Information completion method, device, computer-readable storage medium, and electronic device

Abstract

The present invention discloses an information completion method, apparatus, computer-readable storage medium, and electronic device. The method comprises: determining a target object and at least one target information corresponding to the target object from a genealogical knowledge graph, wherein the genealogical knowledge graph is constructed based on the genealogical information corresponding to the target object, the target object being the object for which information is to be completed, and each target information including at least the kinship relationship between the target relative and the target object and the kinship information corresponding to the target relative; determining target relative information from at least one kinship information based on the target information; and completing the target object's information in the genealogical knowledge graph based on the target relative information. The present invention solves the technical problem of low accuracy in genealogical information completion caused by insufficient reference factors in the character information completion process in related methods of the prior art.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to an information completion method, device, computer-readable storage medium, and electronic device. Background Art

[0002] As a large-scale semantic network system, the primary purpose of a knowledge graph is to describe the relationships between entities or concepts in the real world. Knowledge graphs are also a key branch of artificial intelligence, with in-depth research in knowledge extraction, representation, fusion, and reasoning. In my country, natural families are based on surnames, inherited through lineages and clans. The aggregation of all branches is collectively referred to as a family. A family tree is a collective record of the lineage and related matters by blood relatives sharing a common ancestor. It primarily contains genealogical information such as the origin of the surname, genealogical charts, generation rankings, and the history of hall names, as well as information about the individuals in the family tree.

[0003] Genealogies are historical books that record the lineage and characters of the paternal family. They provide an effective basis for people to trace their roots and help them understand the origins, ancestors, and changes of their own clans. In order to solve problems such as user tracing their roots, inheritance within the clan, and cross-surname analysis, constructing the family tree into a family tree knowledge graph is one of the effective ways to realize family tree big knowledge mining and reasoning. In the family tree knowledge graph, nodes represent characters, edges represent the relationship between characters, and points contain multiple attributes (such as name, gender, age, address, etc.). Family tree is one of the important bases for people to trace their roots and find the same bloodline, but the attribute information of characters is often missing. The existing related technologies have the defect of insufficient reference factors in the process of completing character information, which leads to the problem of low accuracy of family tree information completion.

[0004] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0005] Embodiments of the present invention provide an information completion method, device, computer-readable storage medium, and electronic device to at least solve the technical problem of low accuracy of genealogical information completion caused by insufficient reference factors in the process of character information completion in related methods in the prior art.

[0006] According to one aspect of an embodiment of the present invention, there is provided an information completion method, comprising: determining a target object and at least one target information corresponding to the target object from a genealogical knowledge graph, wherein the genealogical knowledge graph is constructed based on the genealogical information corresponding to the target object, the target object is an object of information to be completed, and each target information includes at least a kinship relationship between a target relative and the target object and kinship information corresponding to the target relative; determining target relative information from at least one kinship information based on the target information; and completing the information of the target object in the genealogical knowledge graph based on the target relative information.

[0007] Furthermore, the relative information includes at least relative addresses, and the target relative information is the target relative address, wherein the information completion method also includes: determining a non-empty relative address in at least one relative address; determining the confidence of the non-empty relative address; if the number of non-empty relative addresses is 1, then using the non-empty relative address as the target relative address; if the number of non-empty relative addresses is multiple, then determining the target relative address from multiple non-empty relative addresses based on the relative relationship and the confidence of the non-empty relative address.

[0008] Furthermore, the information completion method also includes: dividing the non-empty relative address into fields to obtain at least one address field; determining the confidence corresponding to each address field based on the field status corresponding to each address field, wherein the field status is used to characterize whether the address field is empty or non-empty; determining the confidence of the non-empty relative address based on the confidence corresponding to each address field.

[0009] Furthermore, the information completion method also includes: after taking the non-empty relative address as the target relative address, determining the first priority, wherein the first priority represents the degree of association of the relative relationship corresponding to the target relative address; based on the first priority and the confidence of the target relative address, determining the target confidence corresponding to the target relative address.

[0010] Furthermore, the information completion method also includes: determining a second priority, wherein the second priority characterizes the degree of association of the kinship relationship corresponding to each non-empty relative address; determining a target confidence corresponding to each non-empty relative address based on the second priority and the confidence of each non-empty relative address; determining a target relative address from multiple non-empty relative addresses based on the target confidence corresponding to each non-empty relative address, and obtaining a target confidence corresponding to the target relative address.

[0011] Furthermore, the information completion method also includes: after completing the address of the target object in the family tree knowledge graph based on the target relative's address, storing the target confidence corresponding to the target relative's address in the node corresponding to the target object in the family tree knowledge graph.

[0012] According to another aspect of an embodiment of the present invention, an information completion device is also provided, including: a first determination module, used to determine a target object and at least one target information corresponding to the target object from a genealogical knowledge graph, wherein the genealogical knowledge graph is constructed based on the genealogical information corresponding to the target object, the target object is the object of the information to be completed, and each target information includes at least the kinship relationship between the target relative and the target object and the kinship information corresponding to the target relative; a second determination module, used to determine the target relative information from at least one relative information based on the target information; and a completion module, used to complete the information of the target object in the genealogical knowledge graph based on the target relative information.

[0013] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is configured to execute the above-mentioned information completion method when running.

[0014] According to another aspect of an embodiment of the present invention, an electronic device is also provided, which includes one or more processors; a memory for storing one or more programs, which enables the one or more processors to run the programs when the one or more programs are executed by the one or more processors, wherein the programs are configured to execute the above-mentioned information completion method when running.

[0015] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program / instruction, which implements the above-mentioned information completion method when the computer program / instruction is executed by a processor.

[0016] In an embodiment of the present invention, the target object's information is supplemented based on the kinship information corresponding to the target relative of the target object. This involves determining the target object and at least one target information corresponding to the target object from a family tree knowledge graph, and then determining the target relative information from at least one kinship information based on the target information, thereby supplementing the target object's information in the family tree knowledge graph based on the target relative information. The family tree knowledge graph is constructed based on the family tree information corresponding to the target object. The target object is the object to be supplemented, and each target information includes at least the kinship relationship between the target relative and the target object, as well as the kinship information corresponding to the target relative.

[0017] In the above process, since there is a certain correlation between the relevant information of the target object and the relevant information of the target family members, the target object's information in the family tree knowledge graph is supplemented based on the target relative's information, effectively utilizing the relationships between people in the family tree and thus ensuring the accuracy of the supplemented target object's information. In addition, by obtaining the target information and determining the target relative information used to supplement the target object's information based on at least one relative information of the target information, the relative information is effectively screened using the relationships between people in the family tree. This avoids the supplementation conflicts that arise when the target object's information can only be supplemented based on a single relative information when multiple relative information exists, thereby improving the efficiency of information supplementation and further ensuring the accuracy of the target object's information supplemented using the target relative information.

[0018] It can be seen that the solution provided in this application achieves the purpose of completing the information of the target object based on the relative information corresponding to the target relatives of the target object, thereby realizing the technical effect of improving the accuracy of genealogy information completion, and further solving the technical problem of low accuracy of genealogy information completion caused by insufficient reference factors in the process of character information completion in the relevant methods in the existing technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0020] Figure 1 is a schematic diagram of an optional information completion method according to an embodiment of the present invention;

[0021] Figure 2 is a schematic diagram of an optional information completion method according to an embodiment of the present invention;

[0022] Figure 3 is a schematic diagram of an optional information completion device according to an embodiment of the present invention;

[0023] Figure 4 is a schematic diagram of an optional electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention 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 numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] 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 used 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.

[0027] Example 1

[0028] According to an embodiment of the present invention, an embodiment of an information completion method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0029] Figure 1 is a schematic diagram of an optional information completion method according to an embodiment of the present invention, such as Figure 1 As shown, the method includes the following steps:

[0030] Step S102: determine the target object and at least one target information corresponding to the target object from the genealogical knowledge graph, wherein the genealogical knowledge graph is constructed based on the genealogical information corresponding to the target object, the target object is the object of the information to be completed, and each target information includes at least the kinship relationship between the target relative and the target object and the kinship information corresponding to the target relative.

[0031] In step S102, a target object and at least one target information corresponding to the target object can be determined from the family tree knowledge graph by electronic devices, servers, application systems, and other devices. In this embodiment, the target object and at least one target information corresponding to the target object are determined from the family tree knowledge graph by an information completion system. The family tree knowledge graph can be constructed based on information such as the name, address, ID number, gender, age, and relationships between people recorded in the family tree information corresponding to the target object. The family tree knowledge graph consists of a number of nodes and a number of edges. Nodes represent people, and edges represent relationships between people. A node can contain multiple attribute information (such as name, gender, age, address, etc.).

[0032] Optionally, the information completion system can use the system query language of the graph database tool to query the set of characters whose target attribute information is empty from the genealogy knowledge graph database containing at least one genealogy knowledge graph: P = {p i ∈P|p i.address =null,1≤i≤m}, that is, determine a set consisting of at least one target object, where p i Represents the target object, that is, the object to be completed with the target attribute information, p i.address Indicates target attribute information, which may be at least one of an address, a landline number, or other information.

[0033] Furthermore, the information completion system can also determine at least one target information corresponding to the target object from the genealogy knowledge graph database and obtain a relationship list for each target object. in, (ie target information) contains at least the relation name r name (i.e. the aforementioned correspondence) and the relative information p of the relation object address , can also include the relation object p object (i.e. the aforementioned target relatives), where the relative information p of the relationship object address At least includes the target attribute information of the relationship object, that is, at least includes the information with the same attributes as the information to be completed of the target object, the relative information p of the relationship object address It is also possible to include only the target attribute information of the relationship object. name It can be "father", "mother", "grandfather", "spouse", etc. The relative information of the relationship object p address It can be at least one of the following information: the relative's address, the relative's landline number, etc. The relationship object p object It can be the name, ID number, node ID corresponding to the target relative in the family tree knowledge graph, or other identifier that can be used to represent the identity of the person. It can also include the confidence level of relative information It is used to describe the credibility of relative information, wherein the confidence of relative information at least includes the confidence corresponding to the target attribute information of the relationship object. The confidence corresponding to the target attribute information of the relationship object can be determined based on the completeness of the target attribute information. The aforementioned confidence can take values ​​from 0 to 1, and the higher the value, the higher the credibility. The initial confidence is empty. The aforementioned target relatives can be all relatives of the target object, or some relatively important relatives of the target object, such as grandfather, father, etc. Preferably,

[0034] It should be noted that by determining the family information of the target family, it is convenient to complete the information of the target object later.

[0035] Step S104: determining target relative information from at least one relative information based on the target information.

[0036] In step S104, the target relative information can be determined from at least one relative information based on the degree of association of the kinship relationship between the target relative and the target object in the target information. For example, the relative information corresponding to the kinship relationship of "father" is determined as the target relative information. The target relative information can also be determined from at least one relative information based on the confidence of the relative information in the target information. The target relative information can also be determined from at least one relative information based on the degree of association of the kinship relationship between the target relative and the target object and the confidence of the relative information in the target information.

[0037] It should be noted that, based on the target information, the target relative information used to complete the information of the target object is determined from at least one relative information, that is, the target relative information used to complete the information of the target object is determined by utilizing the relationship between the characters in the family tree, thereby realizing effective screening of relative information and avoiding the phenomenon of completion conflict caused by the fact that the information of the target object can only be completed based on one relative information when there are multiple relative information.

[0038] Step S106: Complete the target object information in the family tree knowledge graph based on the target relative information.

[0039] In step S106, since the target object has information to be completed, the information completion system can determine the missing information content of the target object based on the target relative information, such as using the target relative address in the target relative information as the missing address of the target object, or using the target relative phone number in the target relative information as the missing phone number of the target object, thereby completing the corresponding information into the node attribute corresponding to the target object in the genealogical knowledge graph to achieve information completion of the target object.

[0040] It should be noted that due to the correlation between the target subject's information and that of the target family members, and the fact that the genealogy knowledge graph is a new type of domain knowledge graph, there is no external knowledge base available for reference. New knowledge can only be inferred from the existing knowledge in the genealogy knowledge graph. Therefore, the target subject's information in the genealogy knowledge graph is supplemented with the target relative's information, ensuring the accuracy of the supplemented target subject's information. This facilitates relevant users to trace their ancestry, find lineage bloodlines, and understand lineage changes.

[0041] Based on the scheme defined in steps S102 to S106 above, it can be seen that in an embodiment of the present invention, the target object's information is supplemented based on the relative information corresponding to the target relative of the target object. This is done by determining the target object and at least one target information corresponding to the target object from the family tree knowledge graph, and then determining the target relative information from at least one relative information based on the target information, thereby supplementing the target object's information in the family tree knowledge graph based on the target relative information. The family tree knowledge graph is constructed based on the family tree information corresponding to the target object. The target object is the object to be supplemented, and each target information includes at least the kinship relationship between the target relative and the target object, and the relative information corresponding to the target relative.

[0042] It is easy to notice that in the above process, since there is a certain correlation between the relevant information of the target object and the relevant information of the target family members, the target object's information in the family tree knowledge graph is supplemented based on the target relative information, which effectively utilizes the relationships between the characters in the family tree, thereby ensuring the accuracy of the target object's information after supplementation. In addition, by obtaining the target information and determining the target relative information used to supplement the target object's information based on at least one relative information of the target information, the relative information is effectively screened using the relationships between the characters in the family tree, thereby avoiding the supplementation conflict caused by the fact that the target object's information can only be supplemented based on one relative information when there are multiple relative information. This improves the efficiency of information supplementation and further ensures the accuracy of the target object's information supplemented using the target relative information.

[0043] It can be seen that the solution provided in this application achieves the purpose of completing the information of the target object based on the relative information corresponding to the target relatives of the target object, thereby realizing the technical effect of improving the accuracy of genealogy information completion, and further solving the technical problem of low accuracy of genealogy information completion caused by insufficient reference factors in the process of character information completion in the relevant methods in the existing technology.

[0044] In an optional embodiment, the relative information includes at least relative addresses, and the target relative information is the target relative address. In the process of determining the target relative information from at least one relative information based on the target information, the information completion system can determine a non-empty relative address in at least one relative address, and then determine the confidence of the non-empty relative address. If the number of non-empty relative addresses is 1, the non-empty relative address is used as the target relative address. If the number of non-empty relative addresses is multiple, the target relative address is determined from multiple non-empty relative addresses based on the kinship relationship and the confidence of the non-empty relative address.

[0045] Optional, relative information p of the relationship object address At least includes the target attribute information of the aforementioned relationship object. In this embodiment, the target attribute information of the relationship object can be the relative address, that is, the relative information p of the relationship object. address At least include the relative's address and the confidence level of the relative's information At least including the confidence of the relative address. In this embodiment, the relative information p of the relationship object address Relative address, confidence level of relative information The confidence level of the relative address is illustrated as an example. Specifically, the information completion system can obtain a relationship list consisting of at least one target information. After that, the confidence of the relative address corresponding to each target relative in the relationship list is initialized. After that, the information completion system can first determine the non-empty relative address from the relative address based on the attributes of the node corresponding to the target relative in the family tree knowledge graph, and then recalculate the confidence of the non-empty relative address and update the corresponding Among them, the information completion system can be based on the relationship list Middle r name and p address The corresponding data determines whether the relative addresses corresponding to different relative relationships are non-empty relative addresses.

[0046] Furthermore, if there is only one non-empty relative address among the relative addresses corresponding to the target relative, the information completion system can directly use the non-empty relative address as the target relative address. Conversely, if there are multiple non-empty relative addresses among the relative addresses corresponding to the target relative, the information completion system can determine the target relative address based on the kinship relationship and the confidence of the non-empty relative address recalculated above.

[0047] It should be noted that, by determining the target relative address from at least one non-empty relative address based on the kinship relationship and the confidence of the non-empty relative address when there are multiple non-empty relative addresses, the acquisition of a more credible relative address is achieved, thereby improving the accuracy of the information of the completed target object.

[0048] In an optional embodiment, in the process of determining the confidence of a non-empty relative address, the information completion system may divide the non-empty relative address into fields to obtain at least one address field, and then determine the confidence corresponding to each address field based on the field status corresponding to each address field, wherein the field status is used to characterize whether the address field is empty or non-empty, thereby determining the confidence of the non-empty relative address based on the confidence corresponding to each address field.

[0049] Optionally, in this embodiment, the non-empty relative addresses can be divided into fields according to the regional categories, so as to obtain the address fields corresponding to the regional categories R (province), T (city), D (district / county), and S (street), respectively, and then the confidence corresponding to each address field can be determined based on the field status of each address field, that is, whether the address field is in a non-empty state or an empty state. Among them, the corresponding confidence interval can also be determined based on the regional category corresponding to each address field. For example, the confidence interval corresponding to the regional category R (province) is [0,1], and the confidence interval corresponding to T (city) is [0.0.8]. Preferably, the confidence interval corresponding to each regional category is the same, and the value of the confidence within the confidence interval can be determined based on the status of each address field. For example, when the address field corresponding to R (province) is empty, the confidence R of the address field is set to [0,1]. c Confirmed to be 0, when the address field corresponding to R (province) is not empty, the confidence level of the address field is R c Confirmed to 1; when the address field corresponding to T (city) is empty, the confidence level of the address field is T c Confirmed to be 0, when the address field corresponding to T (city) is not empty, the confidence level of the address field is T c Confirmed to 1; when the address field corresponding to D (district / county) is empty, the confidence level of the address field is D c Confirmed to be 0, when the address field corresponding to D (district / county) is not empty, the confidence level of the address field is D c Confirmed to 1; when the address field corresponding to S (street) is empty, the confidence of the address field is S c Confirmed to be 0, when the address field corresponding to S (street) is not empty, the confidence of the address field is S c Confirmed as 1. Thus, the confidence level corresponding to each address field is determined.

[0050] Furthermore, the confidence level of the non-empty relative address can be determined based on the following formula:

[0051]

[0052] Among them, R c Indicates the confidence level of the address field whose geographical category is province, Tc Indicates the confidence level of the address field whose geographical category is city, D c Indicates the confidence level of the address field whose geographical category is district / county, S c Indicates the confidence level of the address field whose geographical category is street.

[0053] It should be noted that by determining the confidence corresponding to each address field based on the field status corresponding to each address field, and then determining the confidence of the non-empty relative address, the accurate calculation of the confidence of the non-empty relative address based on the completeness of the address field is achieved.

[0054] In an optional embodiment, after a non-empty relative address is used as the target relative address, the information completion system may determine a first priority, and then determine a target confidence level corresponding to the target relative address based on the first priority level and the confidence level of the target relative address. The first priority level indicates the degree of relevance of the relative relationship corresponding to the target relative address.

[0055] Optionally, in this embodiment, the kinship relationship between the target object and the target relative is preferably any one of "father", "grandfather", and "spouse", and different kinship relationships have different priorities. Specifically, when the non-empty relative address corresponding to the kinship relationship of "father" is used as the target relative address, the first priority is determined to be 0.8. The target relative address can be completed to p i.address Among them, p i.address Represents the address of the target object. The target confidence corresponding to the target relative address can be calculated based on the following formula:

[0056]

[0057] in, Indicates the target confidence corresponding to the target relative address, Con rule It represents the first priority, and α represents the weight coefficient. α can be defined in combination with the genealogy rules, family precepts, and relevant regulations of the generation.

[0058] Optionally, when the non-empty relative address corresponding to the kinship relationship of "spouse" is used as the target relative address, the first priority is determined to be 0.6, and the target relative address can be completed to p i.address The target confidence level corresponding to the target relative address can also be calculated by using the above formula for calculating the target confidence level when the non-empty relative address corresponding to the relative relationship of "spouse" is used as the target relative address, so it will not be repeated here.

[0059] Optionally, when the non-empty relative address corresponding to the kinship relationship of "grandfather" is used as the target relative address, the first priority is determined to be 0.4, and the target relative address can be completed to pi.address The target confidence level corresponding to the target relative address can also be calculated by using the above formula for calculating the target confidence level when the non-empty relative address corresponding to the relative relationship of "grandfather" is used as the target relative address, so it will not be described in detail here.

[0060] It should be noted that by combining the degree of association of the kinship relationship corresponding to the target relative address and the confidence of the target relative address, the target confidence corresponding to the target relative address is determined, and the confidence attribute is added to the target relative address, thereby improving the accuracy and credibility of the reasoning results, making the completed target object information more convincing.

[0061] In an optional embodiment, during the process of determining a target relative address from multiple non-empty relative addresses based on the kinship relationship and the confidence of the non-empty relative address, the information completion system may determine a second priority, and based on the second priority and the confidence of each non-empty relative address, determine a target confidence corresponding to each non-empty relative address. Thus, based on the target confidence corresponding to each non-empty relative address, the target relative address is determined from the multiple non-empty relative addresses, and a target confidence corresponding to the target relative address is obtained. The second priority represents the degree of association of the kinship relationship corresponding to each non-empty relative address.

[0062] Optionally, if the user has two or more kinship relationships with their father, spouse, or grandfather, and the corresponding kinship addresses are non-empty kinship addresses, the multiple non-empty kinship addresses need to be screened to determine a unique target kinship address. Specifically, the information completion system may first calculate the target confidence corresponding to each non-empty kinship address, then determine the target kinship address from the multiple non-empty kinship addresses based on the target confidence corresponding to each non-empty kinship address, and use the target confidence corresponding to the non-empty kinship address determined as the target kinship address as the target confidence of the target kinship address.

[0063] The information completion system can determine that the priority of the non-empty relative address corresponding to the kinship relationship "father" is 0.8, that is, the second priority is 0.8. The confidence of the non-empty relative address is then calculated based on the following formula:

[0064]

[0065] in, represents the target confidence of non-empty relative addresses, Con rule ' indicates the second priority.

[0066] Optionally, the information completion system can determine that the priority corresponding to the non-empty relative address corresponding to the kinship relationship of "spouse" is 0.6, that is, the second priority is 0.6. Then, the same calculation is performed based on the above formula for calculating the confidence of the non-empty relative address, so it is not repeated here.

[0067] Optionally, the information completion system can determine that the priority corresponding to the non-empty relative address corresponding to the kinship relationship "grandfather" is 0.4, that is, the second priority is 0.4. Then, the same calculation is performed based on the above formula for calculating the confidence of the non-empty relative address, so it is not repeated here.

[0068] Furthermore, after determining the target confidence corresponding to each non-empty relative address, the information completion system can sort the non-empty relative addresses from large to small according to the target confidence corresponding to each non-empty relative address. Since the higher the confidence, the higher the credibility of the non-empty relative address and the more complete the address data, the information completion system can select the non-empty relative address with the highest target confidence among each non-empty relative address as the target relative address, and store the target relative address in the attribute information of the node corresponding to the target object in the genealogical knowledge graph.

[0069] It should be noted that by setting a corresponding target confidence for each non-empty relative address and determining the target relative address based on the target confidence corresponding to each non-empty relative address, the conflict situation when there are multiple non-empty relative addresses is solved, thereby improving the efficiency of information completion.

[0070] In an optional embodiment, after completing the address of the target object in the family tree knowledge graph based on the target relative's address, the information completion system may store the target confidence corresponding to the target relative's address in the node corresponding to the target object in the family tree knowledge graph.

[0071] Optionally, the information completion system can store the target relative address in the attribute information of the node corresponding to the target object in the genealogical knowledge graph, and at the same time store the target confidence corresponding to the target relative address in the attribute information of the node corresponding to the target object in the genealogical knowledge graph.

[0072] It should be noted that by also storing the target confidence corresponding to the target relative's address, relevant users will have a reference basis when consulting the family tree knowledge graph, thereby improving convenience.

[0073] Optionally, another optional embodiment of the present application is described. Figure 2As shown, the information completion system can obtain address inference rules designed by relevant users, wherein the address inference rules include at least the priorities corresponding to different kinship relationships, the calculation rules for the target confidence of non-empty kinship addresses or target kinship addresses, and the determination rules for the target kinship addresses. The information completion system can then query the family tree knowledge graph database for the attribute information of the target object and the corresponding target information (i.e., the aforementioned relationship list), and initialize the confidence of the family information in the target information. Furthermore, the information completion system can extract gender and address information from the target object's attribute information, and simultaneously extract the address information of people who have kinship relationships with the target object, such as the father, grandfather, and spouse, and determine the confidence of the aforementioned relative address information. The information completion system then performs inference based on the address inference rules obtained above. When there are multiple non-empty kinship addresses, that is, multiple inference results, the final inference result can be determined by calculating the target confidence of the non-empty kinship addresses, that is, calculating the confidence of the inference results. The non-empty kinship address corresponding to the inference result with the highest confidence is selected as the target kinship address. Finally, the target relative's address and the corresponding confidence level are stored as address attributes in the attribute information list of the target object node, thereby completing the information of the target object.

[0074] It can be seen that the solution provided in this application achieves the purpose of completing the information of the target object based on the relative information corresponding to the target relatives of the target object, thereby realizing the technical effect of improving the accuracy of genealogy information completion, and further solving the technical problem of low accuracy of genealogy information completion caused by insufficient reference factors in the process of character information completion in the relevant methods in the existing technology.

[0075] Example 2

[0076] According to an embodiment of the present invention, an embodiment of an information completion device is provided, wherein: Figure 3 is a schematic diagram of an optional information completion device according to an embodiment of the present invention, such as Figure 3 As shown, the device includes:

[0077] A first determination module 302 is configured to determine a target object and at least one target information corresponding to the target object from a family tree knowledge graph, wherein the family tree knowledge graph is constructed based on the family tree information corresponding to the target object, the target object is an object for which information is to be completed, and each target information includes at least a kinship relationship between a target relative and the target object, and kinship information corresponding to the target relative;

[0078] A second determining module 304 is configured to determine target relative information from at least one relative information based on the target information;

[0079] The completion module 306 is used to complete the information of the target object in the family tree knowledge graph based on the target relative information.

[0080] It should be noted that the above-mentioned first determination module 302, second determination module 304 and completion module 306 correspond to steps S102 to S106 in the above-mentioned embodiment. The examples and application scenarios implemented by the three modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned embodiment 1.

[0081] Optionally, the relative information includes at least relative addresses, and the target relative information is the target relative address, wherein the second determination module includes: a first sub-determination module, used to determine a non-empty relative address in at least one relative address; a second sub-determination module, used to determine the confidence of the non-empty relative address; a processing module, used to use the non-empty relative address as the target relative address if the number of non-empty relative addresses is 1; and a second processing module, used to determine the target relative address from multiple non-empty relative addresses based on the kinship relationship and the confidence of the non-empty relative address if the number of non-empty relative addresses is multiple.

[0082] Optionally, the first sub-determination module includes: a division module, used to divide the non-empty relative address into fields to obtain at least one address field; a third sub-determination module, used to determine the confidence corresponding to each address field based on the field status corresponding to each address field, wherein the field status is used to characterize whether the address field is empty or non-empty; a fourth sub-determination module, used to determine the confidence of the non-empty relative address based on the confidence corresponding to each address field.

[0083] Optionally, the information completion device also includes: a fifth sub-determination module, used to determine the first priority, wherein the first priority represents the degree of association of the kinship relationship corresponding to the target relative address; and a sixth sub-determination module, used to determine the target confidence corresponding to the target relative address based on the first priority and the confidence of the target relative address.

[0084] Optionally, the second processing module includes: a seventh sub-determination module, used to determine the second priority, wherein the second priority represents the degree of association of the kinship relationship corresponding to each non-empty relative address; an eighth sub-determination module, used to determine the target confidence corresponding to each non-empty relative address based on the second priority and the confidence of each non-empty relative address; and a ninth sub-determination module, used to determine the target relative address from multiple non-empty relative addresses based on the target confidence corresponding to each non-empty relative address, and obtain the target confidence corresponding to the target relative address.

[0085] Optionally, the information completion device further includes: a storage module for storing the target confidence corresponding to the target relative's address in the node corresponding to the target object in the family tree knowledge graph.

[0086] Example 3

[0087] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is further provided, in which a computer program is stored. The computer program is configured to execute the above-mentioned information completion method when running.

[0088] Example 4

[0089] According to another aspect of an embodiment of the present invention, an electronic device is provided, wherein: Figure 4 is a schematic diagram of an optional electronic device according to an embodiment of the present invention, such as Figure 4 As shown, the electronic device includes one or more processors; a memory for storing one or more programs, which, when executed by one or more processors, enables the one or more processors to run the programs, wherein the programs are configured to execute the above-mentioned information completion method when running.

[0090] Example 5

[0091] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program / instruction, which implements the above-mentioned information completion method when the computer program / instruction is executed by a processor.

[0092] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0093] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0094] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0095] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected to achieve the purpose of the present embodiment according to actual needs.

[0096] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0097] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0098] The above are only preferred embodiments of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An information completion method, characterized in that: include: Determining a target object and at least one target information corresponding to the target object from a family tree knowledge graph, wherein the family tree knowledge graph is constructed based on the family tree information corresponding to the target object, the target object is an object for which information is to be completed, and each target information includes at least a kinship relationship between a target relative and the target object and kinship information corresponding to the target relative; determining target relative information from at least one relative information based on the target information; Completing the target object information in the family tree knowledge graph based on the target relative information; The relative information includes at least a relative address, and the target relative information is a target relative address. The target relative information is determined from at least one relative information based on the target information, including: Determine a non-null relative address among at least one relative address; Determining the confidence level of the non-empty relative address; If there are multiple non-empty relative addresses, determining a target relative address from the multiple non-empty relative addresses based on the relative relationship and the confidence of the non-empty relative addresses; Determining the confidence level of the non-empty relative address, including: Dividing the non-empty relative address into fields to obtain at least one address field; Determining a confidence level corresponding to each address field based on a field status corresponding to each address field, wherein the field status is used to indicate whether the address field is empty or not empty; The confidence level of the non-empty relative address is determined based on the confidence level corresponding to each address field.

2. The method according to claim 1, characterized in that The relative information includes at least a relative address, and the target relative information is a target relative address. The target relative information is determined from at least one relative information based on the target information, including: If the number of the non-empty relative addresses is 1, the non-empty relative address is used as the target relative address.

3. The method according to claim 2, characterized in that After using the non-empty relative address as the target relative address, the method further includes: Determining a first priority, wherein the first priority represents a degree of association of the kinship relationship corresponding to the target kinship address; Based on the first priority and the confidence of the target relative address, a target confidence corresponding to the target relative address is determined.

4. The method according to claim 2, characterized in that Determining a target relative address from a plurality of non-empty relative addresses based on the relative relationship and the confidence of the non-empty relative address includes: Determining a second priority, wherein the second priority represents a degree of association of the kinship relationship corresponding to each non-empty kinship address; Determining a target confidence corresponding to each non-empty relative address based on the second priority and the confidence of each non-empty relative address; Based on the target confidence corresponding to each non-empty relative address, a target relative address is determined from the multiple non-empty relative addresses, and the target confidence corresponding to the target relative address is obtained.

5. The method according to claim 3 or 4, characterized in that After completing the address of the target object in the family tree knowledge graph based on the target relative's address, the method further includes: The target confidence corresponding to the target relative address is stored in the node corresponding to the target object in the family tree knowledge graph.

6. An information completion device, characterized in that: include: A first determination module is configured to determine a target object and at least one target information corresponding to the target object from a family tree knowledge graph, wherein the family tree knowledge graph is constructed based on the family tree information corresponding to the target object, the target object is an object for which information is to be completed, and each target information includes at least a kinship relationship between a target relative and the target object and kinship information corresponding to the target relative; a second determining module, configured to determine target relative information from at least one relative information based on the target information; A completion module, configured to complete the target object information in the family tree knowledge graph based on the target relative information; The relative information includes at least a relative address, and the target relative information is a target relative address, wherein the second determining module further includes: A first sub-determining module is configured to determine a non-empty relative address among at least one relative address; A second sub-determination module is used to determine the confidence level of the non-empty relative address; a second processing module, configured to determine a target relative address from the plurality of non-empty relative addresses based on the relative relationship and the confidence of the non-empty relative addresses if there are a plurality of non-empty relative addresses; The first sub-determination module also includes: A division module, configured to divide the non-empty relative address into fields to obtain at least one address field; A third sub-determination module is configured to determine a confidence level corresponding to each address field based on a field status corresponding to each address field, wherein the field status is used to indicate whether the address field is empty or not empty; The fourth sub-determination module is configured to determine the confidence level of the non-empty relative address based on the confidence level corresponding to each address field.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the information completion method according to any one of claims 1 to 5 when running.

8. An electronic device, characterized in that: The electronic device includes one or more processors; A memory for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to run the programs, wherein the programs are configured to execute the information completion method described in any one of claims 1 to 5 when run.

9. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the information completion method according to any one of claims 1 to 5 is implemented.

Images