Object name matching method and device, equipment, storage medium and program product

Abstract

The invention provides an object name matching method and device, equipment, a storage medium and a program product, relates to the technical field of computers, and can improve the accuracy of information query of electronic equipment. According to the specific technical scheme, the electronic equipment combines each target word group obtained by combining words in a target object name with each first word group obtained by combining words in a first object name; and respectively determining whether each second word group obtained by combination appears in the target object name and the first object name, determining the name similarity between the target object name and the first object name according to two determination results, and determining the name similarity between the target object name and the at least one first object name according to the name similarity between the target object name and the at least one first object name. And determining a first reliable parameter, and determining whether the target object name is the object name of the first object or not according to a size relationship between a parameter value of the first reliable parameter and a parameter threshold value. The method is used in a scene for querying the object to which the object name belongs.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of computer, and particularly relate to an object name matching method, device, equipment, storage medium and program product. BACKGROUND

[0002] At present, in the process that a user uses an electronic device to query an enterprise to which a certain enterprise name belongs, the user can input the certain enterprise name in the electronic device, so that the electronic device can first determine a keyword group from the certain enterprise name, and then compare the keyword group with each enterprise name of each enterprise in an enterprise database respectively, and then determine that the certain enterprise name is the enterprise name of the certain enterprise in the case that the keyword group is included in any enterprise name of the certain enterprise, and provide enterprise information of the certain enterprise to the user.

[0003] However, since the enterprise name of multiple enterprises in the enterprise database can include the keyword group, the electronic device can not accurately determine the enterprise to which the certain enterprise name belongs, and thus the accuracy of the electronic device to query the enterprise to which the enterprise name belongs is low, and thus the accuracy of the information query of the electronic device is low. SUMMARY

[0004] Embodiments of the present application provide an object name matching method, device, equipment, storage medium and program product, which can improve the accuracy of information query of the electronic device.

[0005] To achieve the above object, embodiments of the present application adopt the following technical solutions: In a first aspect, an embodiment of the present application provides a method for matching object names, the method comprising: an electronic device can generate at least one target word group according to different numbers of words in a target object name, and generate at least one first word group according to different numbers of words in each of at least one first object name of a first object, respectively; and generate at least one second word group according to each target word group and each first word group corresponding to one first object name, respectively; the electronic device can determine whether each second word group appears in the target object name, respectively, to obtain at least one first determination result, and determine whether each second word group appears in one first object name, respectively, to obtain at least one second determination result; and determine a name similarity between the target object name and one first object name according to the at least one first determination result and the at least one second determination result, and determine a first reliability parameter according to the name similarity between the target object name and the at least one first object name, the first reliability parameter representing a reliability degree of the target object name being an object name of the first object, so that the electronic device can determine whether the target object name is an object name of the first object according to a size relationship between a parameter value of the first reliability parameter and a parameter threshold.

[0006] In some examples, each of the at least one first determination result corresponds to one second word group, and each first determination result is used to indicate whether the corresponding second word group appears in the target object name; and each of the at least one second determination result corresponds to one second word group, and each second determination result is used to indicate whether the corresponding second word group appears in one first object name.

[0007] As can be known from the above, since the electronic device can generate at least one target phrase according to different numbers of words in the target object name, respectively generate at least one first phrase according to different numbers of words in each of the at least one first object name of the first object, and respectively combine each target phrase with each first phrase corresponding to one first object name to generate at least one second phrase, each second phrase in the at least one second phrase includes the target phrase composed of the words in the target object name and the first phrase composed of the words in the one first object name, that is, each second phrase includes more phrases, so that the electronic device can determine whether each second phrase appears in the target object name to obtain at least one first determination result, each first determination result can reflect whether each second phrase appears in the target object name, and determine whether each second phrase appears in one first object name to obtain at least one second determination result, each second determination result can reflect whether each second phrase appears in the one first object name, and the more second phrases appearing in the target object name and the one first object name at the same time can represent that the target object name and the one first object name are more similar, therefore, the electronic device can accurately determine the name similarity between the target object name and the one first object name according to the at least one first determination result and the at least one second determination result, and accurately determine the first reliable parameter according to the name similarity between the target object name and the at least one first object name, to accurately determine the reliability of the target object name as the object name of the first object, so that the electronic device can accurately determine whether the target object name is the object name of the first object according to the size relationship between the parameter value of the first reliable parameter and the parameter threshold, and further improve the accuracy of the electronic device in querying the object to which the object name belongs, so that the accuracy of information query of the electronic device can be improved.

[0008] In a possible implementation manner of the first aspect, the name similarity between the target object name and the first object name is determined according to the at least one first determination result and the at least one second determination result, including: the electronic device can generate a first vector according to the at least one first determination result, and generate a second vector according to the at least one second determination result, the first vector includes at least one first element, each first element corresponds to a first determination result, the second vector includes at least one second element, each second element corresponds to a second determination result; in a case where a first determination result indicates that a corresponding second word group appears in the target object name, a first element corresponding to the first determination result takes a first preset value, otherwise takes a second preset value; in a case where a second determination result indicates that a corresponding second word group appears in a first object name, a second element corresponding to the second determination result takes a first preset value, otherwise takes a second preset value. Thus, the electronic device can determine the name similarity between the target object name and the first object name according to the similarity between the first vector and the second vector.

[0009] As can be seen, since the electronic device can generate the first vector according to the at least one first determination result, and each first element of the first vector corresponds to a first determination result, and the value of each first element is determined by the corresponding first determination result, that is, the first vector can accurately reflect the characteristics of the at least one first determination result, and the electronic device can generate the second vector according to the at least one second determination result, and each second element of the second vector corresponds to a second determination result, and the value of each second element is determined by the corresponding second determination result, that is, the second vector can accurately reflect the characteristics of the at least one second determination result, so that the electronic device can accurately calculate the similarity between the first vector and the second vector according to the first vector reflecting the characteristics of the at least one first determination result and the second vector reflecting the characteristics of the at least one second determination result, and accurately determine the name similarity between the target object name and the first object name according to the similarity between the first vector and the second vector, so that the accuracy of the first reliable parameter determined by the electronic device can be further improved, thereby the accuracy of the electronic device determining the object name of the target object as the first object can be further improved, and the accuracy of the electronic device querying the object to which the object name belongs can be further improved, so that the accuracy of the information query of the electronic device can be further improved.

[0010] In a possible implementation form of the first aspect, the at least one first object name comprises a second object name and at least one third object name, the second object name being an object name with the highest frequency of use among the at least one first object name, and the at least one third object name being an object name other than the second object name among the at least one first object name. The determining the first reliability parameter according to the name similarity between the target object name and the at least one first object name comprises: the electronic device can calculate the first reliability parameter according to a tangent value of the name similarity between the target object name and the second object name and a first numerical value, wherein the first numerical value is a ratio of a sum value of the name similarity between the target object name and each third object name of the first object and a quantity value of the at least one third object name.

[0011] As can be seen, since the at least one first object name can be divided into the second object name (i.e., the first object name with the highest frequency of use) and the at least one third object name (i.e., the first object name with a lower frequency of use), and the tangent value of the name similarity between the target object name and the second object name and the first numerical value are used in the process of determining the first reliability parameter, the tangent function can grow rapidly away from zero, that is, the name similarity between the target object name and the second object name can be amplified in the process of determining the first reliability parameter while the name similarity between the target object name and the first object name with a lower frequency of use is taken into account, and thus the electronic device can accurately calculate the first reliability parameter, thereby further improving the accuracy of the electronic device in determining that the target object name is the object name of the first object, and further improving the accuracy of the electronic device in querying the object to which the object name belongs, and thus the accuracy of information query of the electronic device can be further improved.

[0012] In a possible implementation form of the first aspect, the electronic device can calculate the first reliability parameter according to the tangent value of the name similarity between the target object name and the second object name and the first numerical value, comprising: the electronic device can use a first algorithm to calculate the first reliability parameter according to the tangent value of the name similarity between the target object name and the second object name and the first numerical value. The first algorithm is: ; E is the first reliability parameter, tan(q) is the tangent value of the name similarity between the target object name and the second object name, N is the quantity value of the at least one third object name, and k is a preset correction value.

[0013] Therefore, the electronic device can use the first algorithm to accurately calculate the first reliable parameter, thereby further improving the accuracy of the electronic device in determining the object name of the target object as the first object, and further improving the accuracy of the electronic device in querying the object to which the object name belongs. In this way, the accuracy of information query of the electronic device can be further improved.

[0014] In a possible implementation of the first aspect, the first object includes at least one fourth object name. Before the electronic device combines the target object name and the different number of words, the method further includes: the electronic device determines the word similarity between the target object name and each fourth object name, respectively, and determines the fourth object name with a value of the corresponding word similarity greater than or equal to the similarity threshold as the at least one first object name.

[0015] Therefore, the electronic device can first determine the word similarity between the target object name and each fourth object name, respectively, and screen the fourth object name with a value of the corresponding word similarity greater than or equal to the similarity threshold as the at least one first object name, that is, screen the fourth object name with a greater word similarity with the target object name as the at least one first object name. In this way, the number of object names of the first object used in the subsequent steps can be reduced while ensuring the accuracy of information query, and therefore, the complexity of information query can be reduced while ensuring the accuracy of information query.

[0016] In a possible implementation of the first aspect, the electronic device determines the word similarity between the target object name and each fourth object name, respectively, including: the electronic device calculates the word similarity between the target object name and one fourth object name according to the number of words in the first set, the number of words in the second set, the number of words in the target object name, and the number of words in the one fourth object name; and the first set is the union set of the words in the target object name and the words in the one fourth object name, and the second set is the intersection set of the words in the target object name and the words in the one fourth object name.

[0017] Therefore, the electronic device can accurately calculate the word similarity between the target object name and the fourth object name according to the number of words in the first set, the number of words in the second set, the number of words in the target object name, and the number of words in the fourth object name, and thus can accurately select, in a subsequent step, the fourth object name with a larger word similarity to the target object name as the at least one first object name, thereby reducing the number of object names of the first object used for calculation in the subsequent step while ensuring the accuracy of information query, and thus reducing the complexity of information query while ensuring the accuracy of information query.

[0018] In a possible implementation of the first aspect, the electronic device can calculate the word similarity between the target object name and the fourth object name according to the number of words in the first set, the number of words in the second set, the number of words in the target object name, and the number of words in the fourth object name, including: the electronic device can use a second algorithm to calculate the word similarity between the target object name and the fourth object name according to the number of words in the first set, the number of words in the second set, the number of words in the target object name, and the number of words in the fourth object name. The second algorithm is: ; The word similarity between the target object name and the fourth object name is A, the number of words in the first set is A, the number of words in the second set is B, the number of words in the target object name is a, and the number of words in the fourth object name is b.

[0019] Therefore, the electronic device can accurately calculate the word similarity between the target object name and the fourth object name according to the number of words in the first set, the number of words in the second set, the number of words in the target object name, and the number of words in the fourth object name, and thus can accurately select, in a subsequent step, the fourth object name with a larger word similarity to the target object name as the at least one first object name, thereby reducing the number of object names of the first object used for calculation in the subsequent step while ensuring the accuracy of information query, and thus reducing the complexity of information query while ensuring the accuracy of information query.

[0020] In a possible implementation form of the first aspect, before the different numbers of words in each of the at least one first object name are combined respectively, the method further comprises: the electronic device can obtain at least one first object group from the object database, each of the at least one first object group comprising object names of objects belonging to a same region, each of the at least one first object group being associated with at least one group rule word, and determining a second object group comprising the at least one first object name according to the words in the target object name and the group rule words associated with the at least one first object group.

[0021] As can be seen, since the electronic device can obtain at least one first object group divided according to different regions from the object database, and each of the at least one first object group is associated with at least one group rule word, the electronic device can determine a second object group comprising the at least one first object name according to the words in the target object name and the group rule words associated with the at least one first object group. Therefore, in the subsequent steps, the electronic device only needs to use part of the object names obtained from the object database, without using all the object names obtained from the object database, so as to reduce the number of object names in the object database used in the process of determining the object to which the target object name belongs, and thus the complexity of information query can be reduced.

[0022] In a possible implementation form of the first aspect, the determining of the second object group according to the words in the target object name and the group rule words associated with the at least one first object group comprises: in a case where the words in the target object name match the group rule words associated with any of the at least one first object group, the electronic device can determine any of the at least one first object group as the second object group; or in a case where the words in the target object name do not match the group rule words associated with the at least one first object group, the electronic device can determine the i-th first object group as the second object group, wherein the i-th first object group is the i-th object group in a predetermined order of the at least one first object group, and i is a positive integer.

[0023] Thus, in the case that the word in the target object name matches the group rule word associated with any one of the first object groups, the electronic device can accurately determine the any one of the first object groups as the second object group, so that in the subsequent steps, the electronic device only needs to use part of the object names obtained from the object library, without using all the object names obtained from the object library, thereby reducing the number of object names in the object library used in the process of determining the object to which the target object name belongs; or in the case that the word in the target object name does not match the group rule word associated with at least one of the first object groups, the electronic device can determine the i-th first object group as the second object group, that is, the electronic device can determine the second object group by referring to the predetermined order, so that the electronic device can avoid using all the object names obtained from the object library in the subsequent steps, thereby reducing the number of object names in the object library used in the process of determining the object to which the target object name belongs; thus, the complexity of information query can be reduced.

[0024] In a possible implementation of the first aspect, each of the first object groups corresponds to a priority score, and the predetermined order is an order from large to small according to the corresponding priority scores; wherein the priority score corresponding to one of the first object groups is determined by a second value and a third value, the second value representing a quantity value of objects in a region corresponding to the one of the first object groups, and the third value representing a transaction frequency between a region to which the electronic device belongs and the region corresponding to the one of the first object groups.

[0025] Thus, in the case that the word in the target object name does not match the group rule word associated with at least one of the first object groups, the electronic device can determine the i-th first object group as the second object group, the electronic device determines the second object group by referring to the quantity value of objects in the region corresponding to each of the first object groups and the transaction frequency between the region to which the electronic device belongs and the region corresponding to each of the first object groups, so that the electronic device can determine the object group to which the target object name is most likely to belong as the second object group, thereby reducing the number of object names in the object library used in the process of determining the object to which the target object name belongs; thus, the complexity of information query can be reduced.

[0026] In a second aspect, an object name matching apparatus is provided. The apparatus comprises a generating module configured to generate at least one target phrase by combining different numbers of words in a target object name, and generate at least one first phrase by combining different numbers of words in each of at least one first object name of a first object, respectively; and generate at least one second phrase by combining each target phrase and each first phrase corresponding to the at least one first object name, respectively. The apparatus further comprises a determining module configured to determine whether each second phrase generated by the generating module appears in the target object name to obtain at least one first determination result, and determine whether each second phrase appears in the at least one first object name to obtain at least one second determination result; and determine a name similarity between the target object name and the at least one first object name according to the at least one first determination result and the at least one second determination result; and determine a first reliability parameter according to the name similarity between the target object name and the at least one first object name, the first reliability parameter representing a reliability degree of the target object name being an object name of the first object; and determine whether the target object name is an object name of the first object according to a size relationship between a parameter value of the first reliability parameter and a parameter threshold.

[0027] In a third aspect, an electronic device is provided. The electronic device comprises a memory and at least one processor. The memory is communicatively connected to the processor. The memory is configured to store computer program code including computer instructions. When the processor executes the computer instructions, the electronic device performs the method of the first aspect and any possible implementation manner thereof.

[0028] In a fourth aspect, a computer readable storage medium is provided. The computer readable storage medium stores computer instructions. When the computer instructions are executed by a processor, the computer instructions are used to implement the method of the first aspect and any possible implementation manner thereof.

[0029] In a fifth aspect, a computer program product is provided. When the computer program product is run on a computer / executed by a processor of a computer, the computer program product implements the method of the first aspect and any possible implementation manner thereof. The computer can be the electronic device of the third aspect and any possible implementation manner thereof.

[0030] It can be understood that the object name matching apparatus of the second aspect, the electronic device of the third aspect, the computer readable storage medium of the fourth aspect, and the computer program product of the fifth aspect can achieve the beneficial effects as described with reference to the first aspect and any possible implementation manner thereof, which will not be described herein again. BRIEF DESCRIPTION OF DRAWINGS

[0031] Figure 1 A flowchart of an object name matching method provided by an embodiment of the present application is shown in FIG. 1. Figure 2 A flowchart of another object name matching method provided by an embodiment of the present application is shown in FIG. 2. Figure 3 A flowchart of another object name matching method provided by an embodiment of the present application is shown in FIG. 3. Figure 4 A flowchart of another object name matching method provided by an embodiment of the present application is shown in FIG. 4. Figure 5 A flowchart of another object name matching method provided by an embodiment of the present application is shown in FIG. 5. Figure 6 A flowchart of another object name matching method provided by an embodiment of the present application is shown in FIG. 6. Figure 7 A flowchart of another object name matching method provided by an embodiment of the present application is shown in FIG. 7. Figure 8 A flowchart of another object name matching method provided by an embodiment of the present application is shown in FIG. 8. Figure 9 A flowchart of another object name matching method provided by an embodiment of the present application is shown in FIG. 9. Figure 10 A flowchart of another object name matching method provided by an embodiment of the present application is shown in FIG. 10. Figure 11 A flowchart of another object name matching method provided by an embodiment of the present application is shown in FIG. 11. Figure 12 A structural diagram of an object name matching device provided by an embodiment of the present application is shown in FIG. 12. Figure 13 A structural diagram of an electronic device provided by an embodiment of the present application is shown in FIG. 13. DETAILED DESCRIPTION

[0032] Hereinafter, the terms "first" and "second" are used only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first" and "second" can explicitly or implicitly include one or more of the features. In the description of the embodiments, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0033] The following will be described in detail with reference to the exemplary embodiments, examples of which are shown in the accompanying drawings. In the following description, for the purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the present application. It is apparent, however, that the present application can be practiced without these specific details. In other instances, well-known structures and devices are not shown in order to avoid obscuring the present application. The following exemplary embodiments are described in terms of specific details to provide a thorough understanding of the present application. However, it will be clear to those skilled in the art that the present application can be practiced without these specific details. In other instances, well-known structures and devices are shown in block diagram form in order to avoid obscuring the present application.

[0034] The technical solutions provided in the embodiments of the present application comply with the relevant laws and regulations and do not violate public order and good customs.

[0035] It should be noted that the enterprise name or enterprise information used in the technical solutions of the present application is limited to information that has been individually agreed to by the user of the enterprise, including but not limited to, before the enterprise uses the function, notifying and reminding the user of the enterprise to read the relevant user agreement (notification) and signing the agreement (authorization) including authorization of the relevant enterprise name or enterprise information.

[0036] It should be noted that in the embodiments of the present application, some software, components, models and other industry solutions may be mentioned, which should be considered as exemplary, and the purpose is only to illustrate the feasibility of the implementation of the technical solutions of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0037] At present, in the process of querying an enterprise to which a certain enterprise name belongs by using an electronic device, the user can input the certain enterprise name in the electronic device, so that the electronic device can first determine a keyword group from the certain enterprise name, and then compare the keyword group with each enterprise name of each enterprise in an enterprise database, and then determine that the certain enterprise name is the enterprise name of the certain enterprise when the keyword group is included in any enterprise name of the certain enterprise, and provide enterprise information of the certain enterprise to the user. For example, assuming that a user queries an enterprise to which a certain enterprise English name belongs by using an electronic device, after the user inputs the certain enterprise English name in the electronic device, the electronic device can first replace the symbols in the certain enterprise English name (for example, replace them with uniform symbols) and convert the case (for example, convert them into uniform lowercase English characters) to clean the certain enterprise English name, then output the word segmentation result of the enterprise name by combining the cleaned certain enterprise English name with an enterprise name dictionary, and determine a keyword group from the word segmentation result, so that the electronic device can compare the keyword group with each enterprise name of each enterprise in an enterprise database, and determine the certain enterprise name belonging to the certain enterprise according to the comparison result.

[0038] However, due to language and cultural differences, differences in enterprise naming habits, the same foreign enterprise may have multiple different writing methods, and how to identify the English name of the foreign enterprise extracted from the massive information as the same foreign enterprise becomes a problem. Using the above method may result in multiple enterprise names in the enterprise database including the above key word group, which may cause the electronic device to be unable to accurately determine the enterprise to which the above enterprise name belongs, thus resulting in low accuracy of the electronic device in querying the enterprise to which the enterprise name belongs. Moreover, the above method can only determine whether two enterprise names match a key word group, but in actual application, it is impossible to completely write the English name of the same enterprise in a standard and unified manner. Two enterprise names of the same enterprise may be similar in most content, but have some irrelevant words or inconsistent word order. In this case of incomplete matching, it is determined that they are not matched, and the enterprise cannot be correctly matched. Moreover, the above method cannot measure the similarity of two enterprise English names, and cannot meet the flexible requirements. Therefore, the accuracy and flexibility of information query of the electronic device are low.

[0039] To solve the above technical problems, the embodiments of the present application provide an object name matching method, device, equipment, storage medium and program product. The object name matching method, device, equipment, storage medium and program product provided by the embodiments of the present application will be described in detail below in combination with the drawings and scenarios.

[0040] The data transmission method provided by the embodiments of the present application can be applied to the scenario of querying the object to which the object name belongs.

[0041] Figure 1 A flowchart of an object name matching method provided by the embodiments of the present application is shown in FIG. 1. As shown in FIG. 1, the object name matching method provided by the embodiments of the present application can include the following steps 101 to 106. Figure 1

[0042] Step 101, the electronic device combines different numbers of words in the target object name to generate at least one target word group, and respectively combines different numbers of words in each of the at least one first object name of the first object to respectively generate at least one first word group.

[0043] In some embodiments of the present application, the target object name can be a to-be-queried object name, which can be a Chinese name or a foreign language name, including but not limited to English and the like. The target object name can include at least one word, and each word can be a Chinese word or a foreign language word.

[0044] ​In some embodiments of this application, the first object can be an object in a preset object database, and the first object may include, but is not limited to, at least one of the following: people, animals, enterprises, etc. The number of the first objects can be at least one.

[0045] In some embodiments of this application, the aforementioned at least one first object name can be at least a portion of the object name of a first object. The first object name can be a Chinese name or a foreign language name, wherein the foreign language name includes, but is not limited to, English. The first object name can include at least one word, and each word can be a Chinese word or a foreign language word.

[0046] The language of the at least one first object name can be the same as the language of the target object name. For example, if the language of the target object name is a foreign language (e.g., English), the language of the at least one first object name is also a foreign language (e.g., English).

[0047] In some embodiments of this application, when a user needs to query the object to which the target object name belongs, the user can input the target object name into the electronic device, so that the electronic device can combine different numbers of words in the target object name to generate at least one target word group, and combine different numbers of words in each of the at least one first object name of the first object to generate at least one first word group respectively.

[0048] Users can either manually enter the name of the target object into their electronic device, or they can use a web application on their electronic device to obtain a large amount of information from the internet, including the name of the target object, so that the electronic device can identify the name of the target object from the information.

[0049] In some embodiments of this application, before the electronic device generates at least one target word group by combining different numbers of words in the target object name, and generates at least one first word group by combining different numbers of words in each of the at least one first object names of the first object, the electronic device may first clean the target object name through an object name segmentation device, for example, by replacing symbols and converting capitalization in the target object name, and then input the target object name into a Hidden Markov Model (HMM) model to obtain at least one word of the target object name output by the HMM model, and clean each first object name, and then input each first object name into the HMM model to obtain at least one word of each first object name output by the HMM model.

[0050] In some instances, the HMM model described above can be trained using object names from an object database.

[0051] For example, object names in the object database can be segmented into words beforehand. Electronic devices can then label the segmented sample words using state space annotation to create tags for training data. The initial probability matrix π, transition probability matrix A, and emission probability matrix B of the Hidden Markov Model (HMM) can be estimated, and the Baum-Welch algorithm can be used to train the model, maximizing the likelihood of the training data. After multiple iterations of training and evaluation, a satisfactory performance level is achieved, resulting in a usable HMM model.

[0052] In some embodiments of this application, the electronic device may first delete words belonging to a preset word type from the target object name, and then combine words with a numerical value in the target object name to generate a portion of target word groups, and combine words with a numerical value and a sum of 1 in the target object name to generate another portion of target word groups, and combine words with a numerical value and a sum of 2 in the target object name to generate yet another portion of target word groups, and so on, to generate at least one of the above-mentioned target word groups.

[0053] The preset word types mentioned above may include, but are not limited to, auxiliary words, function words, etc., and the numerical value mentioned above can be a positive integer, such as 1.

[0054] For example, assuming the target name is The ABC DE Company, the electronic device can first delete the word "The" which belongs to a preset word type (such as a function word) in The ABC DE Company, and then combine one word from ABC DE Company to obtain the ABC phrase, the DE phrase, and the Company phrase. Then, it can combine two words from ABC DE Company to obtain the ABC DE phrase and the DE Company phrase, and finally, it can combine three words from ABC DE Company to obtain the ABC DE Company phrase.

[0055] In some embodiments of this application, for each of the at least one first object name mentioned above, the electronic device may first delete a word belonging to a preset word type in a first object name, and then combine words with a numerical value in a first object name to generate a portion of first word groups, and combine words with a numerical value and the sum of 1 in a first object name to generate another portion of first word groups, and combine words with a numerical value and the sum of 2 in a first object name to generate yet another portion of first word groups, and so on, to generate at least one first word group corresponding to at least one first object name.

[0056] In some embodiments of this application, the electronic device includes an object similarity calculation device, which can generate at least one target word group by combining different numbers of words in the target object name, and generate at least one first word group by combining different numbers of words in each of the at least one first object name of the first object.

[0057] Step 102: The electronic device combines each target phrase and each first phrase corresponding to a first object name to generate at least one second phrase.

[0058] In some embodiments of this application, the electronic device may first combine a target word group with a first word group corresponding to a first object name to generate a second word group, and then combine a target word group with another first word group corresponding to a first object name to generate another second word group, and so on, until all the first word groups corresponding to the first object name are combined; then combine the target word group with another first word group corresponding to the first object name to generate yet another second word group, and so on, until all the target word groups and all the first word groups corresponding to all the first object names are combined to generate at least one second word group.

[0059] In some embodiments of this application, an electronic device can generate at least one second phrase by combining each target phrase and each first phrase corresponding to a first object name using an object similarity calculation device.

[0060] Step 103: The electronic device determines whether each second phrase appears in the target object name, obtaining at least one first determination result, and determines whether each second phrase appears in a first object name, obtaining at least one second determination result.

[0061] In the embodiments of this application, each of the at least one first determination result corresponds to a second word group, and each of the at least one second determination result corresponds to a second word group.

[0062] It is understood that the number of at least one first determined result and the number of at least one second phrase can be the same, the number of at least one second determined result and the number of at least one second phrase can be the same, and the number of at least one first determined result and the number of at least one second determined result can be the same.

[0063] In some embodiments of this application, each first determination result may correspond to a second determination result. The corresponding first determination result and second determination result are obtained by determining the same second phrase.

[0064] In some embodiments of this application, the electronic device can use an object similarity calculation device to determine whether each second phrase appears in the target object name, obtain at least one first determination result, and determine whether each second phrase appears in a first object name, obtain at least one second determination result.

[0065] In some embodiments of this application, each first determination result is used to indicate whether the corresponding second phrase appears in the target object, and each second determination result is used to indicate whether the corresponding second phrase appears in a first object name.

[0066] In this embodiment, each second phrase is obtained by combining each target phrase and each first phrase corresponding to a first object name, rather than by combining only at least one word in the target object name. This avoids the situation where, when using a keyword phrase for matching, the target object name and the first object name only have some words in common but other words are completely different, and the electronic device mistakenly believes that the target object name and the first object name are matched. In other words, this application can accurately identify two object names with different spellings (for example, two object names may have most of the same content, but only have some irrelevant words or the word order is different). Therefore, it can improve the accuracy of information retrieval.

[0067] It should be noted that the above "matching" can be understood as: identical, or the similarity between the two is greater than or equal to a preset threshold.

[0068] Step 104: The electronic device determines the name similarity between the target object name and a first object name based on at least one first determination result and at least one second determination result.

[0069] In some embodiments of this application, the name similarity between the target object name and a first object name is used to indicate the name similarity between the target object name and the first object name.

[0070] In some embodiments of this application, the electronic device can determine the similarity between at least one first determination result and at least one second determination result, and determine the name similarity between a target object name and a first object name based on the similarity.

[0071] In some embodiments of this application, an electronic device can determine the name similarity between a target object name and a first object name based on at least one first determination result and at least one second determination result using an object similarity calculation device.

[0072] In some embodiments of this application, the electronic device may repeat steps 103 and 104 above at least once, thereby determining the name similarity between the target object and all first object names in at least one first object name.

[0073] The following example illustrates a specific scheme for an electronic device to determine the name similarity between a target object name and a first object name.

[0074] In some embodiments of this application, combined with Figure 1 ,like Figure 2 As shown, step 104 can be implemented through steps 1041 and 1042 as described below.

[0075] Step 1041: The electronic device generates a first vector based on at least one first determination result and generates a second vector based on at least one second determination result.

[0076] In this embodiment of the application, the first vector includes at least one first element, each first element corresponding to a first determination result; the second vector includes at least one second element, each second element corresponding to a second determination result; when a first determination result indicates that the corresponding second phrase appears in the target object name, the value of the first element corresponding to the first determination result is a first preset value, otherwise it is a second preset value; when a second determination result indicates that the corresponding second phrase appears in a first object name, the value of the second element corresponding to the second determination result is a first preset value, otherwise it is a second preset value.

[0077] In some instances, the first preset value can be a positive integer, such as 0 or 1, and the second preset value can be a positive integer, such as 1 or 0. It is understood that the first and second preset values ​​are different.

[0078] In some instances, an electronic device may first generate a first element based on a first determination result, and generate a second element based on a second determination result corresponding to the first determination result, then generate another first element based on another first determination result, and generate another second element based on a second determination result corresponding to the other first determination result, and so on, to generate all first elements of the first vector and all second elements of the second vector.

[0079] It is understandable that each first element corresponds to a second element.

[0080] Step 1042: The electronic device determines the name similarity between the target object name and a first object name based on the similarity between the first vector and the second vector.

[0081] In some instances, electronic devices can calculate the cosine similarity between a first vector and a second vector, and determine that cosine similarity as the name similarity between the target object name and a first object name.

[0082] The electronic device can use a third algorithm to determine the name similarity between the target object name and a first object name based on the similarity between the first and second vectors. This third algorithm is as follows: Formula 1; Where e represents the name similarity between the target object name and a first object name. Let i be the first element of the first vector. Let i be the i-th element of the second vector. Let be the i-th weight parameter, and n be the number of the first element and / or the second element.

[0083] Optionally, the aforementioned weight parameters can be obtained through a neural network model using the sample object name and external information associated with the sample object name.

[0084] For example, an electronic device can generate vectors A and B using two sample object names according to steps 101 to 104 above. The original cosine similarity of the two vectors (A and B), the length of the two sample object names, and external information associated with the two sample object names (such as the context of the sample object names on a webpage) are used as features. The input layer receives the features of the vector pairs, the hidden layer captures complex patterns and relationships, and the output layer outputs a single numerical value representing the predicted similarity score. The goal is to minimize the difference between the predicted similarity score and the true score. The neural network model automatically adjusts the connection weights between neurons in each layer, thereby learning the feature weights. By setting the activation function before the last layer of the neural network model to a linear function, the weighted feature values ​​(w) can be directly read from the neural network, thus obtaining each weight parameter.

[0085] Thus, it can be seen that since the electronic device can generate a first vector based on at least one first determined result, and each first element of the first vector corresponds to a first determined result, and the value of each first element is determined by the corresponding first determined result, that is, the first vector can accurately reflect the characteristics of at least one first determined result. Furthermore, the electronic device can generate a second vector based on at least one second determined result, and each second element of the second vector corresponds to a second determined result, and the value of each second element is determined by the corresponding second determined result, that is, the second vector can accurately reflect the characteristics of at least one second determined result. In this way, the electronic device can accurately calculate the similarity between the first vector and the second vector (i.e., the first vector and the second vector) based on the first vector reflecting the characteristics of the at least one first determined result and the second vector reflecting the characteristics of the at least one second determined result. Based on the similarity between the first vector and the second vector, it can accurately determine the name similarity between the target object name and a first object name. Therefore, the accuracy of the first reliable parameter determined by the electronic device can be further improved, thereby further improving the accuracy of the electronic device in determining the object name of the target object as the first object, and further improving the accuracy of the electronic device in querying the object to which the object name belongs. Thus, the accuracy of the information query by the electronic device can be further improved.

[0086] Step 105: The electronic device determines a first reliable parameter based on the name similarity between the target object name and at least one first object name.

[0087] In this embodiment of the application, the first reliability parameter describes the reliability of the object name whose target object name is the first object name.

[0088] In some embodiments of this application, the parameter value of the first reliability parameter can be positively or negatively correlated with the reliability of the object name whose target object name is the first object.

[0089] In some instances, where the value of the first reliability parameter is positively correlated with the reliability of the target object name being the name of the first object, the larger the value of the first reliability parameter, the higher the reliability of the target object name being the name of the first object, meaning that the target object name is more likely to be the name of the first object; conversely, the smaller the value of the first reliability parameter, the lower the reliability of the target object name being the name of the first object, meaning that the target object name is less likely to be the name of the first object.

[0090] In other instances, where the value of the first reliability parameter is negatively correlated with the reliability of the target object name being the name of the first object, the larger the value of the first reliability parameter, the lower the reliability of the target object name being the name of the first object, meaning that the target object name is less likely to be the name of the first object; conversely, the smaller the value of the first reliability parameter, the higher the reliability of the target object name being the name of the first object, meaning that the target object name is more likely to be the name of the first object.

[0091] In some embodiments of this application, an electronic device can determine a first reliable parameter based on the name similarity between a target object name and at least one first object name using an object similarity calculation device.

[0092] In some embodiments of this application, the aforementioned at least one first object name includes a second object name and at least one third object name, wherein the second object name is the object name used most frequently among the at least one first object name, and the at least one third object name is an object name other than the second object name among the at least one first object name. (Combined with...) Figure 1 ,like Figure 3 As shown, step 105 above can be implemented through step 1051 below.

[0093] Step 1051: The electronic device calculates the first reliable parameter based on the tangent value of the name similarity between the target object name and the second object name and the first value.

[0094] In this embodiment of the application, the first value mentioned above is the ratio of the sum of the name similarity between the target object name and each third object name of the first object to the number of at least one third object name.

[0095] In some instances, the aforementioned second object name can be referred to as the main object name. The electronic device also includes an object main name determination device, so that the electronic device can first determine the second object name and at least one third object name of the first object through the object main name determination device, and then calculate the first reliable parameter based on the tangent value of the name similarity between the target object name and the second object name and a first numerical value.

[0096] Optionally, for each of the at least one first object names, the electronic device can calculate the percentage (x) of all first object names under that first object name matching more than 0 times, the length (y) of names similar to all first object names under that first object name, and the number (z) of grouping rule words associated with the group to which the at least one first object name belongs (e.g., the second object group in the embodiments below) contained in that first object. To emphasize the importance of a high percentage of matching times, squaring significantly amplifies the influence of those already high percentages of matching times, thus making frequently occurring and well-known names stand out. The number of grouping rule words enhances the professionalism and authority of the name to some extent. Name length often reflects the likelihood of it being the official name of the object; excessively long names may also contain unnecessary redundancy, which can be reflected in the formula using the ratio to the longest English name under the first object. The following formula calculates the score (T), and the first object name with the highest score (T) is selected as the second object name: Formula 2; Where x is the percentage of times a first object name matches all first object names under the first object with a number greater than 0, y is the length of the names similar to all first object names under the first object name, and z is the number of grouping rule words associated with the first object to which at least one of the first object names belongs (e.g., the second object group in the following embodiment).

[0097] It is understandable that, according to Formula 2 above, the electronic device can calculate a corresponding score (T) for each first object name. Thus, the electronic device can determine the first object name with the largest score (T) as the second object name, and determine the first object name other than the second object name as at least one third object name.

[0098] Thus, it can be seen that since at least one first object name can be divided into a second object name (i.e., the most frequently used first object name) and at least one third object name (i.e., the less frequently used first object name), and the tangent value of the name similarity between the target object name and the second object name and a first value are used in the process of determining the first reliable parameter, and the tangent function can grow rapidly when it is far from zero, that is to say, in the process of determining the first reliable parameter, the name similarity between the target object name and the less frequently used first object name can be taken into account, while amplifying the influence of the name similarity between the target object name and the second object name on the first reliable parameter, the electronic device can accurately calculate the first reliable parameter, thereby further improving the accuracy of the electronic device in determining the object name of the target object name as the first object name, and further improving the accuracy of the electronic device in querying the object to which the object name belongs, thus further improving the accuracy of the information query of the electronic device.

[0099] In some instances, combined Figure 3 ,like Figure 4 As shown, step 1051 above can be implemented through step 1051a below.

[0100] Step 1051a: The electronic device uses a first algorithm to calculate a first reliable parameter based on the tangent of the name similarity between the target object name and the second object name and a first numerical value.

[0101] In this embodiment of the application, the first algorithm described above is: Formula 3; E is the first reliable parameter, tan(q) is the tangent of the name similarity between the target object name and the second object name, N is the number of at least one third object name, and k is the preset correction value.

[0102] Alternatively, the electronic device can use a Gradient Boosting Tree (GBT) model to predict the aforementioned preset correction value.

[0103] Specifically, electronic devices can collect data on the similarity of all object names, the frequency of use, name length, and the number of words containing the grouping rules mentioned above for multiple objects. Feature scaling is then applied to bring all features to the same scale, which helps improve the convergence speed and stability of the GBT model. A shallow decision tree is initialized, and new decision tree fitting residuals are formed during iterative training, gradually reducing prediction errors. Root mean square error is used to evaluate model performance. The trained GBT model is then used to predict the aforementioned preset correction values.

[0104] Thus, since the specific structure of the first algorithm is specified in the embodiments of this application, the electronic device can use the first algorithm to accurately calculate the first reliable parameter, thereby further improving the accuracy of the electronic device in determining the object name of the target object as the object name of the first object, and further improving the accuracy of the electronic device in querying the object to which the object name belongs, thus further improving the accuracy of the electronic device in information query.

[0105] Step 106: The electronic device determines whether the target object name is the object name of the first object based on the relationship between the parameter value of the first reliable parameter and the parameter threshold.

[0106] In some embodiments of this application, when the first reliability parameter is positively correlated with the aforementioned reliability level, if the parameter value of the first reliability parameter is greater than or equal to the parameter threshold, then the target object name is the object name of the first object; otherwise, the target object name is not the object name of the first object.

[0107] In some other embodiments of this application, when the first reliability parameter is negatively correlated with the aforementioned reliability level, if the parameter value of the first reliability parameter is greater than the parameter threshold, then the target object name is not the object name of the first object; otherwise, the target object name is the object name of the first object.

[0108] In some embodiments of this application, if the target object name is the object name of the first object, the electronic device may display the second object name of the first object; otherwise, the electronic device may display the target object name.

[0109] In some embodiments of this application, if the target object name is the object name of the first object, the electronic device can add the target object name to the object name of the first object in the object database, thereby updating the object name of the first object.

[0110] In some embodiments of this application, after determining whether the target object name is the object name of the first object, the electronic device may also obtain another object from the object database and perform the above steps 101 to 106 based on the target object name and the other object to determine again whether the target object name is the object name of the other object, and so on, until each object in the object database is determined.

[0111] This application provides an object name matching method. An electronic device can generate at least one target word group by combining different numbers of words in the target object name, and generate at least one first word group by combining different numbers of words in each of the at least one first object names of a first object. Furthermore, it can generate at least one second word group by combining each target word group with each first word group corresponding to a first object name. The electronic device can then determine whether each second word group appears in the target object name, obtaining at least one first determination result, and determine whether each second word group appears in a first object name, obtaining at least one second determination result. Based on the at least one first determination result and the at least one second determination result, the device determines the name similarity between the target object name and a first object name, and determines a first reliability parameter based on the name similarity between the target object name and at least one first object name. This first reliability parameter characterizes the reliability that the target object name is the object name of the first object. Therefore, the electronic device can determine whether the target object name is the object name of the first object based on the relationship between the parameter value of the first reliability parameter and a parameter threshold.Because the electronic device can generate at least one target phrase by combining different numbers of words in the target object name, and generate at least one first phrase by combining different numbers of words in each of the at least one first object names of the first object, and generate at least one second phrase by combining each target phrase with each first phrase corresponding to a first object name, each second phrase in the at least one second phrase includes not only the target phrase formed by combining words in the target object name, but also the first phrase formed by combining words in the first object name. That is, each second phrase includes more phrases, the electronic device can determine whether each second phrase appears in the target object name, obtaining at least one first determination result. Each first determination result can reflect whether each second phrase appears in the target object name, and determine whether each second phrase appears in a first object name, obtaining at least one... The second determination result reflects whether each second phrase appears in the first object name. The more second phrases appear in both the target object name and the first object name, the more similar the target object name and the first object name are. Therefore, the electronic device can accurately determine the name similarity between the target object name and the first object name based on at least one first determination result and at least one second determination result. Based on the name similarity between the target object name and at least one first object name, the electronic device can accurately determine the first reliability parameter to accurately determine the reliability of the target object name as the object name of the first object. Thus, the electronic device can accurately determine whether the target object name is the object name of the first object based on the relationship between the parameter value and the parameter threshold of the first reliability parameter, thereby improving the accuracy of the electronic device in querying the object to which the object name belongs. In this way, the accuracy of the electronic device in querying information can be improved.

[0112] Furthermore, the electronic device determines whether the target object name is the object name of the first object based on the relationship between the parameter value of the first reliable parameter and the parameter threshold. In different scenarios, the electronic device can flexibly determine whether the target object name is the object name of the first object by setting the relationship between the parameter threshold, thus improving the flexibility of information query of the electronic device.

[0113] Furthermore, the embodiments of this application can be applied to the specific niche field of matching enterprise names with enterprises. Even when a large amount of labeled data is unavailable, effective model calculations can be performed based on the various word segmentation information of the name itself, thereby enabling a more comprehensive evaluation of text similarity and solving the problem of large matching errors for specific word groups.

[0114] Furthermore, the similarity between the target object name and the first object is calculated during the process of this application embodiment, which can reflect subtle differences, flexibly adjust the similarity requirements, provide different groupings for use, and improve the applicability of the model.

[0115] In some embodiments of this application, combined with Figure 1 ,like Figure 5 As shown, prior to step 101 above, another object name matching method provided in this application embodiment may further include steps 201 and 202 as described below.

[0116] Step 201: The electronic device retrieves at least one first object group from the object database.

[0117] In this embodiment of the application, each of the at least one first object group includes the object name of an object belonging to the same region, and each first object group is associated with at least one grouping rule word.

[0118] In some instances, the aforementioned first object group can be at least a portion of object groups in an object database. Where at least one first object group is a portion of object groups in an object database, the object database may further include a third object group containing object names of objects that do not belong to any region (or belong to an undefined region), and this third object group is not associated with any grouping rule words.

[0119] In some instances, electronic devices can first divide all objects in the object database into at least one first object group and a third object group based on the region to which the object belongs, and then obtain the words that are usually contained in the object names of the region corresponding to each first object group, and determine the grouping rule words associated with each first object group.

[0120] For example, suppose that at least one first object grouping includes object group 1, object group 2, object group 3, object group 4, ..., and the third object grouping includes object group Q, as shown in Table 1: Table 1

[0121] The object group 1 includes object names from region A, which typically contain the words LLC, Inc., and Corp. Therefore, the grouping rule words associated with object group 1 are LLC, Inc., and Corp. Object group 2 includes object names from region F, which typically contain the words SARL and SA. Therefore, the grouping rule words associated with object group 2 are SARL and SA. Object group 3 includes object names from region R, which typically contain the words KK and GK. Therefore, the grouping rule words associated with object group 3 are KK and GK. Object group 4 includes object names from region Y, which typically contain the words Limited and Itd. Therefore, the grouping rule words associated with object group 4 are Limited and Itd. Object group Q includes object names from undefined regions and is not associated with any grouping rule words.

[0122] Optionally, the electronic device also includes a region grouping device, which allows the electronic device to divide object names in the object database into at least one first object group and a third object group.

[0123] Step 202: The electronic device determines the second object group based on the words in the target object name and at least one grouping rule word associated with the first object group.

[0124] In this embodiment of the application, the second object grouping includes at least one first object name.

[0125] In some instances, electronic devices can determine a second object group based on words in the target object name and at least one grouping rule word associated with a first object group using a regional grouping device.

[0126] Thus, since the electronic device can obtain at least one first object group divided by different regions from the object database, and each first object group is associated with at least one grouping rule word, the electronic device can determine the second object group including the aforementioned at least one first object name based on the words in the target object name and the grouping rule words associated with at least one first object group. Therefore, in subsequent steps, the electronic device only needs to use a portion of the object names obtained from the object database, instead of using all the object names obtained from the object database. This reduces the number of object names in the object database used in the process of determining the object to which the target object name belongs, thereby reducing the complexity of information retrieval.

[0127] In some instances, combined Figure 5 ,like Figure 6 As shown, step 202 above can be implemented through step 2021 or step 2022 as described below.

[0128] Step 2021: If a word in the target object name matches a grouping rule word associated with any first object group, the electronic device identifies the first object group as the second object group.

[0129] In this embodiment of the application, if a word in the target object name matches a word in the grouping rule associated with any first object group, it can be considered that the target object name includes words in the common object names of objects in the region corresponding to the first object group. That is, the region to which the target object name belongs may be the same as the region corresponding to the first object group. Therefore, the electronic device can determine any first object group as the second object group.

[0130] Step 2022: If a word in the target object name does not match a grouping rule word associated with at least one first object group, the electronic device determines the i-th first object group as the second object group.

[0131] In this embodiment of the application, the i-th first object group is the i-th object group after sorting at least one first object group in a predetermined order, where i is a positive integer.

[0132] In this embodiment of the application, if a word in the target object name does not match a grouping rule word associated with at least one first object group, it can be assumed that the region of the object to which the target object name belongs may be different from the region corresponding to at least one first object group. Therefore, the electronic device can determine the i-th first object group as the second object group, and determine it one by one in each first object group.

[0133] Optionally, each first object group corresponds to a priority score, and the predetermined order is in descending order of the corresponding priority scores; wherein, the priority score corresponding to a first object group is determined by a second value and a third value, the second value representing the number of objects in the region corresponding to the first object group, and the third value representing the transaction frequency between the region to which the electronic device belongs and the region corresponding to the first object group.

[0134] For example, the second value mentioned above may include, but is not limited to, Gross Domestic Product (GDP), and the third value may include, but is not limited to, the import and export value between the region to which the electronic device is located and the region corresponding to the first object group. The third value may include two sub-values, such as the import value between the region to which the electronic device is located and the region corresponding to the first object group and the export value between the region to which the electronic device is located and the region corresponding to the first object group.

[0135] For example, the electronic device can use a fourth algorithm to determine a priority score corresponding to a first object group based on a second value and a third value. The fourth algorithm is as follows: Formula 4; Where M is the priority score corresponding to a first object group, G is the second value (e.g., GDP), JC is the third value (e.g., import and export value), J is a sub-value of the third value (e.g., import value), and C is another sub-value of the third value (e.g., export value).

[0136] It's understandable that GDP reflects the size of a region's economy and indirectly reflects the number of businesses. The trade volume between the region where the electronic device is located and other regions reflects the number and frequency of businesses encountered in daily life. The higher the score of M (i.e., the priority score), the more likely the target object name belongs to that first object group. Therefore, at least one first object group can be sorted in descending order of priority score, allowing the electronic device to determine the target object name from the first object group to which it is most likely to belong first. This reduces the number of determinations by the electronic device and lowers the computational complexity.

[0137] Thus, since the priority score corresponding to a first object group is determined by a second and a third value, where the second value represents the number of objects in the region corresponding to the first object group, and the third value represents the transaction frequency between the region to which the electronic device belongs and the region corresponding to the first object group, the electronic device can accurately determine the priority score corresponding to each first object group. Therefore, if a word in the target object name does not match a grouping rule word associated with at least one first object group, the electronic device can determine the i-th first object group as the second object group. In determining the second object group, the electronic device refers to the number of objects in the region corresponding to each first object group and the transaction frequency between the region to which the electronic device belongs and the region corresponding to each first object group. Thus, the electronic device can determine the object group to which the target object name most likely belongs as the second object group, thereby reducing the number of object names in the object database used in determining the object to which the target object name belongs; thus, the complexity of information retrieval can be reduced.

[0138] Optionally, the electronic device can determine the first object group as the second object group and make the determination within the second object group. That is, i can be 1.

[0139] Thus, since the electronic device can accurately identify any first object group as the second object group when a word in the target object name matches a grouping rule word associated with any first object group, in subsequent steps, the electronic device only needs to use a portion of the object names obtained from the object database, instead of using all the object names obtained from the object database. This reduces the number of object names in the object database used in determining the object to which the target object name belongs. Alternatively, since the electronic device can identify the i-th first object group as the second object group when a word in the target object name does not match a grouping rule word associated with at least one first object group, the electronic device can determine the second object group by referring to a predetermined order. Therefore, it can avoid using all the object names obtained from the object database in subsequent steps, thus reducing the number of object names in the object database used in determining the object to which the target object name belongs. In this way, the complexity of information retrieval can be reduced.

[0140] In some embodiments of this application, the first object described above includes at least one fourth object name. (In conjunction with...) Figure 1 ,like Figure 7 As shown, prior to step 101 above, another object name matching method provided in this application embodiment may further include steps 301 and 302 as described below.

[0141] Step 301: The electronic device determines the word similarity between the target object name and each fourth object name.

[0142] In some instances, the word similarity above is used to indicate the degree of overlap between the words of the target object name and the fourth object name.

[0143] In some instances, electronic devices can use similarity calculation devices to determine the word similarity between the target object name and each fourth object name, respectively.

[0144] In some instances, combined Figure 7 ,like Figure 8 As shown, step 301 above can be implemented through step 3011 below.

[0145] Step 3011: The electronic device calculates the word similarity between the target object name and the fourth object name based on the number of words in the first set, the number of words in the second set, the number of words in the target object name, and the number of words in the fourth object name.

[0146] In this embodiment of the application, the first set is the union of the words in the target object name and the words in the fourth object name, and the second set is the intersection of the words in the target object name and the words in the fourth object name.

[0147] Thus, since the number of words in the first set reflects the total number of words in the target object name and the fourth object name, and the number of words in the second set reflects the number of identical words in the target object name and the fourth object name, the electronic device can accurately calculate the word similarity between the target object name and the fourth object name based on the number of words in the first set, the second set, the target object name, and the fourth object name. Therefore, in subsequent steps, the electronic device can accurately select the fourth object name with a higher word similarity to the target object name as at least one of the aforementioned first object names. This reduces the number of first object names used in subsequent steps while ensuring the accuracy of information retrieval, thereby reducing the complexity of information retrieval while ensuring the accuracy of information retrieval.

[0148] Optionally, combined Figure 8 ,like Figure 9 As shown, step 3011 above can be implemented through step 3011a below.

[0149] Step 3011a: The electronic device uses the second algorithm to calculate the word similarity between the target object name and the fourth object name based on the number of words in the first set, the number of words in the second set, the number of words in the target object name, and the number of words in the fourth object name.

[0150] In this embodiment of the application, the second algorithm described above is: Formula 5; Let A be the word similarity between the target object name and the fourth object name, where A is the number of words in the first set, B is the number of words in the second set, a is the number of words in the target object name, and b is the number of words in the fourth object name.

[0151] Thus, since the specific structure of the second algorithm is specified in the embodiments of this application, the electronic device can use the second algorithm to accurately calculate the word similarity between the target object name and the fourth object name. Therefore, in subsequent steps, the electronic device can accurately select the fourth object name with a higher word similarity to the target object name as at least one of the first object names. This can reduce the number of first object names used in subsequent steps while ensuring the accuracy of information retrieval is not affected. Therefore, the complexity of information retrieval can be reduced while ensuring the accuracy of information retrieval is not affected.

[0152] Step 302: The electronic device identifies at least one fourth object name whose corresponding word similarity value is greater than or equal to the similarity threshold as at least one first object name.

[0153] Thus, it can be seen that since the electronic device can first determine the word similarity between the target object name and each fourth object name, and then select the fourth object names whose corresponding word similarity values ​​are greater than or equal to the similarity threshold as at least one first object name, that is, select the fourth object names with higher word similarity to the target object name as at least one first object name, the number of first object names used in subsequent steps can be reduced while ensuring the accuracy of information retrieval is not affected. Therefore, the complexity of information retrieval can be reduced while ensuring the accuracy of information retrieval is not affected.

[0154] The following will illustrate another object name matching method provided in the embodiments of this application with a complete example.

[0155] Figure 10 This is a flowchart illustrating another object name matching method provided in an embodiment of this application. Figure 10As shown, another object name matching method provided in this application embodiment may include the following steps: Step 1: Use the regional grouping device to determine the second object group based on words in the target object name and at least one grouping rule word associated with the first object group.

[0156] If a word in the target object name matches a word in a grouping rule associated with any first object group, then proceed to step 2; otherwise, proceed to step 9.

[0157] Step 2: If a word in the target object name matches a word associated with a grouping rule for any first object group, then that first object group is identified as the second object group.

[0158] Step 3: Using the object master name determination device, determine the second object name for each object in the second object group.

[0159] Step 4: Use the object name segmentation device to segment each object name of each object in the target object name and the second object group to obtain the target object name and each word of each object name.

[0160] Step 5: Using a similarity calculation device, calculate the name similarity of each object name in the target object name and the second object group, and determine the target object name and each first reliable parameter corresponding to each object based on the name similarity.

[0161] Step 6: Based on the relationship between each first reliable parameter and the parameter threshold, determine whether the target object name is the object name of each object.

[0162] Step 7: If the target object name is the name of an object, then display the second object name of that object; otherwise, display the target object name.

[0163] Step 8: If the target object name is the object name of an object, add the target object name to the object name of that object; otherwise, add the object corresponding to the target object name and the target object name to the second object group.

[0164] Step 9: If a word in the target object name does not match a grouping rule word associated with at least one first object group, determine the i-th first object group as the second object group.

[0165] Step 10: Determine the first reliable parameter in each first object group in descending order of priority score corresponding to at least one first object group.

[0166] Step 11 is the same as step 3.

[0167] Step 12 is the same as step 4.

[0168] Step 13 is the same as step 5.

[0169] Step 14 is the same as step 6.

[0170] Step 15: If the target object name is the object name of an object, then display the second object name of that object and add the target object name to the object name of that object.

[0171] Step 16: Delete the object names that match the target object name in the first object group corresponding to the remaining low priority scores.

[0172] Step 17: If the target object name is not the object name of any object, proceed to the next first object group to determine the first reliable parameter, and repeat steps 11 to 14 above until the last first object group. If the target object name is also not the object name of any object in the last first object group, then display the target object name.

[0173] Step 18: Add the target object name and the object corresponding to the target object name to the third object group.

[0174] Figure 11 This is a flowchart illustrating another object name matching method provided in an embodiment of this application. Figure 11 As shown, the step of "calculating the name similarity of each object name in the target object name and each object name in the second object group, and determining the target object name and each first reliable parameter corresponding to each object based on the name similarity" can include the following steps: Step 19: Identify the object name of the first object that is completely unrelated to the target object name.

[0175] The electronic device can determine the word similarity between the target object name and each fourth object name of the first object, and identify the fourth object name whose word similarity value is less than the similarity threshold as an object name that is completely unrelated to the target object name, so that the calculation can be performed without using the completely unrelated object name in subsequent steps.

[0176] Step 20: Calculate the name similarity between at least one first object name and the target object name in pairs.

[0177] Specifically, the electronic device can combine each target phrase with each first phrase corresponding to a first object name to generate at least one second phrase; determine whether each second phrase appears in the target object name to obtain at least one first determination result, and determine whether each second phrase appears in the first object name to obtain at least one second determination result; determine the name similarity between the target object name and the first object name based on at least one first determination result and at least one second determination result. This process is repeated until the name similarity between each first object name and the target object name is determined.

[0178] Step 21: Generate a first vector and a second vector based on at least one first determination result and at least one second determination result, and determine the name similarity between the target object name and the first object name based on the similarity between the first vector and the second vector.

[0179] Step 22: Determine the first reliable parameter based on the name similarity between the target object name and at least one first object name.

[0180] Figure 12 This is a schematic diagram of the structure of an object name matching device provided in an embodiment of this application. Figure 12 As shown, the object name matching device 400 may include a generation module 401 and a determination module 402.

[0181] The generation module 401 is configured to generate at least one target word group by combining different numbers of words in the target object name, and to generate at least one first word group by combining different numbers of words in each of the at least one first object names of the first object; and to generate at least one second word group by combining each target word group with each first word group corresponding to a first object name. The determination module 402 is configured to determine whether each second word group generated by the generation module 401 appears in the target object name, obtaining at least one first determination result, and to determine whether each second word group appears in a first object name, obtaining at least one second determination result; and to determine the name similarity between the target object name and a first object name based on the at least one first determination result and the at least one second determination result; and to determine a first reliability parameter based on the name similarity between the target object name and at least one first object name, the first reliability parameter representing the reliability that the target object name is the object name of the first object; thereby determining whether the target object name is the object name of the first object based on the relationship between the parameter value of the first reliability parameter and the parameter threshold.

[0182] This application provides an object name matching device. The device can generate at least one target word group by combining different numbers of words in the target object name, and at least one first word group by combining different numbers of words in each of the at least one first object names of a first object. It can also generate at least one second word group by combining each target word group with each first word group corresponding to a first object name. Each second word group includes not only the target word group formed by combining words from the target object name, but also the first word group formed by combining words from the first object name. In other words, each second word group includes more word groups. Thus, the object name matching device can determine whether each second word group appears in the target object name, obtaining at least one first determination result. Each first determination result reflects whether each second word group appears in the target object name and whether each second word group appears in a first object name. At least one second determination result is obtained, each second determination result reflecting whether each second phrase appears in the first object name. The more second phrases appear in both the target object name and the first object name, the more similar the target object name and the first object name are. Therefore, the object name matching device can accurately determine the name similarity between the target object name and the first object name based on the at least one first determination result and the at least one second determination result. Based on the name similarity between the target object name and at least one first object name, it can accurately determine the first reliability parameter to accurately determine the reliability of the target object name as the object name of the first object. Thus, the object name matching device can accurately determine whether the target object name is the object name of the first object based on the relationship between the parameter value of the first reliability parameter and the parameter threshold, thereby improving the accuracy of the object name matching device in querying the object to which the object name belongs. In this way, the accuracy of the information query of the object name matching device can be improved.

[0183] In other embodiments, the determining module 402 is specifically configured to generate a first vector based on at least one first determining result and a second vector based on at least one second determining result. The first vector includes at least one first element, each first element corresponding to a first determining result. The second vector includes at least one second element, each second element corresponding to a second determining result. If a first determining result indicates that a corresponding second phrase appears in the target object name, the value of the first element corresponding to the first determining result is a first preset value; otherwise, the value is a second preset value. If a second determining result indicates that a corresponding second phrase appears in a first object name, the value of the second element corresponding to the second determining result is a first preset value; otherwise, the value is a second preset value. Furthermore, the similarity between the target object name and a first object name is determined based on the similarity between the first vector and the second vector.

[0184] In other embodiments, the at least one first object name includes a second object name and at least one third object name, wherein the second object name is the most frequently used object name among the at least one first object name, and the at least one third object name is an object name other than the second object name among the at least one first object name. The determining module 402 is specifically used to calculate a first reliable parameter based on the tangent value of the name similarity between the target object name and the second object name and a first numerical value; wherein the first numerical value is the ratio of the sum of the name similarities between the target object name and each third object name of the first object to the number of the at least one third object name.

[0185] In some other embodiments, the determination module 402 is specifically used to calculate a first reliable parameter using a first algorithm based on the tangent value of the name similarity between the target object name and the second object name and a first numerical value. The first algorithm is as follows: ; E is the first reliable parameter, tan(q) is the tangent of the name similarity between the target object name and the second object name, N is the number of at least one third object name, and k is the preset correction value.

[0186] In some embodiments, the first object includes at least one fourth object name. Before the generation module 401 combines different numbers of words in the target object name, the determination module 402 is further configured to determine the word similarity between the target object name and each fourth object name, and to determine at least one fourth object name whose corresponding word similarity value is greater than or equal to a similarity threshold as at least one first object name.

[0187] In other embodiments, the determining module 402 is specifically used to calculate the word similarity between the target object name and the fourth object name based on the number of words in the first set, the number of words in the second set, the number of words in the target object name, and the number of words in the fourth object name; wherein the first set is the union of the words in the target object name and the words in the fourth object name, and the second set is the intersection of the words in the target object name and the words in the fourth object name.

[0188] In other embodiments, the determination module 402 is specifically used to use a second algorithm to calculate the word similarity between the target object name and the fourth object name based on the number of words in the first set, the number of words in the second set, the number of words in the target object name, and the number of words in the fourth object name. The second algorithm is as follows: ; Let A be the word similarity between the target object name and a fourth object name, where A is the number of words in the first set, B is the number of words in the second set, a is the number of words in the target object name, and b is the number of words in a fourth object name.

[0189] In other embodiments, the object name matching device 400 provided in this application may further include an acquisition module. The acquisition module is configured to acquire at least one first object group from an object database, each first object group including object names of objects belonging to the same region, and each first object group being associated with at least one grouping rule word. The determination module 402 is further configured to, before the generation module 401 combines different numbers of words from each of the at least one first object names of the first object, determine a second object group based on words in the target object name and the grouping rule words associated with at least one first object group, the second object group including at least one first object name.

[0190] In other embodiments, the determining module 402 is specifically used to determine any first object group as a second object group if a word in the target object name matches a grouping rule word associated with any first object group; or, if a word in the target object name does not match a grouping rule word associated with at least one first object group, determine the i-th first object group as a second object group; wherein the i-th first object group is the i-th object group after sorting at least one first object group in a predetermined order, and i is a positive integer.

[0191] In other embodiments, each first object group corresponds to a priority score, and the predetermined order is in descending order of the corresponding priority scores; wherein, the priority score corresponding to a first object group is determined by a second value and a third value, the second value representing the number of objects in the region corresponding to a first object group, and the third value representing the transaction frequency between the region to which the object name matching device 400 belongs and the region corresponding to a first object group.

[0192] The object name matching device provided in this application embodiment can execute the method shown in the above method embodiment. Its implementation principle and beneficial effects can be referred to the relevant description in the method embodiment, and will not be repeated here.

[0193] Figure 13 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 13 As shown, the electronic device includes a memory 501 and at least one processor 502.

[0194] The memory 501 is used to store computer program code, which includes computer instructions. These computer instructions run in the aforementioned electronic device to implement the method shown in the above-described method embodiments. For example, the memory may include high-speed random access memory (RAM), and may also include non-volatile memory (NVM), such as at least one disk drive, or a USB flash drive, portable hard drive, read-only memory, magnetic disk, or optical disk, etc.

[0195] Processor 502 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. Processor 502 can also be other general-purpose processors. The general-purpose processor can be a microprocessor or any conventional processor.

[0196] The memory 501 and processor 502 are communicatively connected. For example, the memory 501 can be connected to the processor 502 via a system bus and communicate with it. The system bus can be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, an Industry Standard Architecture (ISA) bus, etc. The system bus can be divided into address bus, data bus, control bus, etc. For ease of representation, only one thick line is used in the figure, but this does not mean that there is only one bus or one type of bus.

[0197] Optionally, the memory 501 can be either standalone or integrated with the processor 502. When the memory 501 is set up independently, it is connected to the processor 502 via a system bus.

[0198] This application also provides a chip for executing instructions, which is used to execute the object name matching method in the above embodiments.

[0199] This application also provides a computer-readable storage medium storing computer instructions. When these computer instructions are executed by a processor, they are used to implement the technical solution of the object name matching method in the above embodiments. Specifically, when the computer instructions are executed by a processor, the electronic device can perform the technical solution of the object name matching method in the above embodiments.

[0200] This application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium, and when the at least one processor executes the computer program, it can implement the technical solution of the object name matching method in the above embodiments.

[0201] The aforementioned computer-readable storage media can be implemented from any type of volatile or non-volatile storage device or a combination thereof, such as Static Random-Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The computer-readable storage media can be any available medium accessible to a general-purpose or special-purpose computer.

[0202] An exemplary computer-readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the computer-readable storage medium can also be a component of the processor. The processor and the computer-readable storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the processor and the computer-readable storage medium can exist as discrete components in an electronic control unit or main control device; this application does not limit this.

[0203] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.

[0204] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to implement the solution of this embodiment according to actual needs.

[0205] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The unit composed of the above modules can be implemented in hardware or in the form of hardware plus software functional units.

[0206] The integrated modules described above, implemented as software functional modules, can be stored in a computer-readable storage medium. These software functional modules, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods of the various embodiments of this application.

[0207] It should be understood that the steps of the method disclosed in the embodiments of this application can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor.

[0208] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0209] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for matching object names, characterized in that, include: At least one target word group is generated by combining different numbers of words in the target object name, and at least one first word group is generated by combining different numbers of words in each of the at least one first object name of the first object. Each target phrase is combined with each first phrase corresponding to a first object name to generate at least one second phrase; Each second phrase is determined to appear in the target object name to obtain at least one first determination result, and each second phrase is determined to appear in the first object name to obtain at least one second determination result; Based on the at least one first determination result and the at least one second determination result, determine the name similarity between the target object name and the first object name; A first reliability parameter is determined based on the name similarity between the target object name and the at least one first object name. The first reliability parameter characterizes the reliability that the target object name is the object name of the first object. Based on the relationship between the parameter value of the first reliable parameter and the parameter threshold, it is determined whether the target object name is the object name of the first object.

2. The method according to claim 1, characterized in that, Determining the name similarity between the target object name and the first object name based on the at least one first determination result and the at least one second determination result includes: A first vector is generated based on the at least one first determination result, and a second vector is generated based on the at least one second determination result. The first vector includes at least one first element, each first element corresponding to a first determination result. The second vector includes at least one second element, each second element corresponding to a second determination result. Based on the similarity between the first vector and the second vector, determine the name similarity between the target object name and the first object name; Wherein, if a first determination result indicates that the corresponding second phrase appears in the name of the target object, the value of the first element corresponding to the first determination result is a first preset value; otherwise, the value is a second preset value. If a second phrase corresponding to a second determination result appears in the name of a first object, the value of the second element corresponding to the second determination result is the first preset value; otherwise, the value is the second preset value.

3. The method according to claim 1, characterized in that, The at least one first object name includes a second object name and at least one third object name, wherein the second object name is the object name that is used most frequently among the at least one first object names, and the at least one third object name is an object name other than the second object name among the at least one first object names; The step of determining the first reliable parameter based on the name similarity between the target object name and at least one first object name includes: The first reliable parameter is calculated based on the tangent of the name similarity between the target object name and the second object name and the first value. Wherein, the first value is: the ratio of the sum of the name similarity between the target object name and each third object name of the first object to the number of the at least one third object name.

4. The method according to claim 3, characterized in that, The calculation of the first reliable parameter based on the tangent of the name similarity between the target object name and the second object name and a first numerical value includes: Using the first algorithm, the first reliable parameter is calculated based on the tangent of the name similarity between the target object name and the second object name and the first value. The first algorithm is as follows: ； E is the first reliable parameter, tan(q) is the tangent of the name similarity between the target object name and the second object name, N is the number of the at least one third object name, and k is a preset correction value.

5. The method according to claim 1, characterized in that, The first object includes at least one fourth object name; Before combining words according to different numbers of words in each of at least one first object name of the first object, the method further includes: Determine the word similarity between the target object name and each fourth object name; The fourth object name whose word similarity value is greater than or equal to the similarity threshold in the at least one fourth object name is determined as the at least one first object name.

6. The method according to claim 5, characterized in that, The step of determining the word similarity between the target object name and each fourth object name includes: The word similarity between the target object name and the fourth object name is calculated based on the number of words in the first set, the number of words in the second set, the number of words in the target object name, and the number of words in the fourth object name. Wherein, the first set is the union of the words in the target object name and the words in the fourth object name, and the second set is the intersection of the words in the target object name and the words in the fourth object name.

7. The method according to claim 6, characterized in that, The step of calculating the word similarity between the target object name and the fourth object name based on the number of words in the first set, the number of words in the second set, the number of words in the target object name, and the number of words in the fourth object name includes: Using the second algorithm, the word similarity between the target object name and the fourth object name is calculated based on the number of words in the first set, the number of words in the second set, the number of words in the target object name, and the number of words in the fourth object name. The second algorithm is as follows: ； The word similarity between the target object name and the fourth object name is defined as follows: A is the number of words in the first set, B is the number of words in the second set, a is the number of words in the target object name, and b is the number of words in the fourth object name.

8. The method according to any one of claims 1 to 7, characterized in that, Before combining words according to different numbers of words in each of at least one first object name of the first object, the method further includes: Obtain at least one first object group from the object database. Each first object group includes the object name of an object belonging to the same region. Each first object group is associated with at least one grouping rule word. A second object group is determined based on the words in the target object name and the grouping rule words associated with the at least one first object group, wherein the second object group includes the at least one first object name.

9. The method according to claim 8, characterized in that, The step of determining the second object group based on words in the target object name and grouping rule words associated with at least one first object group includes: If a word in the target object name matches a grouping rule word associated with any first object group, then that first object group is identified as the second object group; or, If a word in the target object name does not match a grouping rule word associated with at least one first object group, the i-th first object group is determined as the second object group. Wherein, the i-th first object group is the i-th object group after sorting the at least one first object group in a predetermined order, and i is a positive integer.

10. The method according to claim 9, characterized in that, Each first object group corresponds to a priority score, and the predetermined order is based on the corresponding priority scores from largest to smallest. The priority score corresponding to a first object group is determined by a second value and a third value. The second value represents the number of objects in the region corresponding to the first object group, and the third value represents the transaction frequency between the region to which the electronic device belongs and the region corresponding to the first object group.

11. An object name matching device, characterized in that, include: The generation module is used to generate at least one target phrase by combining different numbers of words in the target object name, and to generate at least one first phrase by combining different numbers of words in each of the at least one first object names of the first object. Each target phrase is combined with each first phrase corresponding to a first object name to generate at least one second phrase; The determining module is used to determine whether each second phrase generated by the generating module appears in the target object name, to obtain at least one first determining result, and to determine whether each second phrase appears in the first object name, to obtain at least one second determining result; Based on the at least one first determination result and the at least one second determination result, the name similarity between the target object name and the first object name is determined; Furthermore, a first reliability parameter is determined based on the name similarity between the target object name and the name of at least one first object. The first reliability parameter characterizes the reliability that the target object name is the name of the first object. Furthermore, based on the relationship between the parameter value of the first reliable parameter and the parameter threshold, it is determined whether the target object name is the object name of the first object.

12. An electronic device, characterized in that, include: A memory and at least one processor; the memory is communicatively connected to the processor; the memory is used to store computer program code, the computer program code including computer instructions; when the processor executes the computer instructions, the electronic device performs the method as described in any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, are used to implement the method as described in any one of claims 1 to 10.

14. A computer program product, characterized in that, When the computer program product is run on a computer / executed by the computer's processor, it implements the method as described in any one of claims 1 to 10.

Images