object and determining the target directional label, the problem of high trial and error cost and low efficiency of directional labels in the information delivery system is solved, and the efficiency and effect of information delivery are improved.
Patent Information
- Application Number
- CN202210312879.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-03-28
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2042-03-28
AI Technical Summary
In the information delivery system, when the delivery object faces a large number of new targeted labels, the trial and error cost is high and the information delivery efficiency is low.
By obtaining the tag operation data of the target delivery object and multiple preset decomposition data, the operation information that does not use the target label is predicted, thereby determining the target directional label, reducing trial and error costs and improving information delivery efficiency.
The prediction of the degree of interest of unused targeted labels based on the target delivery object is achieved, and the targeted targeted labels are determined, which reduces the trial and error cost of information delivery and improves the efficiency and effectiveness of information delivery.
Smart Images

Figure CN114818865B_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of information processing technology, and in particular to a tag information processing method, device, electronic device and storage medium. Background Art
[0002] In the information delivery system, corresponding targeted tags will be created based on the attribute information of the delivered object. The targeted tags can be used as the basis for the targeted information delivery, thereby optimizing the effect of information delivery.
[0003] In related technologies, delivery targets are familiar with frequently used targeted tags. However, as tag information becomes more and more abundant, faced with a large number of new targeted tags, delivery targets need to constantly explore new targeted tags, and the trial and error cost is high, resulting in low information delivery efficiency. Summary of the invention
[0004] The present disclosure provides a tag information processing method, device, electronic device and storage medium to at least solve the problem of high trial and error cost and low information delivery efficiency of the delivery object for new directional tags in the related art. The technical solution of the present disclosure is as follows:
[0005] According to a first aspect of an embodiment of the present disclosure, a tag information processing method is provided, including:
[0006] Acquire tag operation data corresponding to the target delivery object; the tag operation data includes empty elements and non-empty elements, and the non-empty elements represent the historical operation information of the target delivery object on the used directional tags;
[0007] Acquire multiple preset decomposition data corresponding to the tag operation data; the element scale obtained by merging the multiple preset decomposition data is consistent with the element scale of the tag operation data;
[0008] Based on the multiple preset decomposition data and the non-empty elements, predict the operation data corresponding to the empty elements to obtain the operation prediction data corresponding to the empty elements; the operation prediction data represents the operation information of the target delivery object on the unused directional tags corresponding to the empty elements;
[0009] A target orientation tag is determined from the unused orientation tags based on the operational prediction data.
[0010] In an exemplary embodiment, before obtaining the tag operation data corresponding to the target delivery object, the method further includes:
[0011] Acquire a preset directional tag; the preset directional tag includes the used directional tag and the unused directional tag of the target delivery object;
[0012] Determining the non-empty element based on historical operation information of the used directional tags;
[0013] Determining the empty element corresponding to the unused directional tag;
[0014] The tag operation data is generated based on the empty element and the non-empty element.
[0015] In an exemplary embodiment, the used directional tags include a plurality of used directional tags;
[0016] The determining the non-empty element based on the historical operation information of the used directional tag includes:
[0017] Determine the operation amount of each used directional tag by the target delivery object;
[0018] Based on the operation amount, each used directional label is grouped to obtain a plurality of label groups;
[0019] Determine the operation information corresponding to each of the plurality of tag groups; the operation information of the plurality of used directional tags in the same tag group is the same;
[0020] The non-empty element is determined based on the operation information of the used directional tag.
[0021] In an exemplary embodiment, predicting the operation data corresponding to the empty element based on the plurality of preset decomposition data and the non-empty element to obtain the operation prediction data corresponding to the empty element includes:
[0022] Identify multiple decomposition data to be determined;
[0023] Performing information fusion processing on the multiple pieces of decomposition data to be determined to obtain predicted label data;
[0024] Determine element difference information based on the non-empty element and a first corresponding element in the predicted label data corresponding to the non-empty element;
[0025] Based on the element difference information, the plurality of decomposition data to be determined are updated to obtain the plurality of updated decomposition data to be determined;
[0026] When the element difference information is less than or equal to a preset difference threshold, the operation data corresponding to the empty element is predicted based on each element in the multiple target decomposition data to obtain the operation prediction data; the multiple target decomposition data are the multiple decomposition data to be determined when the element difference information is less than or equal to the preset difference threshold.
[0027] In an exemplary embodiment, the step of predicting the operation data corresponding to the empty element based on each element in the multi-objective decomposition data to obtain the operation prediction data includes:
[0028] Multiplying the multiple target decomposition data to obtain target prediction label data;
[0029] The operation prediction data is determined based on a second corresponding element in the target prediction label data that corresponds to the empty element.
[0030] In an exemplary embodiment, the method further comprises:
[0031] Determining conversion information corresponding to the unused targeting tag based on conversion information of delivered information using the unused targeting tag;
[0032] The determining a target directional tag from the unused directional tags based on the operation prediction data comprises:
[0033] Performing information fusion processing on the operation prediction data and the conversion information corresponding to the unused directional tags to obtain a fusion result;
[0034] The target orientation label is determined from the unused orientation labels based on the fusion result.
[0035] In an exemplary embodiment, after determining the target directional tag from the unused directional tags based on the operation prediction data, the method further includes:
[0036] Receive an information delivery request from the target delivery object; the information delivery request includes target delivery information and the target orientation tag;
[0037] The target delivery information is delivered to the target delivery object having the target directional tag.
[0038] According to a second aspect of an embodiment of the present disclosure, there is provided a tag information processing device, including:
[0039] A tag operation data acquisition unit is configured to acquire tag operation data corresponding to a target delivery object; the tag operation data includes empty elements and non-empty elements, and the non-empty elements represent historical operation information of the target delivery object on the used directional tags;
[0040] A preset decomposition data acquisition unit is configured to acquire a plurality of preset decomposition data corresponding to the tag operation data; the element scale obtained by merging the plurality of preset decomposition data is consistent with the element scale of the tag operation data;
[0041] A first prediction unit is configured to predict the operation data corresponding to the empty element based on the multiple preset decomposition data and the non-empty element, and obtain the operation prediction data corresponding to the empty element; the operation prediction data represents the operation information of the target delivery object on the unused directional tag corresponding to the empty element;
[0042] The target orientation label determination unit is configured to determine a target orientation label from the unused orientation labels based on the operation prediction data.
[0043] In an exemplary embodiment, the apparatus further comprises:
[0044] A preset directional tag acquisition unit is configured to acquire a preset directional tag; the preset directional tag includes the used directional tag and the unused directional tag of the target delivery object;
[0045] a non-empty element determining unit, configured to determine the non-empty element based on historical operation information of the used directional tags;
[0046] an empty element determining unit, configured to determine the empty element corresponding to the unused directional tag;
[0047] The tag operation data generating unit is configured to generate the tag operation data based on the empty element and the non-empty element.
[0048] In an exemplary embodiment, the used directional tags include a plurality of used directional tags;
[0049] The non-empty element determination unit comprises:
[0050] An operation amount determination unit, configured to determine the operation amount of the target delivery object for each used directional tag;
[0051] A label grouping unit is configured to perform grouping of each used directional label based on the operation amount to obtain a plurality of label groups;
[0052] An operation information determination unit is configured to determine the operation information corresponding to each of the plurality of tag groups; the operation information of the plurality of used directional tags in the same tag group is the same;
[0053] The first determining unit is configured to determine the non-empty element based on the operation information of the used directional tag.
[0054] In an exemplary embodiment, the first prediction unit includes:
[0055] A second determining unit is configured to determine a plurality of decomposition data to be determined;
[0056] A predicted label data determination unit is configured to perform information fusion processing on the multiple pieces of decomposition data to be determined to obtain predicted label data;
[0057] an element difference information determining unit, configured to determine element difference information based on the non-empty element and a first corresponding element in the predicted label data corresponding to the non-empty element;
[0058] a decomposition data updating unit, configured to update the plurality of decomposition data to be determined based on the element difference information to obtain updated plurality of decomposition data to be determined;
[0059] The operation prediction data determination unit is configured to perform, when the element difference information is less than or equal to a preset difference threshold, prediction of the operation data corresponding to the empty element based on each element in the multiple target decomposition data to obtain the operation prediction data; the multiple target decomposition data are the multiple decomposition data to be determined when the element difference information is less than or equal to the preset difference threshold.
[0060] In an exemplary embodiment, the operation prediction data determination unit includes:
[0061] a target prediction label data determining unit, configured to perform multiplication processing on the multiple target decomposition data to obtain target prediction label data;
[0062] The third determining unit is configured to determine the operation prediction data based on a second corresponding element in the target prediction label data corresponding to the empty element.
[0063] In an exemplary embodiment, the apparatus further comprises:
[0064] A conversion information determination unit is configured to perform conversion information based on the delivered information using the unused directional tag, and determine conversion information corresponding to the unused directional tag;
[0065] The target orientation label determination unit comprises:
[0066] an information fusion unit, configured to perform information fusion processing on the operation prediction data and the conversion information corresponding to the unused directional tags to obtain a fusion result;
[0067] The fourth determining unit is configured to determine the target directional label from the unused directional labels based on the fusion result.
[0068] In an exemplary embodiment, the apparatus further comprises:
[0069] An information delivery request receiving unit is configured to execute receiving an information delivery request of the target delivery object; the information delivery request includes target delivery information and the target orientation tag;
[0070] The information delivery unit is configured to deliver the target delivery information to the target delivery object having the target directional tag.
[0071] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the tag information processing method as described above.
[0072] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of a server, the server is enabled to execute the tag information processing method as described above.
[0073] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, the computer program product comprising a computer program, the computer program being stored in a readable storage medium, at least one processor of a computer device reading and executing the computer program from the readable storage medium, so that the device performs the above-mentioned label information processing method.
[0074] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects:
[0075] The present disclosure obtains the label operation data corresponding to the target delivery object and multiple preset decomposition data corresponding to the label operation data, wherein the label operation data includes empty elements and non-empty elements, and the non-empty elements can characterize the historical operation information of the target delivery object on the used directional tags; then based on the non-empty elements in the label operation data and multiple preset decomposition data, the operation data corresponding to the empty elements are predicted to obtain the operation prediction data corresponding to the empty elements, and the operation prediction data can characterize the operation information of the target delivery object on the unused directional tags corresponding to the empty elements; based on the operation prediction data, the target directional tags are determined from the unused directional tags. Thus, the present disclosure can predict the operation information of the unused directional tags of the target delivery object based on the historical operation information of the used directional tags of the target delivery object, obtain the interest degree of the target delivery object in the unused directional tags, and then determine the target directional tags; the target delivery object delivers information based on the target directional tags, which can reduce the trial and error cost of the target delivery object for delivering information based on the unused directional tags, improve the efficiency of information delivery, and optimize the effect of information delivery.
[0076] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0077] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.
[0078] Figure 1 It is a schematic diagram of an implementation environment according to an exemplary embodiment.
[0079] Figure 2 The figure is a flow chart of a tag information processing method according to an exemplary embodiment.
[0080] Figure 3 The figure is a flow chart of a method for generating tag operation data according to an exemplary embodiment.
[0081] Figure 4 The present invention is a flow chart of a method for determining a non-empty element based on historical operation information of a used directional tag according to an exemplary embodiment.
[0082] Figure 5 The figure is a flow chart of a method for predicting operation data corresponding to a null element according to an exemplary embodiment.
[0083] Figure 6 The present invention is a flow chart of a method for determining operation prediction data according to an exemplary embodiment.
[0084] Figure 7 is a flow chart of another tag information processing method according to an exemplary embodiment.
[0085] Figure 8 The figure is a block diagram of a tag information processing device according to an exemplary embodiment.
[0086] Fig. 9 The figure is a schematic diagram showing the structure of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION
[0087] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.
[0088] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.
[0089] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.
[0090] See also Figure 1 , which shows a schematic diagram of the implementation environment provided by the embodiment of the present disclosure, the implementation environment may include: at least one information delivery request end 110 and an information delivery processing end 120, and the information delivery request end 110 and the information delivery processing end 120 can communicate data through the network.
[0091] Specifically, the information delivery request end 110 may send an information delivery request to the information delivery processing end 120, wherein the information delivery request includes target delivery information and a target orientation tag; the information delivery processing end 120 may deliver the target delivery information to the delivery object having the target orientation tag.
[0092] Furthermore, the information delivery processing end 120 can also push unused directional tags to the delivery object based on the historical operation data of the used directional tags requested by the information delivery end 110, so that the delivery object can formulate a delivery plan based on the pushed directional tags.
[0093] The information delivery request end 110 can communicate with the information delivery processing end 120 based on the browser / server mode (B / S) or the client / server mode (C / S). The information delivery request end 110 may include: physical devices such as smart phones, tablet computers, laptops, digital assistants, smart wearable devices, vehicle terminals, servers, etc., and may also include software running in physical devices, such as applications, etc. The operating system running on the information delivery request end 110 in the embodiment of the present disclosure may include but is not limited to Android system, IOS system, Linux, Windows, etc.
[0094] The information delivery processing end 120 can establish a communication connection with the information delivery request end 110 via wired or wireless communication. The information delivery processing end 120 can include an independently operated server, or a distributed server, or a server cluster composed of multiple servers, wherein the server can be a cloud server.
[0095] In order to solve the problem of high trial and error cost and low information delivery efficiency of the delivery object for new directional tags in the related art, the present disclosure provides a tag information processing method, the execution subject of the method can be the above-mentioned information delivery processing end, please refer to Figure 2 , the method may include:
[0096] S210. Obtain tag operation data corresponding to the target delivery object; the tag operation data includes empty elements and non-empty elements, and the non-empty elements represent the historical operation information of the target delivery object on the used directional tags.
[0097] The delivery object in the embodiment of the present disclosure may be an information delivery initiator, that is, an object having a demand for information delivery; the delivery object may be an information delivery receiver, that is, an object receiving the delivery information.
[0098] Furthermore, the label in the embodiment of the present disclosure may be a directional label in the process of information delivery. The directional label can generally be obtained by mining and extracting the attribute information and behavior information of the delivered object; the directional label can indicate the direction of information delivery. Specifically, when delivering information, a corresponding directional label can be carried. The directional label can be used to deliver the delivered object of the targeted delivery information, that is, the delivered information can be delivered to the delivered object with the directional label.
[0099] The tag operation data can be used to represent the historical operation information of the target delivery object on multiple preset directional tags. For each directional tag, if the target delivery object has used the directional tag, then there is a corresponding non-empty element in the tag operation data, and the non-empty element can represent the historical operation information of the target delivery object on the used directional tag; if the target delivery object has not used the directional tag, then there is a corresponding empty element in the tag operation data. Simply put, the non-empty element corresponds to the used directional tag of the target delivery object, and the empty element corresponds to the unused directional tag of the target delivery object.
[0100] In an optional embodiment, the historical operation information of the target delivery object on the used targeted tags may be operations using the used targeted tags during the information delivery process, specifically operations of the target delivery object formulating a delivery plan based on the used targeted tags, or operations of the target delivery object performing information delivery based on the used targeted tags, etc.
[0101] In another optional embodiment, non-empty elements can be obtained based on the historical operation information of the target delivery object on the used directional tags, and can be specifically determined based on the number of operations of the target delivery object on the used directional tags; accordingly, the higher the number of operations, the larger the element value of the non-empty element; the fewer the number of operations, the smaller the element value of the non-empty element.
[0102] In one example, the tag operation data may specifically be a tag matrix used to characterize the correspondence between the target delivery object and multiple preset directional tags, each row of the tag matrix may be used to characterize the historical operation information of the target delivery object for multiple preset directional tags, and each column may be used to characterize the historical operation information of different target delivery objects for the same preset directional tag. An empty element in the tag matrix may indicate that the target object has not performed an operation on the corresponding preset directional tag.
[0103] In another example, the tag operation data may specifically be a tag list used to characterize the correspondence between the target delivery object and multiple preset directional tags. The tag list may record the correspondence data items between the target delivery object and the preset directional tags, so that the historical operation data of the target delivery object for each preset directional tag can be determined through the tag list.
[0104] In an optional embodiment, the data format of the elements in the label operation data can be a numerical value that can represent the degree of operation, or a field that can represent the degree of operation; when the element is a numerical value that can represent the degree of operation, the corresponding non-empty element can be "10", "5", "1", etc., and the empty element can be "0" or "-1", etc.; when the element is a field that can represent the degree of operation, the corresponding non-empty element can be "high", "medium", "low", etc., and the empty element can be "empty" or "NULL".
[0105] S220. Acquire multiple preset decomposition data corresponding to the tag operation data; the element scale obtained by merging the multiple preset decomposition data is consistent with the element scale of the tag operation data.
[0106] The element data in multiple preset decomposition data can be obtained through random initialization. In terms of data format, the data format of the elements in multiple preset decomposition data is the same as the data format of the elements in the label operation data, so as to facilitate the comparison and analysis of the data obtained after the fusion of multiple preset decomposition data and the label operation data; in terms of element data, each element data in the multiple preset decomposition data may have no association with each element data in the label operation data; the multiple preset decomposition data can be continuously updated subsequently so that the fusion result of the updated multiple decomposition data is close to the label operation data; that is, the label operation data can be represented by the multiple decomposition data; in terms of element scale, the element scale obtained by fusion of multiple preset decomposition data is consistent with the element scale of the label operation data.
[0107] In an example, taking the label operation data as a label matrix, the multiple preset decomposition data can specifically be multiple preset decomposition matrices, and the data format of the elements in the label matrix is the same as the data format of the elements in the multiple preset decomposition matrices, for example, both can be numerical values; the matrix scale of the label matrix is consistent with the matrix scale of the matrix obtained by multiplying the multiple preset decomposition matrices; for example, the scale of the label matrix is M*N, then the matrix scale of the matrix obtained by multiplying the multiple preset decomposition matrices is also M*N.
[0108] In another example, taking the label operation data as a label list, the multiple preset decomposition data can be specifically multiple preset decomposition lists, and the data format of the elements in the label list is the same as the data format of the elements in the multiple preset decomposition lists, for example, both can be numerical values; the list size of the label list is the same as the list size obtained after the multiple preset decomposition lists are merged
[0109] The size of the list is consistent; for example, if the number of elements in the label list is X, then the corresponding multiple preset decomposition lists are merged
[0110] The number of elements in the resulting list is also X.
[0111] In a specific embodiment, the number of items of the preset decomposition data may be greater than or equal to two items. The specific number of items may be determined based on implementation conditions and is not limited here.
[0112] S230. Based on the multiple preset decomposition data and the non-empty elements, the operation data corresponding to the empty elements are predicted to obtain the operation prediction data corresponding to the empty elements; the operation prediction data represents the operation information of the target delivery object on the unused directional tags corresponding to the empty elements.
[0113] In this embodiment, multiple preset decomposition data are decomposition data corresponding to the label operation data. By continuously updating the multiple preset decomposition data, the fusion results of the updated multiple decomposition data can be made infinitely close to the label operation data, that is, the label operation data can be represented by the fusion data of the multiple decomposition data.
[0114] Furthermore, the label operation data includes empty elements and non-empty elements, and the non-empty elements can be used to represent the historical operation information of the target delivery object on the used directional tags; when the elements corresponding to the non-empty elements in the fusion result of the updated multi-decomposition data are infinitely close to the non-empty elements, the elements in the fusion result of the multi-decomposition data can be used to represent the original label operation data; since the fusion result of the multi-decomposition data is obtained through the multi-decomposition data, the multi-decomposition data does not contain empty elements, and the corresponding fusion result of the multi-decomposition data does not contain empty elements, so the operation prediction data corresponding to the corresponding empty element can be determined based on the elements corresponding to the empty elements in the fusion result of the multi-decomposition data; since the preset directional tags corresponding to the empty elements can be directional tags that have not been used by the target delivery object, the determined operation prediction data can represent the operation information of the target delivery object on the unused directional tags corresponding to the empty elements, that is, it can represent the possibility of the target delivery object using the unused directional tags corresponding to the empty elements. The greater the possibility, the higher the interest of the target delivery object in the unused directional tags; otherwise, the lower the interest. Specifically, if the operation prediction data is a numerical value, the larger the operation prediction data is, the greater the possibility that the corresponding target delivery object uses the unused targeting tag corresponding to the empty element; conversely, the smaller the possibility that the target delivery object uses the unused targeting tag corresponding to the empty element.
[0115] In one example, the position information of the elements can be used to determine the elements corresponding to the empty elements and the elements corresponding to the non-empty elements in the fusion result of the multi-decomposition data; for example, when the label operation data and the multi-decomposition data are matrices, the label operation data is matrix A, and the fusion result of the multi-decomposition data is matrix B, then the element a in matrix A is ij and element b in matrix B ij Correspondingly, that is, the element in the i-th row and j-th column of matrix A corresponds to the element in the i-th row and j-th column of matrix B.
[0116] S240. Determine a target directional tag from the unused directional tags based on the operation prediction data.
[0117] Specifically, the target directional tags with a greater possibility of use may be determined based on the operation prediction data corresponding to each unused directional tag.
[0118] In an optional embodiment, an operation data threshold may be pre-set, the operation prediction data corresponding to each empty element is compared with the operation data threshold, and the unused directional tags corresponding to the operation prediction data greater than or equal to the operation data threshold are determined as target directional tags. Specifically, the operation data threshold may be determined based on the historical operation information of the target delivery object on the used directional tags, thereby improving the rationality of the determination of the operation data threshold, and further improving the accuracy of the determination of the target directional tags.
[0119] In another optional embodiment, each unused directional tag can be sorted based on the order of the operation prediction data from large to small, and a preset number of unused directional tags with a higher order can be determined as the target directional tags. The preset number here can be determined based on actual usage. For example, if the number of directional tags currently used by the target delivery object is low, a larger preset number can be set accordingly; if the number of directional tags currently used by the target delivery object is high, a smaller preset number can be set accordingly, thereby achieving flexible setting of the preset number, thereby achieving adaptive determination of the target directional tags and improving the flexibility of determining the target directional tags.
[0120] The present disclosure can predict the operation information of the target delivery object without using the targeted tags based on the historical operation information of the target delivery object on the used targeted tags, obtain the target delivery object's interest level in the unused targeted tags, and then determine the target targeted tags; the target delivery object delivers information based on the target targeted tags, which can reduce the trial and error cost of the target delivery object for information delivery based on the unused targeted tags, improve the efficiency of information delivery, and optimize the effect of information delivery.
[0121] For further information, see Figure 3 , which shows a method for generating label operation data, which may include:
[0122] S310. Obtain a preset directional tag; the preset directional tag includes the used directional tag and the unused directional tag of the target delivery object.
[0123] S320. Determine the non-empty element based on the historical operation information of the used directional tags.
[0124] S330. Determine the empty element corresponding to the unused directional tag.
[0125] S340. Generate the tag operation data based on the empty element and the non-empty element.
[0126] The preset directional tags can be directional tags existing in the information delivery system, specifically including directional tags that have been used by the target delivery object, and unused directional tags; for the used directional tags of the target delivery object, there will be historical operation information for the used directional tags, so that corresponding non-empty elements can be generated based on the historical operation information; for the unused directional tags of the target delivery object, there is no corresponding historical operation information, so the elements corresponding to the unused directional tags are empty elements. Therefore, based on the determined empty elements and non-empty elements, the tag operation data is generated. Based on the historical operation information of the target delivery object for each preset directional tag, each element in the tag operation data is determined, that is, each element can represent the corresponding historical operation information, thereby realizing the expression of historical operation information through elements in the tag operation data, and improving the data representation ability of the tag operation data.
[0127] In an optional embodiment, the preset directional tags may be updated, for example, a new tag may be generated, so that there will be operation information on the new tag, and then the corresponding element information is determined; further, in the process of information delivery, the unused directional tags of the target delivery objects may become used directional tags, so that based on the actual operation information of the corresponding used directional tags, the operation prediction data of the used directional tags can be replaced, thereby ensuring the accuracy of the element data in the tag operation data.
[0128] Specifically, the used directional tags in this embodiment may include multiple used directional tags; accordingly, please refer to Figure 4 , which shows a method for determining a non-empty element based on historical operation information using a directional tag, the method may include:
[0129] S410. Determine the operation amount of the target delivery object for each used directional tag.
[0130] In one example, the amount of operations on the used targeting tag by the target delivery object may specifically be the number of times the used targeting tag is used, such as the number of delivery plans using the used targeting tag, or the number of times information is delivered using the used targeting tag, etc. The higher the amount of operations on the used targeting tag by the target delivery object, the higher the degree of interest of the target delivery object in the used targeting tag.
[0131] S420. Based on the operation amount, group the used directional tags to obtain multiple tag groups.
[0132] By grouping, used directional tags with similar operation amounts can be divided into the same tag group.
[0133] In an optional embodiment, the number of groups m1 can be pre-set, the number of used directional tags can be counted, and then based on the number of used directional tags and the number of groups, the average number of used directional tags in each tag group m2 can be calculated, that is, the number of used directional tags in each tag group is the same. When grouping, the used directional tags are sorted in order from small to large based on the operation amount, and according to the sorting result, the top m2 used directional tags are selected each time and put into the corresponding tag group.
[0134] In another optional embodiment, the minimum operation amount x and the maximum operation amount y can be determined from the operation amounts of each used directional tag, and the number of groups n1 is set in advance. Accordingly, the length of the operation amount interval in each tag group is w = (yx) / n1, and the group boundaries are x+w, x+2w..., x+(n1-1)w; accordingly, the tag group to which each used directional tag belongs can be determined.
[0135] Furthermore, a chi-square binning method may be used to group the used directional tags, which will not be described in detail here.
[0136] S430. Determine the operation information corresponding to each of the plurality of tag groups; the operation information of the plurality of used directional tags in the same tag group is the same.
[0137] The operation information of the label group is adapted to the operation amount of the directional tags used in the label group. The operation information of the label group can specifically be the operation score obtained based on the directional tags used, that is, the higher the operation amount of the directional tags used in the label group, the higher the operation score of the corresponding label group.
[0138] In an optional embodiment, the operation information of each label group is assigned according to the amount of operation of the used directional tags in each label group; for example, there are label group 1, label group 2 and label group 3, wherein the amount of operation of each used directional tag in label group 2 is greater than the amount of operation of each used directional tag in label group 1, and the amount of operation of each used directional tag in label group 3 is greater than the amount of operation of each used directional tag in label group 2, so that the operation score of label group 1 can be assigned to s1, the operation score of label group 2 can be assigned to s2, the operation score of label group 3 can be assigned to s3, and s1 <s2<s3。
[0139] In another optional embodiment, the operation information of the label group can be determined based on the operation amount of the used directional tags in each label group; specifically, the sum of the operation amounts of each used directional tag in each label group can be used as the operation information of the label group, or the average value of the operation amount of each used directional tag in each label group can be used as the operation information of the label group.
[0140] S440. Determine the non-empty element based on the operation information of the used directional tag.
[0141] When the operation information of the used directional tag is determined, an element corresponding to the used directional tag may be determined in the tag operation data, and the value of the element may be assigned as the operation information of the used directional tag.
[0142] Therefore, by grouping the used directional tags with similar operation amounts, and the used directional tags in the same tag group have the same operation information, the consumption of computing resources caused by separately determining different operation information for each used directional tag is avoided, thereby improving the convenience and efficiency of determining the operation information of the directional tag; further, the convenience and efficiency of determining the non-empty elements in the tag operation data can be improved.
[0143] For further information, see Figure 5 , which shows a method for predicting operation data corresponding to a null element, the method may include:
[0144] S510. Determine multiple pieces of decomposition data to be determined.
[0145] When the plurality of decomposition data to be determined is determined for the first time, the plurality of decomposition data to be determined is the plurality of preset decomposition data; and then the decomposition data to be determined is continuously updated through subsequent loop steps.
[0146] S520. Perform information fusion processing on the multiple pieces of decomposition data to be determined to obtain predicted label data.
[0147] Here, the fusion processing of the plurality of decomposition data to be determined may include multiplying the plurality of decomposition data to be determined, or performing multiplication processing after weighting the plurality of decomposition data to be determined.
[0148] S530. Based on the non-empty element and the first corresponding element in the predicted label data corresponding to the non-empty element, determine element difference information; the element difference information is obtained based on the difference between the non-empty element and the first corresponding element.
[0149] In one example, the element scale of the label operation data is consistent with that of the predicted label data, and the first corresponding element corresponding to the non-empty element in the predicted label data can be determined by the position information of the element; when the label operation data and the predicted label data are both matrices, the label operation data is matrix A, and the predicted label data is matrix C, then the element a in matrix A ij and element c in matrix C ij Correspondingly, element c ij That is, with the non-empty element a ijThe corresponding first corresponding element.
[0150] In an alternative embodiment, the non-empty element a ij The first corresponding element c ij The difference is a ij -c ij , so the element difference information can be determined as:
[0151]
[0152] Where N is the number of non-empty elements in the tag operation data.
[0153] In another alternative embodiment, the non-empty element a ij The first corresponding element c ij The difference is a ij -c ij , so the element difference information can be determined as:
[0154]
[0155] Where N is the number of non-empty elements in the tag operation data.
[0156] In another alternative embodiment, the non-empty element a ij The first corresponding element c ij The difference is a ij -c ij , so the element difference information can be determined as:
[0157]
[0158] Where N is the number of non-empty elements in the tag operation data.
[0159] S540. Update the multiple pieces of decomposition data to be determined based on the element difference information to obtain updated pieces of decomposition data to be determined.
[0160] Based on the element difference information, each element in the multiple decomposition data to be determined is adjusted to reduce the element difference information. The decomposition data to be determined can be optimized by the gradient descent method, and specifically, the stochastic gradient descent method or the batch gradient descent method can be used.
[0161] S550. Determine whether the element difference information is less than or equal to a preset difference threshold; if so, execute step S560; if not, execute step S510.
[0162] S560. Based on each element in the multiple target decomposition data, predict the operation data corresponding to the empty element to obtain the operation prediction data; the multiple target decomposition data are the multiple decomposition data to be determined when the element difference information is less than or equal to the preset difference threshold.
[0163] The fusion of multiple target decomposition data can restore the label operation data, so that the empty elements in the label operation data can be predicted by each element in the multiple target decomposition data.
[0164] Therefore, based on the element difference information between the elements in the label operation data and the elements in the predicted label data, multiple items of decomposition data to be confirmed are updated to obtain multiple items of target decomposition data that can characterize the label operation data, thereby improving the efficiency and accuracy of determining the target decomposition data, and further improving the efficiency and accuracy of predicting the operation data corresponding to the empty elements.
[0165] See also Figure 6 , which shows a method for determining operation prediction data, which may include:
[0166] S610. Multiply the multiple target decomposition data to obtain target prediction label data.
[0167] S620. Determine the operation prediction data based on the second corresponding element in the target prediction label data corresponding to the empty element.
[0168] In a specific embodiment, the label operation data is matrix A, and the multi-objective decomposition data is matrix D and matrix E. The matrix A can be represented by the result of multiplying the matrix D and the matrix E, where a 11 It can represent the operation data of the target delivery object 1 on the preset directional tag 1, a 12 It can represent the operation data of the target delivery object 1 on the preset directional tag 2, a 21 It can represent the operation data of the target delivery object 2 on the preset directional tag 1, and so on; as shown in formula (4):
[0169]
[0170] Each element in matrix D and matrix E has a specific element value, and there may be empty elements in matrix A. Then any empty element in matrix A can be calculated by elements in matrix D and matrix E. If a 11 is an empty element, for a 11 The calculation of is shown in formula (5):
[0171] a 11 =d 11 *e 11 +d12 *e 21 +d 13 *e 31 (5)
[0172] Then, the operation prediction data corresponding to each empty element in the matrix A can be obtained.
[0173] The multi-objective decomposition data is determined by continuously narrowing the difference with the label operation data, and the multiplication operation of the multi-objective decomposition data is easy to implement, so that the empty elements in the label operation data are calculated by the elements in the multi-objective decomposition data, which can improve the prediction accuracy and convenience of the operation data corresponding to the empty elements.
[0174] See also Figure 7 , which shows another tag information processing method, which may include:
[0175] S710. Based on the conversion information of the delivered information using the unused targeting tag, determine the conversion information corresponding to the unused targeting tag.
[0176] S720. Perform information fusion processing on the operation prediction data and the conversion information corresponding to the unused directional tags to obtain a fusion result.
[0177] S730. Determine the target orientation label from the unused orientation labels based on the fusion result.
[0178] In an optional embodiment, when the target delivery object is delivering information, a directional tag may be set for the information to be delivered, so that the information to be delivered is delivered to the delivery object with the directional tag. Therefore, for the directional tag not used by the target delivery object 1, other target delivery objects, such as the target delivery object 2 or the target delivery object 3, may have used it, and delivered information based on the directional tag not used by the target delivery object 1. First, the conversion information of the delivered information using the directional tag not used by the target delivery object 1 can be determined, and further the conversion information corresponding to the unused directional tag can be obtained.
[0179] For example, if delivered information 1, delivered information 2, and delivered information 3 all use target delivery object 1 but do not use targeting tag 1, and the corresponding conversion information is z1, z2, and z3, then the conversion information corresponding to not using targeting tag 1 is z1+z2+z3.
[0180] In an optional embodiment, the operation prediction data and the conversion information corresponding to the unused directional tags described above in this embodiment can be weighted to obtain a corresponding fusion result, so that the target directional tag can be determined based on the fusion result. The fusion result can specifically be the weighted value of the operation prediction data and the conversion information, the weighted values corresponding to each unused directional tag are sorted, and K unused directional tags with larger corresponding weights are determined as target directional tags; or unused directional tags with corresponding weights greater than a preset value are determined as target directional tags.
[0181] Therefore, based on the above-mentioned operation prediction data in this embodiment, combined with the conversion information corresponding to the unused targeted tags, the target targeted tags are determined, which can realize the data information characterization of the unused targeted tags from multiple aspects, thereby improving the comprehensiveness of the feature expression of the unused targeted tags; in addition, the conversion information can characterize the usage effect information of the target targeted tags in the actual usage scenarios, thereby improving the delivery effect of information based on the target targeted tags.
[0182] In an optional embodiment, when the target delivery object does not have a used directional tag, the target directional tag can be determined based on the conversion information corresponding to the unused directional tags in the embodiment described above; thereby enabling the target delivery object to deliver information based on the target directional tag. Specifically, the conversion information can be a conversion rate, so that L unused directional tags with larger conversion rates can be determined as target directional tags; or unused directional tags with a conversion rate greater than a preset conversion rate can be determined as target directional tags.
[0183] In another optional embodiment, the target delivery objects can be divided into different industries, such as the e-commerce industry, the game industry, the application promotion industry, etc. The usage of the same directional tag in different industries may be different, so the same directional tag can be processed separately for different industries, and then the target directional tag is determined in the corresponding industry. That is, through industry classification, the push of directional tags in different industries can be realized, thereby improving the accuracy and adaptability of directional tag determination.
[0184] In a specific embodiment, an information delivery request of the target delivery object may be received; the information delivery request includes target delivery information and the target orientation tag; and the target delivery information is delivered to the target delivery object having the target orientation tag. Thus, the target delivery object is able to deliver information based on the pushed target orientation tag, expand the tag delivery range of the target delivery object, reduce the cost of the target delivery object to explore new tags, and improve the information delivery effect.
[0185] Figure 8 is a block diagram of a tag information processing device according to an exemplary embodiment. Figure 8 , the device comprises:
[0186] The tag operation data acquisition unit 810 is configured to acquire tag operation data corresponding to the target delivery object; the tag operation data includes empty elements and non-empty elements, and the non-empty elements represent the historical operation information of the target delivery object on the used directional tags;
[0187] The preset decomposition data acquisition unit 820 is configured to acquire a plurality of preset decomposition data corresponding to the tag operation data; the element scale obtained by merging the plurality of preset decomposition data is consistent with the element scale of the tag operation data;
[0188] The first prediction unit 830 is configured to predict the operation data corresponding to the empty element based on the multiple preset decomposition data and the non-empty element, and obtain the operation prediction data corresponding to the empty element; the operation prediction data represents the operation information of the target delivery object on the unused directional tag corresponding to the empty element;
[0189] The target orientation tag determining unit 840 is configured to determine a target orientation tag from the unused orientation tags based on the operation prediction data.
[0190] In an exemplary embodiment, the apparatus further comprises:
[0191] A preset directional tag acquisition unit is configured to acquire a preset directional tag; the preset directional tag includes the used directional tag and the unused directional tag of the target delivery object;
[0192] a non-empty element determining unit, configured to determine the non-empty element based on historical operation information of the used directional tags;
[0193] an empty element determining unit, configured to determine the empty element corresponding to the unused directional tag;
[0194] The tag operation data generating unit is configured to generate the tag operation data based on the empty element and the non-empty element.
[0195] In an exemplary embodiment, the used directional tags include a plurality of used directional tags;
[0196] The non-empty element determination unit comprises:
[0197] An operation amount determination unit, configured to determine the operation amount of the target delivery object for each used directional tag;
[0198] A label grouping unit is configured to perform grouping of each used directional label based on the operation amount to obtain a plurality of label groups;
[0199] An operation information determination unit is configured to determine the operation information corresponding to each of the plurality of tag groups; the operation information of the plurality of used directional tags in the same tag group is the same;
[0200] The first determining unit is configured to determine the non-empty element based on the operation information of the used directional tag.
[0201] In an exemplary embodiment, the first prediction unit 830 includes:
[0202] A second determining unit is configured to determine a plurality of decomposition data to be determined;
[0203] A predicted label data determination unit is configured to perform information fusion processing on the multiple pieces of decomposition data to be determined to obtain predicted label data;
[0204] an element difference information determining unit, configured to determine element difference information based on the non-empty element and a first corresponding element in the predicted label data corresponding to the non-empty element;
[0205] a decomposition data updating unit, configured to update the plurality of decomposition data to be determined based on the element difference information to obtain updated plurality of decomposition data to be determined;
[0206] The operation prediction data determination unit is configured to perform, when the element difference information is less than or equal to a preset difference threshold, prediction of the operation data corresponding to the empty element based on each element in the multiple target decomposition data to obtain the operation prediction data; the multiple target decomposition data are the multiple decomposition data to be determined when the element difference information is less than or equal to the preset difference threshold.
[0207] In an exemplary embodiment, the operation prediction data determination unit includes:
[0208] a target prediction label data determining unit, configured to perform multiplication processing on the multiple target decomposition data to obtain target prediction label data;
[0209] The third determining unit is configured to determine the operation prediction data based on a second corresponding element in the target prediction label data corresponding to the empty element.
[0210] In an exemplary embodiment, the apparatus further comprises:
[0211] A conversion information determination unit is configured to perform conversion information based on the delivered information using the unused directional tag, and determine conversion information corresponding to the unused directional tag;
[0212] The target orientation label determination unit comprises:
[0213] an information fusion unit, configured to perform information fusion processing on the operation prediction data and the conversion information corresponding to the unused directional tags to obtain a fusion result;
[0214] The fourth determining unit is configured to determine the target directional label from the unused directional labels based on the fusion result.
[0215] In an exemplary embodiment, the apparatus further comprises:
[0216] An information delivery request receiving unit is configured to execute receiving an information delivery request of the target delivery object; the information delivery request includes target delivery information and the target orientation tag;
[0217] The information delivery unit is configured to deliver the target delivery information to the target delivery object having the target directional tag.
[0218] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0219] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided. Optionally, the computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a tape, a floppy disk, an optical data storage device, etc.; when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute any of the methods described above.
[0220] In an exemplary embodiment, a computer program product is also provided, which includes a computer program stored in a readable storage medium, and at least one processor of a computer device reads and executes the computer program from the readable storage medium, so that the device performs any of the above methods.
[0221] Fig. 9 is a block diagram of an electronic device for tag information processing according to an exemplary embodiment. The electronic device may be a server, and its internal structure diagram may be as shown in FIG. Fig. 9As shown. The electronic device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a label information processing method is implemented.
[0222] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present disclosure, and does not constitute a limitation on the electronic device to which the scheme of the present disclosure is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0223] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.
[0224] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims
1. A tag information processing method, characterized in that: include: Obtain the label operation data corresponding to the target delivery object; The tag operation data includes empty elements and non-empty elements, and the non-empty elements represent the historical operation information of the target delivery object on the used directional tags; Acquire multiple preset decomposition data corresponding to the tag operation data; the element scale obtained by merging the multiple preset decomposition data is consistent with the element scale of the tag operation data; Determine a plurality of decomposition data to be determined; when the plurality of decomposition data to be determined is determined for the first time, the plurality of decomposition data to be determined is the plurality of preset decomposition data; Performing information fusion processing on the multiple pieces of decomposition data to be determined to obtain predicted label data; Determine element difference information based on the non-empty element and a first corresponding element in the predicted label data corresponding to the non-empty element; Based on the element difference information, the plurality of decomposition data to be determined are updated to obtain the plurality of updated decomposition data to be determined; In the case where the element difference information is less than or equal to the preset difference threshold, the multiple target decomposition data are multiplied to obtain target prediction label data; based on the second corresponding element corresponding to the empty element in the target prediction label data, the operation prediction data is determined; the multiple target decomposition data are the multiple decomposition data to be determined in the case where the element difference information is less than or equal to the preset difference threshold; the operation prediction data represents the operation information of the target delivery object on the unused directional label corresponding to the empty element; A target orientation tag is determined from the unused orientation tags based on the operational prediction data.
2. The method according to claim 1, characterized in that Before obtaining the label operation data corresponding to the target delivery object, the method further includes: Acquire a preset directional tag; the preset directional tag includes the used directional tag and the unused directional tag of the target delivery object; Determining the non-empty element based on historical operation information of the used directional tags; Determining the empty element corresponding to the unused directional tag; The tag operation data is generated based on the empty element and the non-empty element.
3. The method according to claim 2, characterized in that The used directional tags include a plurality of used directional tags; The determining the non-empty element based on the historical operation information of the used directional tag includes: Determine the operation amount of each used directional tag by the target delivery object; Based on the operation amount, each used directional label is grouped to obtain a plurality of label groups; Determine the operation information corresponding to each of the plurality of tag groups; the operation information of the plurality of used directional tags in the same tag group is the same; The non-empty element is determined based on the operation information of the used directional tag.
4. The method according to claim 1, characterized in that The method further comprises: Determining conversion information corresponding to the unused targeting tag based on conversion information of delivered information using the unused targeting tag; The determining a target directional tag from the unused directional tags based on the operation prediction data comprises: Performing information fusion processing on the operation prediction data and the conversion information corresponding to the unused directional tags to obtain a fusion result; The target orientation label is determined from the unused orientation labels based on the fusion result.
5. The method according to claim 1, characterized in that After determining the target directional tag from the unused directional tags based on the operation prediction data, the method further includes: Receive an information delivery request from the target delivery object; the information delivery request includes target delivery information and the target orientation tag; The target delivery information is delivered to the target delivery object having the target directional tag.
6. A label information processing device, characterized in that: include: A label operation data acquisition unit is configured to acquire label operation data corresponding to a target delivery object; The tag operation data includes empty elements and non-empty elements, and the non-empty elements represent the historical operation information of the target delivery object on the used directional tags; A preset decomposition data acquisition unit is configured to acquire a plurality of preset decomposition data corresponding to the tag operation data; the element scale obtained by merging the plurality of preset decomposition data is consistent with the element scale of the tag operation data; A first prediction unit is configured to predict the operation data corresponding to the empty element based on the multiple preset decomposition data and the non-empty element, so as to obtain the operation prediction data corresponding to the empty element; The operation prediction data represents the operation information of the target delivery object on the unused directional tag corresponding to the empty element; The first prediction unit comprises: A second determining unit is configured to determine a plurality of decomposition data to be determined; when the plurality of decomposition data to be determined is determined for the first time, the plurality of decomposition data to be determined is the plurality of preset decomposition data; A predicted label data determination unit is configured to perform information fusion processing on the multiple pieces of decomposition data to be determined to obtain predicted label data; an element difference information determining unit, configured to determine element difference information based on the non-empty element and a first corresponding element in the predicted label data corresponding to the non-empty element; a decomposition data updating unit, configured to update the plurality of decomposition data to be determined based on the element difference information to obtain updated plurality of decomposition data to be determined; The operation prediction data determination unit is configured to predict the operation data corresponding to the empty element based on each element in the multiple target decomposition data when the element difference information is less than or equal to the preset difference threshold, so as to obtain the operation prediction data; the multiple target decomposition data are multiple decomposition data to be determined when the element difference information is less than or equal to the preset difference threshold; the operation prediction data determination unit includes: a target prediction label data determination unit, configured to perform multiplication processing on the multiple target decomposition data to obtain target prediction label data; a third determination unit, configured to determine the operation prediction data based on the second corresponding element in the target prediction label data corresponding to the empty element; The target orientation label determination unit is configured to determine a target orientation label from the unused orientation labels based on the operation prediction data.
7. The device according to claim 6, characterized in that The device also includes: A preset directional tag acquisition unit is configured to acquire a preset directional tag; the preset directional tag includes the used directional tag and the unused directional tag of the target delivery object; a non-empty element determining unit, configured to determine the non-empty element based on historical operation information of the used directional tags; an empty element determining unit, configured to determine the empty element corresponding to the unused directional tag; The tag operation data generating unit is configured to generate the tag operation data based on the empty element and the non-empty element.
8. The device according to claim 7, characterized in that The used directional tags include a plurality of used directional tags; The non-empty element determination unit comprises: An operation amount determination unit, configured to determine the operation amount of the target delivery object for each used directional tag; A label grouping unit is configured to perform grouping of each used directional label based on the operation amount to obtain a plurality of label groups; An operation information determination unit is configured to determine the operation information corresponding to each of the plurality of tag groups; the operation information of the plurality of used directional tags in the same tag group is the same; The first determining unit is configured to determine the non-empty element based on the operation information of the used directional tag.
9. The device according to claim 6, characterized in that The device also includes: A conversion information determination unit is configured to perform conversion information based on the delivered information using the unused directional tag, and determine conversion information corresponding to the unused directional tag; The target orientation label determination unit comprises: an information fusion unit, configured to perform information fusion processing on the operation prediction data and the conversion information corresponding to the unused directional tags to obtain a fusion result; The fourth determining unit is configured to determine the target directional label from the unused directional labels based on the fusion result.
10. The device according to claim 6, characterized in that The device also includes: An information delivery request receiving unit is configured to execute receiving an information delivery request of the target delivery object; the information delivery request includes target delivery information and the target orientation tag; The information delivery unit is configured to deliver the target delivery information to the target delivery object having the target directional tag.
11. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the tag information processing method according to any one of claims 1 to 5.
12. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the tag information processing method as claimed in any one of claims 1 to 5.
13. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the tag information processing method according to any one of claims 1 to 5 is implemented.
Citation Information
Patent Citations
Multi-source data fusion method and device, computer equipment and storage medium
CN111985578A
Information pushing method, device and equipment and storage medium
CN112070532A
Label recommendation method and device, equipment, storage medium and computer program product
CN112989023A
Advertisement putting effect prediction method and device, computer equipment and storage medium
CN113763035A
Recommended content determination method and device, recommendation method and device, equipment and storage medium
CN113869951A
