A store identification method, device, equipment and medium

Abstract

The disclosed embodiments relate to a store identification method, device, equipment and medium, wherein the method comprises: obtaining clue model data of a candidate store; performing similarity calculation based on the clue model data of the candidate store and the store model data of the stores in the pre-constructed store network to obtain the similarity between the candidate store and each store; determining the connected store of the candidate store from each store based on the similarity and a preset similarity threshold; obtaining the initial credibility of the candidate store and the credibility of the connected store; performing calculation based on the initial credibility of the candidate store, the credibility of the connected store and the similarity between the candidate store and the connected store to obtain the target credibility of the candidate store, and determining the candidate store as the target store when the target credibility is greater than the preset credibility threshold. The above technical solution can screen out target stores with higher credibility, thereby improving the efficiency and accuracy of store identification.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a store identification method, device, equipment and medium. Background Art

[0002] Currently, in the real estate business, information management and maintenance of real estate stores has always been an important issue; unlike fixed information such as real estate projects, the actual offline operating conditions of real estate stores change rapidly, and new stores may usually be opened in a relatively short period of time.

[0003] In the related art, the real estate store information of newly opened stores is obtained through manual offline collection. However, the manual offline collection method is costly and the store discovery efficiency is relatively low, which leads to problems such as untimely store information updates. Summary of the invention

[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides a store identification method, device, equipment and medium.

[0005] The present disclosure provides a store identification method, the method comprising:

[0006] Obtain lead model data for candidate stores;

[0007] Perform similarity calculation based on the clue model data of the candidate store and the store model data of the stores in the pre-built store network to obtain the similarity between the candidate store and each store;

[0008] Determining a connected store of the candidate store from each of the stores based on the similarity and a preset similarity threshold;

[0009] Obtaining the initial credibility of the candidate store and the credibility of the connected store;

[0010] A target credibility of the candidate store is obtained based on the initial credibility of the candidate store, the credibility of the connected store, and the similarity between the candidate store and the connected store, and when the target credibility is greater than a preset credibility threshold, the candidate store is determined to be the target store.

[0011] The present disclosure also provides a store identification device, the device comprising:

[0012] The first acquisition module is used to acquire the clue model data of the candidate store;

[0013] A first calculation module, configured to perform similarity calculation based on the clue model data of the candidate store and the store model data of the stores in the pre-built store network, to obtain the similarity between the candidate store and each store;

[0014] A first determining module, configured to determine a connected store of the candidate store from each of the stores based on the similarity and a preset similarity threshold;

[0015] A second acquisition module, used to acquire the initial credibility of the candidate store and the credibility of the connected store;

[0016] A second calculation module, configured to calculate based on the initial credibility of the candidate store, the credibility of the connected store, and the similarity between the candidate store and the connected store to obtain a target credibility of the candidate store;

[0017] The second determination module is used to determine the candidate store as a target store when the target credibility is greater than a preset credibility threshold.

[0018] An embodiment of the present disclosure also provides an electronic device, comprising: a processor; a memory for storing executable instructions of the processor; the processor is used to read the executable instructions from the memory and execute the instructions to implement the store identification method provided in the embodiment of the present disclosure.

[0019] The embodiment of the present disclosure further provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the store identification method provided by the embodiment of the present disclosure.

[0020] The embodiment of the present disclosure further provides a computer program product, including a computer program, wherein the computer program implements the store identification method described in the above aspect when executed by a processor.

[0021] The technical solution provided by the embodiment of the present disclosure has the following advantages over the prior art: the store identification solution provided by the embodiment of the present disclosure obtains the clue model data of the candidate store; performs similarity calculation based on the clue model data of the candidate store and the store model data of the store in the pre-constructed store network to obtain the similarity between the candidate store and each store; determines the connected store of the candidate store from each store based on the similarity and the preset similarity threshold; obtains the initial credibility of the candidate store and the credibility of the connected store; performs calculation based on the initial credibility of the candidate store, the credibility of the connected store and the similarity between the candidate store and the connected store to obtain the target credibility of the candidate store, and when the target credibility is greater than the preset credibility threshold, determines the candidate store as the target store. By adopting the above technical solution, the similarity between the candidate store and the store in the pre-constructed store network is calculated through the clue model data of the candidate store, and the similarity is used to calculate the target credibility of the candidate store, and finally the candidate store whose target credibility is greater than the preset credibility threshold is used as the target store, so that the target store with higher credibility can be screened out, and the efficiency and accuracy of store identification can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0023] Figure 1 A flowchart of a store identification method provided by an embodiment of the present disclosure;

[0024] Figure 2 A flowchart of another store identification method provided by an embodiment of the present disclosure;

[0025] Figure 3 A schematic diagram of a pre-built store network provided in an embodiment of the present disclosure;

[0026] Figure 4 A schematic diagram of another pre-built store network provided in an embodiment of the present disclosure;

[0027] Figure 5 A schematic diagram of another pre-built store network provided in an embodiment of the present disclosure;

[0028] Figure 6 A schematic diagram of the structure of a store identification device provided in an embodiment of the present disclosure;

[0029] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0031] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0032] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0033] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0034] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0035] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0036] Currently, real estate store information is obtained through manual offline collection. In actual applications, the frequency of real estate store information update is relatively fast. The offline collection method relies on manual inspections, which is inefficient and difficult to update store information in real time. Due to manpower and time constraints, it is difficult for offline collection personnel to cover all market stores, that is, the coverage is limited, resulting in the inability to update some store information in a timely manner. Due to untimely information updates, the accuracy and consistency of the data may be affected. In addition, offline collection not only requires a large amount of human resources, but also has subsequent data review costs, resulting in relatively high economic costs.

[0037] In response to the above problems, the present disclosure proposes a method of obtaining clue model data of candidate stores; obtaining clue model data of candidate stores; performing similarity calculation based on clue model data of candidate stores and store model data of stores in a pre-constructed store network to obtain the similarity between the candidate store and each store; determining the connected stores of the candidate store from each store based on the similarity and a preset similarity threshold; obtaining the initial credibility of the candidate store and the credibility of the connected stores; performing calculation based on the initial credibility of the candidate store, the credibility of the connected stores and the similarity between the candidate store and the connected stores to obtain the target credibility of the candidate store, and determining the candidate store as the target store when the target credibility is greater than the preset credibility threshold. By adopting the above technical solution, the similarity between the candidate store and the stores in the pre-constructed store network is calculated through the clue model data of the candidate store, and the similarity is used to calculate the target credibility of the candidate store, and finally the candidate store whose target credibility is greater than the preset credibility threshold is used as the target store, so that target stores with higher credibility can be screened out, thereby improving the efficiency and accuracy of store identification.

[0038] Figure 1 The present invention provides a flow chart of a store identification method provided in an embodiment of the present invention. The method can be executed by a store identification device, wherein the device can be implemented by software and / or hardware and can generally be integrated in an electronic device. Figure 1 As shown, the method includes:

[0039] Step 101: Obtain clue model data of candidate stores.

[0040] Among them, the store can be a real estate type store, and the candidate store can be understood as one or more potential stores, that is, stores that may actually exist; the clue model data refers to the data information used to describe the candidate store, including multiple fields, and each field has corresponding field information; for example, the multiple fields include store name, store address, longitude and latitude, brand, contact information and business scope, for example, the field information corresponding to the store name is "XXX".

[0041] In the embodiments of the present disclosure, there are many ways to obtain the lead model data of the candidate stores. As an example, multiple initial lead data from multiple data sources are obtained, the multiple initial lead data are preprocessed to obtain candidate lead data, and information is extracted from the candidate lead data according to preset key fields to obtain the lead model data of the candidate stores.

[0042] As another example, multiple clue data to be processed are obtained, key fields of each clue data to be processed are identified, multiple candidate clue model data are obtained, and multiple candidate clue model data are fused, deduplicated, etc. to obtain clue model data of candidate stores. The above two methods are only examples of methods for obtaining clue model data of candidate stores, and the present disclosure does not limit the specific methods for obtaining clue model data of candidate stores.

[0043] Specifically, during the store identification process, one or more clue data related to the target type store (such as map data, registration data, etc. related to real estate stores) can be obtained, and the clue data can be processed to obtain clue model data of one or more candidate stores.

[0044] Step 102: perform similarity calculation based on the clue model data of the candidate store and the store model data of the stores in the pre-built store network to obtain the similarity between the candidate store and each store.

[0045] Among them, the pre-built store network refers to a network with stores as nodes and the similarities between stores as edges to connect the nodes. Each store in the pre-built store network has corresponding store model data. The store model data refers to the data information used to describe the stores in the pre-built store network, including multiple fields, and each field has corresponding field information; for example, the multiple fields include store name, store address, longitude and latitude, brand, contact information and business scope, for example, the field information corresponding to the store address is "YYY".

[0046] Among them, a store network is pre-constructed. Specifically, real model data of multiple real stores can be obtained, and similarity calculation is performed based on the real model data of any two real stores to obtain the real similarity between any two real stores. The connection relationship between any two real stores is determined based on the real similarity and the similarity threshold, and a pre-constructed store network is constructed based on the connection relationship with each real store as a node and the real similarity as a connecting edge. In other words, the pre-constructed store network can be determined based on the real model data of verified real stores.

[0047] It should be noted that after the pre-constructed store network is determined for the first time based on the real model data of the verified real stores, the pre-constructed store network can be continuously updated according to the store identification results. Therefore, in the embodiment of the present disclosure, each node in the pre-constructed store network can be a real store (a store that has been verified to exist) or a real store and a newly identified candidate store (a store that may exist and needs to be verified).

[0048] In the embodiments of the present disclosure, similarity calculation is performed based on the clue model data of the candidate store and the store model data of each store. There are many ways to obtain the similarity between the candidate store and each store. As an example, all the same fields in the clue model data and other clue model data are obtained; and / or, all the same fields in the clue model data and the store model data are obtained, and the field similarity between each of the same fields is calculated respectively, and all field similarities are weighted summed to obtain the similarity between the candidate store and each store.

[0049] As another example, obtain the preset target field and the weight information of each target field, calculate the field similarity between the target field in the clue model data and the target field in the clue model data respectively; and / or calculate the field similarity between the target field in the clue model data and the target field in the store model data, and finally determine the similarity between the candidate store and each store according to the weight information of each target field of the field similarity. The above two methods are only examples of performing similarity calculation based on the clue model data of the candidate store and the store model data of each store to obtain the similarity between the candidate store and each store. The present disclosure does not limit the specific method of performing similarity calculation based on the clue model data of the candidate store and the store model data of each store to obtain the similarity between the candidate store and each store.

[0050] In the disclosed embodiment, after obtaining the clue model data of the candidate store, similarity calculation can be performed based on the clue model data and the store model data of each store in the pre-built store network to obtain the similarity between the candidate store and each store, that is, the same number of similarities can be obtained as the number of stores in the pre-built store network.

[0051] Step 103: Determine a connected store of the candidate store from each store based on the similarity and a preset similarity threshold.

[0052] Among them, a similarity threshold is pre-set and can be selected and set according to the application scenario; a connected store can be understood as a store that has a connection relationship with a candidate store, and a candidate store can establish a connection relationship with a connected store to be added to the pre-built store network.

[0053] In an embodiment of the present disclosure, there are many ways to determine the connected stores of a candidate store from a pre-built store network based on the similarity and a preset similarity threshold. As an example, the similarity can be compared with the similarity threshold, and the stores corresponding to the similarity greater than or equal to the similarity threshold are selected as the connected stores of the candidate store; as another example, the similarity threshold includes a first similarity threshold and a second similarity threshold, and the similarity is greater than the second similarity threshold and less than the first similarity threshold, and the store corresponding to the similarity is determined to be the connected store of the candidate store.

[0054] Specifically, after obtaining the similarity between the candidate store and each store, one or more stores are determined from the pre-built store network as connected stores of the candidate store based on the similarity and a preset similarity threshold.

[0055] Step 104: Obtain the initial credibility of the candidate store and the credibility of the connected store.

[0056] Step 105: Calculate the target credibility of the candidate store based on the initial credibility of the candidate store, the credibility of the connected store, and the similarity between the candidate store and the connected store, and determine the candidate store as the target store when the target credibility is greater than a preset credibility threshold.

[0057] Among them, the initial credibility of the candidate store can be set in advance, that is, the probability that the candidate store is a real store. Specifically, the initial credibility of the candidate store can be set according to the number of data sources of the clue model data of the candidate store and / or the confidence of each data source, that is, the reliability of the data source, so as to improve the accuracy of subsequent store identification.

[0058] Among them, each store in the pre-built store network has a corresponding credibility. If the store is a verified real store, the corresponding credibility is 1; the credibility threshold is set in advance and can be selected and set according to the application scenario.

[0059] In the disclosed embodiment, the target credibility of the candidate store can be determined based on the initial credibility of the candidate store, the credibility of the connected store and the similarity between the candidate store and the connected store. For example, if there is one connected store, the credibility of the connected store is multiplied by the similarity and then added to the initial credibility to obtain the total credibility, and the initial credibility and the credibility of the connected store are added to obtain the sum of the credibility, and finally the total credibility is divided by the sum of the credibility to obtain the target credibility of the candidate store; for another example, if there are multiple connected stores, the credibility of the connected store can be multiplied by the similarity to obtain multiple multiplied credibility, and the multiple multiplied credibility can be added and divided by the sum of the credibility of all connected stores to obtain the target credibility of the candidate store.

[0060] Furthermore, the target credibility is compared with a preset credibility threshold, and when the target credibility is greater than the preset credibility threshold, the candidate store is determined to be the target store, that is, as a newly identified store.

[0061] Specifically, after determining the connected stores of the candidate store, the target credibility of the candidate store is determined according to the initial credibility of the candidate store, the credibility of the connected stores and the similarity between the candidate store and the connected stores, and when the target credibility is greater than a preset credibility threshold, the candidate store is determined to be the target store.

[0062] The store identification solution provided by the embodiment of the present disclosure obtains the clue model data of the candidate store; performs similarity calculation based on the clue model data of the candidate store and the store model data of the stores in the pre-constructed store network to obtain the similarity between the candidate store and each store; determines the connected store of the candidate store from each store based on the similarity and the preset similarity threshold; obtains the initial credibility of the candidate store and the credibility of the connected store; performs calculation based on the initial credibility of the candidate store, the credibility of the connected store and the similarity between the candidate store and the connected store to obtain the target credibility of the candidate store, and when the target credibility is greater than the preset credibility threshold, determines the candidate store as the target store. Using the above technical solution, the clue model data of the candidate store is used to calculate the similarity between the candidate store and the stores in the pre-constructed store network, and the similarity is used to calculate the target credibility of the candidate store, and finally the candidate store whose target credibility is greater than the preset credibility threshold is used as the target store, so that the target store with higher credibility can be screened out, thereby improving the efficiency and accuracy of store identification.

[0063] In some embodiments, obtaining the lead model data of the candidate store includes: obtaining multiple initial lead data from multiple data sources; preprocessing the multiple initial lead data to obtain candidate lead data; extracting information from the candidate lead data according to preset key fields to obtain the lead model data of the candidate store.

[0064] Among them, multiple data sources refer to different data sources such as map data, registration data or data disclosed through other channels. One or more data sources can be selected according to actual application needs to obtain multi-dimensional clue model data of candidate stores, thereby improving the accuracy of subsequent store identification.

[0065] Specifically, first determine multiple data sources, and obtain multiple initial clue data of the target type (such as real estate type) from each data source, such as real estate store information on map A, real estate store information on map B, real estate store information on real estate registration information C, and real estate store information on public document D, etc.; it is understandable that the initial clue data from different data sources may be repeated, and the data formats of different data sources are different. Therefore, it is necessary to pre-process multiple initial clue data to improve subsequent data efficiency and effectiveness.

[0066] In the embodiments of the present disclosure, there are many ways to pre-process multiple initial clue data, such as fusing multiple initial clue data from different data sources to remove redundant and repeated information, and then cleaning the fused initial clue data to remove invalid, erroneous and duplicate data, such as unifying the data formats of different data sources to ensure data consistency, deduplicating duplicate clue data, and correcting or deleting obviously erroneous data, such as incorrect address format, invalid contact information, etc.; finally, the cleaned initial clue data is checked for validity and completeness, such as checking the legitimacy of fields such as name, longitude and latitude, address, etc., and checking the integrity of necessary fields such as name, longitude and latitude, address, etc., to obtain candidate clue data.

[0067] In the disclosed embodiment, key fields are pre-set, that is, basic fields that the clue model data must include, and fields can also be customized according to actual needs, such as store name, store address, longitude and latitude, and contact information as basic fields, and brand and business scope as custom fields.

[0068] Specifically, after obtaining the candidate lead data, information can be extracted from the candidate lead data according to key fields to obtain the lead model data of the candidate store. For example, the lead model data includes multiple fields, and each field has corresponding field information; for example, multiple fields include store name, store address, longitude and latitude, brand, contact information, business scope and other fields. For example, the field information corresponding to the store name is "XXX".

[0069] In some embodiments, when obtaining clue model data of a candidate store, the initial credibility of the candidate store can be determined based on the number and confidence level of the target data source according to the target data source corresponding to the clue model data.

[0070] Specifically, the clue model data can be obtained from only one target data source or from multiple data sources, that is, one clue model data exists in multiple data sources, that is, the number of target data sources can be one or more, and the confidence of each data source is different, that is, different data sources can set confidence based on the reliability of historical data provided and user evaluation. Generally, the higher the number and confidence of target data sources, the higher the initial credibility of the candidate store.

[0071] The above solution solves the problems of limited coverage and low data accuracy of traditional offline collection methods. By integrating multiple data sources, more comprehensive and diversified clue model data can be obtained, thereby improving the coverage and accuracy of clue model data and providing a reliable data foundation for the follow-up; and setting the initial credibility of the store based on the quantity and quality of the data sources of the clue model data, thereby further improving the subsequent store identification effect.

[0072] In some embodiments, a similarity calculation is performed based on the clue model data of the candidate store and the store model data of the stores in the pre-built store network to obtain the similarity between the candidate store and each store, including: obtaining a preset target field and weight information of each target field; calculating the field similarity between the target field in the clue model data and the target field in the store model data of the stores in the pre-built store network, and determining the similarity between the candidate store and each store based on the field similarity and the weight information of each target field.

[0073] In the disclosed embodiment, the target fields and the weight information of each target field are preset, that is, the weights of different target fields can be set according to the importance of different target fields.

[0074] It can be understood that when there is only one candidate store, it is only necessary to calculate the field similarity between the target field in the lead model data of the candidate store and the target field in the store model data of the stores in the pre-built store network, and calculate based on the field similarity and the weight information of each target field to obtain the similarity between the candidate store and each store in the pre-built store network.

[0075] It can also be understood that when there are multiple candidate stores, the similarity between the candidate stores can be calculated first according to actual application needs, that is, the field similarity between the target fields in the clue model data of any two candidate stores is calculated, and the field similarity and the weight information of each target field are calculated to obtain the similarity between the candidate stores, and then the field similarity between the target field in the clue model data of the candidate store and the target field in the store model data of the store in the pre-built store network is calculated, and the field similarity and the weight information of each target field are calculated to obtain the similarity between the candidate store and each store in the pre-built store network; that is, the similarity between the candidate store and each store can be understood as the similarity between the candidate store and other candidate stores; and / or the similarity between the candidate store and each store in the pre-built store network, so that when the connected stores of the candidate store are subsequently determined, the connected stores of the candidate store can be other candidate stores or stores in the pre-built store network.

[0076] As an example, the name field similarity between the store name field in the clue model data and the store name field in the store model data of each store is calculated based on a preset string similarity algorithm; the address field similarity between the store address field in the clue model data and the store address field in the store model data of each store is calculated based on a string similarity algorithm; the longitude and latitude field similarity between the longitude and latitude fields in the clue model data and the longitude and latitude fields in the store model data of each store is calculated based on a preset geographic location similarity algorithm; the contact information field similarity between the contact information field in the clue model data and the contact information field in the store model data of each store is calculated based on a string similarity algorithm; based on the name field similarity, address field similarity, longitude and latitude field similarity and contact information field similarity and preset weight information, such as the corresponding name field weight value, address field weight value, longitude and latitude field weight value and contact information field weight value, a weighted summation calculation is performed to obtain the similarity between the candidate store and each store.

[0077] It should be noted that the brand field, business scope field, etc. can also be used to calculate field similarity according to actual application needs, and used to determine the similarity between the candidate store and each store; it can also be understood that only one or more of the above fields can be selected for deletion and not used to determine the similarity between the candidate store and each store, thereby further improving flexibility and meeting the usage requirements of different scenarios.

[0078] In the above scheme, the similarity between the candidate store and each store can be flexibly and accurately calculated, so that the subsequent determination of the connected stores is more accurate to ensure that the candidate stores obtain accurate target credibility, further improving the effect of store identification.

[0079] In some embodiments, the similarity threshold includes a first similarity threshold and a second similarity threshold, and the connected stores of the candidate store are determined from each store based on the similarity and the preset similarity threshold, including: when the similarity is greater than the second similarity threshold and less than the first similarity threshold, the store corresponding to the similarity is determined as the connected store of the candidate store.

[0080] Among them, the similarity threshold is set in advance and can be selected and set according to actual application needs. For example, a first similarity threshold and a second similarity threshold are set, and the first similarity threshold is greater than the second similarity threshold, so that the similarity between all candidate stores and each store is compared with the first similarity threshold and the second similarity threshold. If the similarity is greater than the second similarity threshold and less than the first similarity threshold, the store corresponding to the similarity is determined as the connected store of the candidate store, and when the candidate store is added to the pre-built store network, a connection relationship between the candidate store and the connected store is established.

[0081] It should be noted that, if the similarity is greater than or equal to the first similarity threshold, the store corresponding to the similarity is marked as the same store as the candidate store, that is, when the candidate store is added to the pre-built store network, the store corresponding to the similarity is the same node as the candidate store; if the similarity is less than or equal to the second similarity threshold, it is determined that there is no connected store of the candidate store in the pre-built store network, that is, when the similarity reaches a certain threshold, it is determined to be the same store; if the similarity is lower than a certain threshold, the two stores have no association relationship, that is, when the candidate store is added to the pre-built store network, the store corresponding to the similarity has no connection relationship with the candidate store.

[0082] In the above scheme, connected stores are screened by setting a similarity threshold, so as to obtain connected stores that have an associated relationship with the candidate stores to assist in determining the target credibility of the candidate stores, thereby improving the accuracy of store identification, and accurately adding candidate stores to the pre-built store network, further improving the subsequent store identification effect.

[0083] In some embodiments, the connected store is a store to be verified, and the method further includes: calculating based on the initial credibility of the candidate store, the similarity between the candidate store and the connected store, and the credibility of the connected store to obtain the current credibility of the connected store, and updating the credibility of the connected store to the current credibility.

[0084] In the disclosed embodiment, the credibility of stores in the pre-built store network can be dynamically adjusted. It can be understood that the credibility of verified real stores is 1, and the candidate stores to be verified need to update the corresponding credibility according to the dynamic changes of the pre-built store network.

[0085] Specifically, when it is determined that a connected store of a candidate store is also a store to be verified, it is necessary to calculate the current credibility of the connected store based on the initial credibility of the candidate store, the similarity between the candidate store and the connected store, and the credibility of the connected store, and update the credibility of the connected store to the current credibility.

[0086] It should be noted that in order to further ensure the store identification effect, the clue model data of the candidate store can be tested according to the preset standard model data; and / or the current credibility can be tested according to the preset credibility setting information. When the detection result is abnormal, the candidate store and / or the current credibility can be processed according to the preset processing strategy.

[0087] Specifically, standard model data is pre-set, such as what data the store name cannot include, the format of the store address, etc. When the clue model data of a candidate store does not meet the standard model data, the candidate store will not be added to the pre-built store network or the candidate store already in the pre-built store network will be deleted. In addition, credibility setting information is pre-set, such as the numerical range and format of the credibility. When the current credibility does not meet the credibility setting information, the credibility of the connected store may not be updated to the current credibility.

[0088] It should be noted that before the connected store updates its credibility, the credibility of the connected store is less than or equal to the credibility threshold, and the connected store is not used as a target store. After the credibility of the connected store is updated to the current credibility, it can be further determined whether the current credibility of the connected store is greater than the credibility threshold. If the current credibility is greater than the credibility threshold, the connected store can be used as a target store. By dynamically updating the credibility, the real-time and accuracy of the data is ensured, thereby improving the accuracy of store identification.

[0089] In the above scheme, by dynamically updating the credibility of the stores to be verified, the real-time and accuracy of the data is ensured, the effect of store screening is optimized, thereby improving the efficiency and effectiveness of store identification.

[0090] In some embodiments, the method further includes: generating a collection task based on the clue model data of the target store; determining the target collection subject based on the collection subject's geographic location, workload information, and task priority information of the collection task, and sending the collection task to the target collection subject.

[0091] Among them, the collection subject can be a collection person, or equipment such as a collection robot, and the specific settings are selected according to the actual application.

[0092] Specifically, after determining the target store, it can be determined that the probability that the target store is a new store is relatively high. Therefore, the clue model data of the target store is used as effective clue data, and a collection task is generated based on the clue model data of the target store, such as a collection task for verifying the store name, contact information and other information within a certain range of store addresses within a certain period of time. At the same time, based on the geographical location of the collection subject, the workload information of the collection subject, such as the existing collection tasks, and the task priority of the collection task (that is, the corresponding priority can be set according to the requirements such as the importance level of the target store), a target collection subject is finally determined, and the collection task is sent to the target collection subject.

[0093] In some embodiments, the method also includes: obtaining information collection results of the target store; determining that the target store is a real store based on the information collection results, and setting the credibility of the target store to a first target value; wherein the first target value is greater than the credibility of the target store; determining that the target store is not a real store based on the information collection results, and setting the credibility of the target store to a second target value; wherein the second target value is less than the credibility of the target store.

[0094] The first target value and the second target value can be set according to actual application needs. Usually, the first target value is greater than the second target value, for example, the first target value is 1 and the second target value is 0.

[0095] Specifically, the screened valid clue data (the clue model data of the target store) is used to generate specific collection tasks, and the collection tasks are dynamically allocated according to the geographical location of the collection subject, workload information, and collection task priority.

[0096] In the above solution, through automated task distribution and intelligent scheduling, the efficiency of task allocation and execution is improved, the process of new store discovery is optimized, and the problems of low efficiency and high economic cost of traditional offline collection methods are solved.

[0097] In some embodiments, the method also includes: obtaining real model data of multiple real stores; performing similarity calculation based on the multiple real model data to obtain the real similarity between any two real stores; determining the connection relationship between any two real stores based on the real similarity and the similarity threshold; and constructing a pre-constructed store network based on the connection relationship with each real store as a node and the real similarity as a connecting edge.

[0098] In an embodiment of the present disclosure, a preconstructed store network can be preconstructed. Specifically, the field similarity between the target field in the real model data and the target field in other real model data is calculated, and the real similarity between two real stores is determined based on the weight information of each target field of the field similarity. The connection relationship between two real stores corresponding to a similarity greater than or equal to a certain similarity threshold is determined to be a connection. On the contrary, the connection relationship between two real stores corresponding to a similarity less than a certain similarity threshold is considered to have no connection relationship. Finally, a preconstructed store network is constructed according to the connection relationship with each real store as a node and the real similarity as a connecting edge.

[0099] In some embodiments, the similarity between the candidate store and the connected store is used as a connecting edge, and the candidate store is connected to the connected store as a new node to add the candidate store to the pre-built store network.

[0100] It can be understood that during the store identification process, the nodes in the pre-built store network can change dynamically. Candidate stores can be added to the pre-built store network one by one, or multiple candidate stores can be pre-connected and added to the pre-built store network as a whole. The specific settings can be selected according to the actual application scenario.

[0101] Specifically, after obtaining the similarity between the candidate store and the connected store, the similarity between the candidate store and the connected store is used as a connecting edge, and the candidate store is connected to the connected store as a new node to add the candidate store to the pre-built store network.

[0102] In the above scheme, by calculating the similarity between stores based on real model data, a pre-constructed store network is established, and the target credibility of candidate stores is calculated based on the pre-constructed store network. Stores with higher credibility are selected as target stores, thereby further improving the accuracy of store identification.

[0103] Figure 2 This is a flow chart of another store identification method provided by an embodiment of the present disclosure. This embodiment further optimizes the above-mentioned store identification method based on the above-mentioned embodiment. Figure 2 As shown, the method includes:

[0104] Step 201: Acquire multiple initial clue data from multiple data sources, pre-process the multiple initial clue data to obtain candidate clue data, extract information from the candidate clue data according to preset key fields, and obtain clue model data of the candidate store.

[0105] In an embodiment of the present disclosure, a target data source corresponding to clue model data of a candidate store is obtained, and an initial credibility of the candidate store is determined based on the number and confidence of the target data source.

[0106] Specifically, the initial clue data from different data sources are accessed and integrated, and the initial clue data are cleaned and verified for validity, etc., to output standardized clue model data. Among them, the initial clue data of real estate store types from different data sources, such as map data, registration information, and other channels of public data, are used to obtain the initial clue data of real estate store types; the standardized clue model data includes fields such as store name, address, latitude and longitude, brand, contact information, business scope, and specific field information corresponding to each field.

[0107] More specifically, initial clue data are accessed from different data sources to ensure data diversity and coverage, and the initial clue data from different data sources are merged to remove redundant and repeated information; wherein, for the same initial clue data, if it appears in multiple data sources, the initial credibility of the initial clue data (corresponding candidate store) will be higher, or the confidence of the data source corresponding to the initial clue data is relatively high, so the initial credibility of the initial clue data can be adjusted, thereby further improving the subsequent store recognition accuracy.

[0108] Furthermore, the fused initial clue data is cleaned to remove invalid, erroneous and duplicate data. Specifically, the data formats of different data sources are unified to ensure data consistency; duplicate initial clue data is deduplicated; and obviously erroneous data is corrected or deleted, such as incorrect address format, invalid contact information, etc.; then the cleaned data is validated and completeness checked to ensure that the data meets the clue model standards. Specifically, the validity check includes the legality of fields such as name, longitude and latitude, address, etc.; the completeness check includes the integrity of necessary fields such as name, longitude and latitude, address, etc.; the field information corresponding to the key fields is extracted from the cleaned and checked data to generate standardized clue model data, including clue model data such as store name, address, longitude and latitude, brand, contact information, business scope, etc., and output in accordance with the defined standard clue model format to ensure data standardization and consistency.

[0109] As a result, it is possible to effectively access and integrate clue data from different data sources, perform data cleaning and verification, and output standardized clue model data, providing a reliable data basis for subsequent clue credibility calculation and task management. In addition, the credibility of clue data can be cross-verified through multiple independent data sources to reduce the deviation caused by a single data source.

[0110] Therefore, by obtaining multi-dimensional potential store lead data and performing data fusion, we can obtain more comprehensive and diversified lead data, improve the coverage and accuracy of lead data, and provide a reliable data foundation for the follow-up, thus solving the problems of limited coverage and low data accuracy of traditional offline collection methods.

[0111] Step 202: Obtain preset target fields and weight information of each target field.

[0112] Step 203: Calculate the field similarity between the target field in the clue model data and the target field in the store model data of the stores in the pre-built store network, and determine the similarity between the candidate store and each store based on the field similarity and the weight information of each target field.

[0113] It is understandable that after obtaining the clue model data of the candidate stores, it is necessary to evaluate the credibility of the clue model data and screen out the candidate stores with higher credibility as the target stores.

[0114] In an embodiment of the present disclosure, real model data of multiple real stores are obtained, similarity is calculated based on the multiple real model data to obtain the real similarity between any two real stores, the connection relationship between any two real stores is determined based on the real similarity and a similarity threshold, and a pre-constructed store network is constructed based on the connection relationship with each real store as a node and the real similarity as a connecting edge.

[0115] For example, Figure 3 The pre-built store network shown includes real store S1, real store S2 and real store S3; Figure 4 The pre-built store network shown includes real store S1, real store S2, real store S3, and candidate store C1. Figure 3 and Figure 4 The stores shown in the figure are nodes, and the edge connecting the two stores represents the similarity between the two stores, such as "0.3", "0.5" and "0.6" shown in the figure.

[0116] Specifically, the target field can be set according to actual application selection, such as store name, address, longitude and latitude, etc. When the number of candidate stores is one, it is only necessary to calculate the similarity between the target field in the clue model data and the target field in the store model data of the store in the pre-built store network, wherein the clue model data includes standard clue fields, such as store name, address, brand, longitude and latitude, contact information, business scope, etc.; the store model data is verified real offline store data, containing the same standard fields as the clue model data.

[0117] For example, similarity calculation is performed through standard fields (such as store name, store address, etc.). For example, the similarity calculation of store name and store address can use string similarity algorithm (such as Jaccard similarity, Levenshtein distance, etc.) to calculate the similarity of store name and store address; the longitude and latitude similarity calculation can use geographic location similarity algorithm (such as Haversine formula) to calculate the similarity of store address; the contact information similarity calculation can use string similarity algorithm to calculate the similarity of contact information; finally, the field similarity of all fields is normalized to obtain the similarity between the candidate store and the store in the pre-built store network.

[0118] It can also be understood that when the number of candidate stores is at least two, it is also necessary to calculate the field similarity between the target fields in the clue model data of any two candidate stores and determine the similarity between the two candidate stores based on the weight information of each target field.

[0119] Step 204: if the similarity is greater than or equal to the first similarity threshold, the store corresponding to the similarity is marked as the same store as the candidate store; if the similarity is less than or equal to the second similarity threshold, a connected store without the candidate store in the pre-built store network is determined; if the similarity is greater than the second similarity threshold and less than the first similarity threshold, the store corresponding to the similarity is determined as a connected store of the candidate store.

[0120] Specifically, two stores with high similarity indicate that the correlation between the two stores is higher. When the similarity reaches a certain threshold, they are determined to be the same store; when the similarity is lower than a certain threshold, the two stores have no association.

[0121] For example, Figure 5 As shown, the similarity between the candidate store C1 and the real store S1 is greater than or equal to the first similarity threshold, for example, the first similarity threshold is 0.8. Figure 5 The similarity between the candidate store C1 and the real store S1 is 0.9, which is greater than 0.8. The candidate store C1 and the real store S1 are marked as the same store. The similarity between the candidate store C2 and the real store S2 is greater than the second similarity threshold and less than the first similarity threshold. For example, the second similarity threshold is 0.2, and the similarity between the candidate store C2 and the real store S2 is 0.3, which is greater than 0.2 and less than 0.9. The candidate store C2 and the real store S2 are connected. Figure 5 The similarity between candidate store C2 and real store S3 is 0.5, which is greater than 0.2 and less than 0.8, so candidate store C2 and real store S3 are connected; the similarity between candidate store C3 and real store S2 is 0.4, which is greater than 0.2 and less than 0.9, so candidate store C3 and real store S2 are connected, the similarity between candidate store C3 and real store S3 is less than or equal to the second similarity threshold, the similarity between candidate store C3 and real store S3 is 0.1, which is less than 0.2, so candidate store C3 and real store S3 have no association relationship.

[0122] After step 204, step 205 and / or step 206 and / or step 207 may be executed. The execution order of step 204 to step 207 may be determined according to actual conditions. Figure 2 These are examples only.

[0123] Step 205: Calculate the target credibility of the candidate store based on the initial credibility of the candidate store, the credibility of the connected stores, and the similarity between the candidate store and the connected stores, and determine the candidate store as the target store when the target credibility is greater than a preset credibility threshold.

[0124] Specifically, based on the calculated target credibility, target stores with higher credibility are screened out, that is, a credibility threshold is set, and the lead model data of candidate stores exceeding the credibility threshold are considered to be valid leads. The screened out valid leads are output in the standard lead model format defined by the system to ensure the standardization and consistency of the data.

[0125] Step 206: Obtain the initial credibility of the candidate store and the credibility of the connected store, calculate based on the initial credibility of the candidate store, the similarity between the candidate store and the connected store, and the credibility of the connected store, obtain the current credibility of the connected store, and update the credibility of the connected store to the current credibility.

[0126] Step 207: Using the similarity between the candidate store and the connected store as a connecting edge, the candidate store is connected to the connected store as a new node to add the candidate store to the pre-built store network.

[0127] Specifically, the initial credibility of the obtained candidate stores is set according to the number of data sources and confidence of their clue model data, and then the credibility of the pre-built store network is recalculated, that is, the credibility of the stores to be verified is updated.

[0128] In the embodiments of the present disclosure, the clue model data of the candidate store is detected according to the preset standard model data; and / or the current credibility is detected according to the preset credibility setting information, and when the detection result is abnormal, the candidate store and / or the current credibility is processed according to the preset processing strategy.

[0129] Specifically, an anomaly detection mechanism can be performed during the update process to identify and filter out possible abnormal nodes and edges, thereby reducing the impact of noise data.

[0130] In this way, the credibility of lead data can be effectively evaluated, the pre-built store network can be updated, and valid leads with higher credibility can be screened out, providing a reliable data foundation for subsequent task management and intelligent scheduling.

[0131] Specifically, operations such as similarity calculation and dynamic update of credibility are used to evaluate the credibility of clue data.

[0132] Therefore, through credibility calculation, valid store data with higher credibility can be screened out, the accuracy of store screening can be improved, and dynamic updates can ensure the real-time and accuracy of the data, optimize the effect of store screening, and solve the problems of low efficiency and poor data accuracy of traditional offline collection methods.

[0133] For example, continue with Figure 5 For example, Figure 5 C4 in the figure is a newly added candidate store. The target credibility of C4 can be determined based on the initial credibility of C4, the credibility of S2, and the similarity between the two stores. Figure 5 C5 in the figure is a newly added candidate store, and C3 connected to it is a store to be verified. The credibility of C3 can be updated according to the initial credibility of C5 and the similarity between the two stores, and then the credibility of C3 can be updated according to the credibility of C3 in turn, so as to update the credibility of the nodes of the pre-built store network as a whole, and further improve the data reliability.

[0134] Step 208: Generate a collection task based on the clue model data of the target store, determine the target collection subject based on the geographical location, workload information and task priority information of the collection task of the collection subject, and send the collection task to the target collection subject.

[0135] After step 205, steps 208 to 209 may be executed. The specific execution order is Figure 2 Just an example.

[0136] Step 209, obtaining the information collection results of the target store, determining that the target store is a real store based on the information collection results, and setting the credibility of the target store to a first target value; wherein the first target value is greater than the credibility of the target store, determining that the target store is not a real store based on the information collection results, and setting the credibility of the target store to a second target value; wherein the second target value is less than the credibility of the target store.

[0137] Specifically, when the clue model data of the target store is collected and verified offline, the credibility of the store in the pre-built store network will be updated again. The verified clue model data will affect the credibility of its adjacent nodes and gradually spread to the entire network, further improving the subsequent recognition accuracy, so that the credibility of the clues can be dynamically updated according to the offline collection results.

[0138] Specifically, the clue model data of the screened target stores are used as effective clue data to automatically generate collection tasks, and sent to offline collection entities. At the same time, the collection tasks are dynamically allocated according to the geographical location, workload information and collection task priority of the collection entity; that is to say, the specific tasks assigned to the collection personnel can be determined based on the clue model data with higher credibility, the geographical location and workload information of the collection entity, and the collection task priority, that is, the collection tasks are generated according to the clue model data, and the collection tasks are dynamically allocated using the intelligent scheduling algorithm to improve the efficiency of task allocation and execution, thereby ensuring the rationality and executability of the tasks.

[0139] Therefore, through automated task distribution and intelligent scheduling, the efficiency of task allocation and execution is improved, the process of new store discovery is optimized, and the problems of low efficiency and high economic cost of traditional offline collection methods are solved.

[0140] The store identification solution provided by the embodiment of the present disclosure obtains clue model data of candidate stores by accessing and integrating multiple data sources for calculating the similarity between stores, determines the credibility of the candidate stores based on the pre-built store network, screens the candidate stores with higher credibility as target stores, and uses the clue model data of the target store as an effective clue to generate a specific collection task, thereby improving the efficiency and accuracy of offline collection and reducing the overall economic cost. After the collection is completed, the credibility is updated according to the audited collection results, so that the credibility calculation is more accurate, which not only improves the accuracy and consistency of the data, but also continuously optimizes the pre-built store network to make it more efficient and reliable in future applications. In other words, the present disclosure not only improves the efficiency and accuracy of data collection, but also solves the problems of limited coverage and high economic cost of traditional offline collection methods. By adjusting the credibility through collection, the accuracy and reliability are further improved, which provides strong support for the management and maintenance of store information, and can significantly improve the efficiency and accuracy of new store discovery in the real estate market, cover a wider range of market stores, and optimize the process and effect of new store discovery.

[0141] Figure 6 This is a schematic diagram of the structure of a store identification device provided by an embodiment of the present disclosure. The device can be implemented by software and / or hardware and can generally be integrated into an electronic device. Figure 6 As shown, the device comprises:

[0142] The first acquisition module 301 is used to acquire clue model data of candidate stores;

[0143] A first calculation module 302 is used to perform similarity calculation based on the clue model data of the candidate store and the store model data of the stores in the pre-built store network to obtain the similarity between the candidate store and each store;

[0144] A first determining module 303, configured to determine a connected store of the candidate store from each of the stores based on the similarity and a preset similarity threshold;

[0145] A second acquisition module 304 is used to acquire the initial credibility of the candidate store and the credibility of the connected store;

[0146] A second calculation module 305 is used to calculate based on the initial credibility of the candidate store, the credibility of the connected store, and the similarity between the candidate store and the connected store to obtain the target credibility of the candidate store;

[0147] The second determination module 306 is configured to determine the candidate store as a target store when the target credibility is greater than a preset credibility threshold.

[0148] Optionally, the first acquisition module 301 is specifically configured to:

[0149] Obtain multiple initial clue data from multiple data sources;

[0150] Preprocessing the multiple initial clue data to obtain candidate clue data;

[0151] Information is extracted from the candidate lead data according to preset key fields to obtain lead model data of the candidate store.

[0152] Optionally, the device further comprises:

[0153] A second acquisition module is used to acquire a target data source corresponding to the clue model data of the candidate store;

[0154] The third determination module is used to determine the initial credibility of the candidate store based on the number and confidence of the target data source.

[0155] Optionally, the first calculation module 302 is specifically configured to:

[0156] Obtaining preset target fields and weight information of each of the target fields;

[0157] When the number of the candidate store is one, calculating the first field similarity between the target field in the clue model data and the target field in the store model data of the stores in the pre-built store network, and determining the similarity between the candidate store and each of the stores according to the first field similarity and the weight information of each of the target fields; or,

[0158] When the number of the candidate stores is at least two, the second field similarity between the target fields in the clue model data of any two of the candidate stores is calculated, and the similarity between the candidate store and each of the stores is determined based on the first field similarity, the second field similarity and the weight information of each of the target fields.

[0159] Optionally, the first determining module 303 is specifically configured to:

[0160] The similarity is greater than the second similarity threshold and less than the first similarity threshold, and the store corresponding to the similarity is determined to be a connected store of the candidate store.

[0161] Optionally, the device further comprises:

[0162] The first processing module is used to mark the store corresponding to the similarity as the same store as the candidate store when the similarity is greater than or equal to the first similarity threshold; or, when the similarity is less than or equal to the second similarity threshold, determine that there is no connected store of the candidate store in the pre-built store network.

[0163] Optionally, the device further comprises:

[0164] A third calculation module, configured to calculate based on the initial credibility of the candidate store, the similarity between the candidate store and the connected store, and the credibility of the connected store to obtain the current credibility of the connected store;

[0165] An updating module is used to update the credibility of the connected store to the current credibility.

[0166] Optionally, the device further comprises:

[0167] A detection module, used to detect the clue model data of the candidate store according to the preset standard model data; and / or to detect the current credibility according to the preset credibility setting information;

[0168] The second processing module is used to process the candidate store and / or the current credibility according to a preset processing strategy when the detection result is abnormal.

[0169] Optionally, the device further comprises:

[0170] A generation module, used to generate a collection task based on the clue model data of the target store;

[0171] The fourth determination module is used to determine the target collection subject based on the geographical location of the collection subject, the workload information and the task priority information of the collection task, and send the collection task to the target collection subject.

[0172] Optionally, the device further comprises:

[0173] A third acquisition module is used to obtain the information collection results of the target store;

[0174] A setting module, configured to determine that the target store is a real store based on the information collection result, and set the credibility of the target store to a first target value; wherein the first target value is greater than the credibility of the target store;

[0175] The setting module is further used to determine that the target store is not a real store based on the information collection result, and set the credibility of the target store to a second target value; wherein the second target value is less than the credibility of the target store.

[0176] Optionally, the device further comprises:

[0177] A fourth acquisition module is used to acquire real model data of multiple real stores;

[0178] A fourth calculation module, configured to perform similarity calculation based on the plurality of real model data to obtain a real similarity between any two of the real stores;

[0179] a fifth determining module, configured to determine a connection relationship between any two of the real stores based on the real similarity and the similarity threshold;

[0180] A construction module is used to construct the pre-constructed store network based on the connection relationship, with each of the real stores as a node and the real similarity as a connection edge.

[0181] Optionally, the device further comprises:

[0182] An adding module is used to connect the candidate store to the connected store as a new node using the similarity between the candidate store and the connected store as a connecting edge, so as to add the candidate store to the pre-built store network.

[0183] The store identification device provided in the embodiments of the present disclosure can execute the store identification method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0184] The embodiments of the present disclosure also provide a computer program product, including a computer program / instruction, which, when executed by a processor, implements the store identification method provided by any embodiment of the present disclosure.

[0185] Figure 7 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Figure 7, which shows a schematic diagram of the structure of an electronic device 400 suitable for implementing the embodiment of the present disclosure. The electronic device 400 in the embodiment of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0186] like Figure 7 As shown, the electronic device 400 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage device 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 are also stored. The processing device 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0187] Typically, the following devices may be connected to the I / O interface 405: an input device 406 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 409. The communication device 409 may allow the electronic device 400 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 7 The electronic device 400 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0188] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 409, or installed from the storage device 408, or installed from the ROM 402. When the computer program is executed by the processing device 401, the above-mentioned functions defined in the store identification method of the embodiment of the present disclosure are executed.

[0189] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0190] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0191] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0192] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains clue model data of the candidate store; performs similarity calculation based on the clue model data of the candidate store and the store model data of the stores in the pre-built store network to obtain the similarity between the candidate store and each store; determines the connected stores of the candidate store from each store based on the similarity and a preset similarity threshold; calculates based on the initial credibility of the candidate store, the credibility of the connected stores and the similarity between the candidate store and the connected stores to obtain the target credibility of the candidate store, and when the target credibility is greater than the preset credibility threshold, determines the candidate store as the target store.

[0193] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0194] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0195] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0196] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0197] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0198] According to one or more embodiments of the present disclosure, the present disclosure provides an electronic device, including:

[0199] processor;

[0200] a memory for storing instructions executable by the processor;

[0201] The processor is used to read the executable instructions from the memory and execute the instructions to implement any store identification method provided in the present disclosure.

[0202] According to one or more embodiments of the present disclosure, the present disclosure provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute any store identification method as provided in the present disclosure.

[0203] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0204] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0205] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A store identification method, characterized in that: include: Obtain lead model data for candidate stores; Perform similarity calculation based on the clue model data of the candidate store and the store model data of the stores in the pre-built store network to obtain the similarity between the candidate store and each store; Determining a connected store of the candidate store from each of the stores based on the similarity and a preset similarity threshold; Obtaining the initial credibility of the candidate store and the credibility of the connected store; A target credibility of the candidate store is obtained based on the initial credibility of the candidate store, the credibility of the connected store, and the similarity between the candidate store and the connected store, and when the target credibility is greater than a preset credibility threshold, the candidate store is determined to be the target store.

2. The method according to claim 1, characterized in that: The step of obtaining the clue model data of the candidate store includes: Obtain multiple initial clue data from multiple data sources; Preprocessing the multiple initial clue data to obtain candidate clue data; Information is extracted from the candidate lead data according to preset key fields to obtain lead model data of the candidate store.

3. The method according to claim 2, characterized in that The method further comprises: Obtaining a target data source corresponding to the clue model data of the candidate store; The initial credibility of the candidate store is determined based on the quantity and confidence of the target data sources.

4. The method according to claim 1, characterized in that: The similarity calculation based on the clue model data of the candidate store and the store model data of the stores in the pre-built store network to obtain the similarity between the candidate store and each store includes: Obtaining preset target fields and weight information of each of the target fields; Calculating field similarity between a target field in the lead model data and a target field in the store model data of a store in the pre-built store network; The similarity between the candidate store and each of the stores is determined according to the first field similarity and the weight information of each of the target fields.

5. The method according to claim 1, characterized in that The connected store is a store to be verified, and the method further includes: Calculating based on the initial credibility of the candidate store, the similarity between the candidate store and the connected store, and the credibility of the connected store to obtain the current credibility of the connected store; The credibility of the connected store is updated to the current credibility.

6. The method according to claim 1, characterized in that The method further comprises: Generate a collection task based on the clue model data of the target store; A target collection subject is determined based on the geographical location of the collection subject, the workload information, and the task priority information of the collection task, and the collection task is sent to the target collection subject.

7. The method according to claim 1, characterized in that The method further comprises: Obtaining information collection results of the target store; Determining that the target store is a real store based on the information collection result, and setting the credibility of the target store to a first target value; wherein the first target value is greater than the credibility of the target store; Based on the information collection result, it is determined that the target store is not a real store, and the credibility of the target store is set to a second target value; wherein the second target value is less than the credibility of the target store.

8. The method according to claim 1, characterized in that The method further comprises: Obtain real model data from multiple real stores; Performing similarity calculation based on the plurality of real model data to obtain the real similarity between any two real stores; Determine a connection relationship between any two of the real stores based on the real similarity and the similarity threshold; The pre-constructed store network is constructed based on the connection relationship with each of the real stores as a node and the real similarity as a connection edge.

9. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the store identification method described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the store identification method described in any one of claims 1 to 8.

11. A computer program product, characterized in that The method comprises a computer program, wherein the computer program is executed by a processor to perform the store identification method described in any one of claims 1 to 8.

Images